Refresh evidence after stale lock guard
This commit is contained in:
yaojingang
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
|
||||
},
|
||||
"compatibility": {
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16T16:15:39Z",
|
||||
"generated_at": "2026-06-17",
|
||||
"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"
|
||||
}
|
||||
|
||||
@@ -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`
|
||||
|
||||
@@ -3,23 +3,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 56,
|
||||
"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/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/compiled_targets.json",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/evidence_consistency.md",
|
||||
" M reports/install_simulation.json"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f",
|
||||
"evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379",
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -34,29 +47,30 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
"world-class source checks are not all accepted (7/13 pass, 6 blocked)"
|
||||
"world-class source checks are not all accepted (6/13 pass, 7 blocked)"
|
||||
],
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"ready": false,
|
||||
"commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -64,7 +78,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f"
|
||||
"sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -137,8 +151,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7965,
|
||||
"sha256": "6334c2f0261c2c978ebcb518cdac4ddf409f41e3732b08998c8e4b80529e446d"
|
||||
"bytes": 7967,
|
||||
"sha256": "6450488d6ac4f80b0160161d5385bbf2f6aec2856076621a81027ae5c89fa38a"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -187,84 +201,84 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "dfd07c1825de99435bd661e2663ae74251bbe03cb5ddda66d268efb6a872eb31"
|
||||
"sha256": "8683ab3f627c2fe16c77dabe34798d2fb6942bb05c636cc35e4f6edd617c79d5"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "a27941fdb8651371fc7abc69247e15cf8e2863d5805b0538d67c326d4095148f"
|
||||
"sha256": "1372317d59e9ff19cfa4f69bfcfb5ddb9a9770f5628d9454a8f165e363c5b95b"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8758,
|
||||
"sha256": "5269d6e6364aaa39e935cbf02df7569a6a88d2653120bc6e3e34d3684a73639d"
|
||||
"bytes": 8604,
|
||||
"sha256": "3a707c08d4b0df167b835215f0f7696568a5a1e4099854d8a02647cdcd5b8b37"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
"path": "reports/skill_os2_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 14310,
|
||||
"sha256": "390d0bb42652e9f84fcab195de1da3c9cda213c254fd9319d31c54dd8429aee7"
|
||||
"sha256": "453a86240e7fe1a703615ba3ce9a97d940e9c552ee9e39d5cccbf7c3481dd507"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_plan",
|
||||
"path": "reports/world_class_evidence_plan.json",
|
||||
"exists": true,
|
||||
"bytes": 20828,
|
||||
"sha256": "9b74155fb9bfe44ba838d64b1a31768b83978b154bdd8eaa606f494c816f189f"
|
||||
"sha256": "0a836a86ad6c648d8c442a16cae7cdb17d3640a0ba6ec69c1290825ede6d152a"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_ledger",
|
||||
"path": "reports/world_class_evidence_ledger.json",
|
||||
"exists": true,
|
||||
"bytes": 22285,
|
||||
"sha256": "f6e1a69b0359c28c88e9e9e69ff66763c721ac8a112a43a673ce98cd9d3bce41"
|
||||
"bytes": 22288,
|
||||
"sha256": "fe81833eab69292525975b347177bc7fcda6410f493fc60bd840a20e86ca0039"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_intake",
|
||||
"path": "reports/world_class_evidence_intake.json",
|
||||
"exists": true,
|
||||
"bytes": 19319,
|
||||
"sha256": "46f801051ec075725059e4e2682ef2162fd892b5e7255c8d5121d7b24dcc7f2c"
|
||||
"sha256": "4506c836338c65a3a01b15b1f26a1fdd0a8ef520a1e5f1574ee89ce9d3bbeb29"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_preflight",
|
||||
"path": "reports/world_class_evidence_preflight.json",
|
||||
"exists": true,
|
||||
"bytes": 41202,
|
||||
"sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454"
|
||||
"bytes": 41208,
|
||||
"sha256": "725d10a6f951ab1e64f4e6a1cfa907404b51f598a753b5a0351e1381fef7cd9e"
|
||||
},
|
||||
{
|
||||
"label": "world_class_submission_review",
|
||||
"path": "reports/world_class_submission_review.json",
|
||||
"exists": true,
|
||||
"bytes": 13655,
|
||||
"sha256": "9fbd4cd437986fca9a043cbab24aec7d575aaf166a8d9365c79c56f093cab5b8"
|
||||
"bytes": 13658,
|
||||
"sha256": "7693638c2e8369a8a179b3420c11090668f8f104f452dc370082dc9ebafe882d"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook",
|
||||
"path": "reports/world_class_operator_runbook.json",
|
||||
"exists": true,
|
||||
"bytes": 24835,
|
||||
"sha256": "2d32a2e917b7215afe7a7a93ca8bacffa540a245953aa39e2ee47eea1b169d17"
|
||||
"bytes": 24899,
|
||||
"sha256": "f90d59c3e5866da33138869c1c5299350a43389d81e84ba466df794befb494fa"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_markdown",
|
||||
"path": "reports/world_class_operator_runbook.md",
|
||||
"exists": true,
|
||||
"bytes": 15424,
|
||||
"sha256": "00d8ebabb91e14a06cacdb212f448668aa1e47b72587448e30681fc53acaad9a"
|
||||
"bytes": 15479,
|
||||
"sha256": "be79ee0f70a3ceed473c481562c5fddaee6cfb36c960ba15ae10c846d5809650"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_html",
|
||||
"path": "reports/world_class_operator_runbook.html",
|
||||
"exists": true,
|
||||
"bytes": 21348,
|
||||
"sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49"
|
||||
"bytes": 21409,
|
||||
"sha256": "9a7be02a6990245c9dd1f72ced5928d80a3aaebea4647737c2aaf0b0a2f798df"
|
||||
},
|
||||
{
|
||||
"label": "world_class_claim_guard",
|
||||
|
||||
@@ -1,29 +1,29 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Commit: `b6ded57f9cc65b1dd7dbbac9c394647dadc131d7`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f`
|
||||
Commit: `67058cecebd13cd6e6fa54c009300cc145e8e999`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `9cb9a19e7745`
|
||||
- archive sha256: `5802e5f52255`
|
||||
- archive sha256: `419593870964`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `23`
|
||||
- provider evidence complete: `false`
|
||||
- human review complete: `false`
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `7` pass / `13` total; `6` blocked
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `56`
|
||||
|
||||
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.
|
||||
|
||||
@@ -35,22 +35,23 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
| world-class source checks are not all accepted (7/13 pass, 6 blocked) |
|
||||
| world-class source checks are not all accepted (6/13 pass, 7 blocked) |
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- ready: `false`
|
||||
- reason: working tree was 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: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f`
|
||||
- sha256: `733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,25 +73,25 @@ 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 | `6334c2f0261c` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `6450488d6ac4` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `5b05d1110b96` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `8b48340618cc` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `dfd07c1825de` |
|
||||
| package_verification | `reports/package_verification.json` | present | `a27941fdb865` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `5269d6e6364a` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `390d0bb42652` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `9b74155fb9bf` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `f6e1a69b0359` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `46f801051ec0` |
|
||||
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `b7fd72d7e754` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `9fbd4cd43798` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `2d32a2e917b7` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `00d8ebabb91e` |
|
||||
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `ca72c65b437b` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `8683ab3f627c` |
|
||||
| package_verification | `reports/package_verification.json` | present | `1372317d59e9` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `3a707c08d4b0` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `453a86240e7f` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `0a836a86ad6c` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `fe81833eab69` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `4506c836338c` |
|
||||
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `725d10a6f951` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `7693638c2e83` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f90d59c3e586` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `be79ee0f70a3` |
|
||||
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `9a7be02a6990` |
|
||||
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
|
||||
|
||||
## Reproduction Commands
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-13",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"target_count": 5,
|
||||
@@ -512,12 +512,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -554,7 +555,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -576,7 +577,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -768,12 +769,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -810,7 +812,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -830,7 +832,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -1430,12 +1432,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -1472,7 +1475,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -1494,7 +1497,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -1686,12 +1689,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -1728,7 +1732,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -1748,7 +1752,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -2348,12 +2352,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -2390,7 +2395,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -2412,7 +2417,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -2597,12 +2602,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -2639,7 +2645,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -2659,7 +2665,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -3250,12 +3256,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -3292,7 +3299,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -3314,7 +3321,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -3499,12 +3506,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -3541,7 +3549,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -3561,7 +3569,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -4152,12 +4160,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -4194,7 +4203,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -4216,7 +4225,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
@@ -4405,12 +4414,13 @@
|
||||
},
|
||||
"subprocess": {
|
||||
"required": true,
|
||||
"script_count": 10,
|
||||
"script_count": 11,
|
||||
"scripts": [
|
||||
"scripts/apply_adaptation.py",
|
||||
"scripts/ci_test.py",
|
||||
"scripts/render_benchmark_reproducibility.py",
|
||||
"scripts/render_eval_dashboard.py",
|
||||
"scripts/render_evidence_consistency.py",
|
||||
"scripts/run_eval_suite.py",
|
||||
"scripts/run_output_execution.py",
|
||||
"scripts/sync_local_install.py",
|
||||
@@ -4447,7 +4457,7 @@
|
||||
"secret_findings": 0,
|
||||
"network_script_count": 3,
|
||||
"file_write_script_count": 73,
|
||||
"subprocess_script_count": 10,
|
||||
"subprocess_script_count": 11,
|
||||
"interactive_script_count": 0,
|
||||
"help_smoke_failed_count": 0
|
||||
}
|
||||
@@ -4467,7 +4477,7 @@
|
||||
"capability_counts": {
|
||||
"network": 3,
|
||||
"file_write": 73,
|
||||
"subprocess": 10,
|
||||
"subprocess": 11,
|
||||
"interactive": 0
|
||||
},
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
|
||||
@@ -6,9 +6,9 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1078122,
|
||||
"other_text_tokens": 1078201,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1078919,
|
||||
"estimated_total_text_tokens": 1078998,
|
||||
"deferred_resource_tokens": 495718,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"generated_at": "2026-03-31",
|
||||
"generated_at": "2026-06-17",
|
||||
"targets": [
|
||||
{
|
||||
"label": "root",
|
||||
|
||||
@@ -207,8 +207,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches git dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -218,12 +218,16 @@
|
||||
"key": "benchmark-clean-worktree-release-lock",
|
||||
"label": "Clean worktree keeps a clean benchmark release lock",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": "checked only when git is available and the current worktree is clean",
|
||||
"actual": {
|
||||
"available": true,
|
||||
"clean": false,
|
||||
"changed_file_count": 57
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
"detail": "If the current worktree is clean, the committed benchmark report must not still carry a dirty release lock from an earlier generation."
|
||||
"detail": "Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass."
|
||||
},
|
||||
{
|
||||
"key": "skill-ir-evidence-path-contract",
|
||||
@@ -259,8 +263,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"expected": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"actual": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -272,30 +276,30 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -309,13 +313,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -323,13 +327,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -352,8 +356,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"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,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -364,8 +368,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"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,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -385,7 +389,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7
|
||||
"source_pass_count": 6
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -393,7 +397,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7
|
||||
"source_pass_count": 6
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -405,8 +409,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"expected": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"actual": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -418,30 +422,30 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -455,13 +459,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -469,13 +473,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -498,8 +502,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"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,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -510,8 +514,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"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,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -531,7 +535,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7
|
||||
"source_pass_count": 6
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -539,7 +543,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7
|
||||
"source_pass_count": 6
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -1338,7 +1342,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_pass_count": 6,
|
||||
"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": [
|
||||
@@ -1397,7 +1401,8 @@
|
||||
"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"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1411,7 +1416,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_pass_count": 6,
|
||||
"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": [
|
||||
@@ -1470,7 +1475,8 @@
|
||||
"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"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1820,15 +1826,15 @@
|
||||
"expected": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"actual": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"paths": [
|
||||
@@ -1844,8 +1850,8 @@
|
||||
"expected": {
|
||||
"pending_count": 4,
|
||||
"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,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -1853,8 +1859,8 @@
|
||||
"actual": {
|
||||
"pending_count": 4,
|
||||
"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,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -2108,8 +2114,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -2257,8 +2263,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -2415,8 +2421,8 @@
|
||||
"`3` warnings",
|
||||
"`54` declared internal modules",
|
||||
"`86 / 86` CLI help smoke checks passing across `140` scripts",
|
||||
"`658` zip entries",
|
||||
"archive with `658` entries",
|
||||
"`677` zip entries",
|
||||
"archive with `677` entries",
|
||||
"`12` installer permission checks enforced",
|
||||
"`0` permission failures",
|
||||
"`25` required artifacts",
|
||||
|
||||
@@ -20,7 +20,7 @@ This gate compares generated evidence reports against each other. It does not cr
|
||||
| Release evidence flow covers first-class reports | `pass` | Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted. | `AGENTS.md`, `reports/output_execution_runs.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/registry_audit.json`, `reports/package_verification.json`, `reports/upgrade_check.json`, `reports/adoption_drift_report.json`, `reports/architecture_maintainability.json`, `reports/python_compatibility.json`, `reports/runtime_permission_probes.json`, `reports/review_waivers.json`, `reports/review_annotations.json`, `reports/skill_atlas.json`, `reports/skill_os2_audit.json`, `reports/skill_os2_coverage.json`, `reports/context_budget.json`, `reports/context_budget_summary.json`, `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-viewer.json`, `reports/world_class_evidence_preflight.json`, `reports/skillops/daily`, `reports/skillops/weekly`, `reports/review-studio.json`, `reports/evidence_consistency.json` |
|
||||
| Review Studio mirrors context budget governance | `pass` | Review Studio must not keep stale context warnings after context reports prove large deferred resources are governed. | `reports/context_budget.json`, `reports/review-studio.json` |
|
||||
| Benchmark release lock matches git dirty state | `pass` | The benchmark release lock must reflect the generation-time git dirty flag. | `reports/benchmark_reproducibility.json` |
|
||||
| Clean worktree keeps a clean benchmark release lock | `pass` | If the current worktree is clean, the committed benchmark report must not still carry a dirty release lock from an earlier generation. | `reports/benchmark_reproducibility.json` |
|
||||
| Clean worktree keeps a clean benchmark release lock | `pass` | Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass. | `reports/benchmark_reproducibility.json` |
|
||||
| Human-facing reports expose the canonical Skill IR artifact | `pass` | Skill IR is the 2.0 platform-neutral semantic source, so user-facing reports must link to the artifact that actually exists. | `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-studio.json`, `skill-ir/examples/yao-meta-skill.json` |
|
||||
| overview embeds the benchmark commit | `pass` | Human-facing reports must point to the same benchmark release-lock commit. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` |
|
||||
| overview embeds benchmark summary fields | `pass` | Selected summary fields must match exactly across generated reports. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` |
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-13",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"package_dir": "dist",
|
||||
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 677,
|
||||
@@ -26,7 +26,7 @@
|
||||
{
|
||||
"id": "archive-present",
|
||||
"status": "pass",
|
||||
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
|
||||
"detail": "Package archive exists: dist/yao-meta-skill.zip"
|
||||
},
|
||||
{
|
||||
"id": "archive-safe-paths",
|
||||
@@ -272,9 +272,9 @@
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
"artifacts": {
|
||||
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
|
||||
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
|
||||
"json": "tests/tmp_review_studio/install_simulation.json",
|
||||
"markdown": "tests/tmp_review_studio/install_simulation.md"
|
||||
"archive": "dist/yao-meta-skill.zip",
|
||||
"package_manifest": "dist/manifest.json",
|
||||
"json": "reports/install_simulation.json",
|
||||
"markdown": "reports/install_simulation.md"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Install Simulation
|
||||
|
||||
- OK: `True`
|
||||
- Package directory: `tests/tmp_review_studio/dist`
|
||||
- Package directory: `dist`
|
||||
- Archive extracted: `True`
|
||||
- Entrypoint loaded: `True`
|
||||
- Manifest loaded: `True`
|
||||
@@ -16,7 +16,7 @@
|
||||
|
||||
| Check | Status | Detail |
|
||||
| --- | --- | --- |
|
||||
| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
|
||||
| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip |
|
||||
| `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
|
||||
| `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
|
||||
| `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.12,
|
||||
"duration_ms": 27.03,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.28,
|
||||
"duration_ms": 25.75,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.37,
|
||||
"duration_ms": 25.71,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.8,
|
||||
"duration_ms": 27.67,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.59,
|
||||
"duration_ms": 28.25,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.55,
|
||||
"duration_ms": 26.51,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.89,
|
||||
"duration_ms": 34.54,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.9,
|
||||
"duration_ms": 30.74,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.03,
|
||||
"duration_ms": 27.88,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.51,
|
||||
"duration_ms": 26.38,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
|
||||
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
|
||||
|
||||
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
|
||||
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 26.12 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 28.28 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.37 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.8 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.59 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.55 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.89 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.9 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.03 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.51 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 27.03 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 25.75 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 25.71 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 27.67 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.25 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.51 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 34.54 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.74 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.88 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.38 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -1,15 +1,15 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"summary": {
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_entry_count": 658,
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"archive_entry_count": 677,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b`
|
||||
- Archive SHA256: `4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69`
|
||||
- Package SHA256: `9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b`
|
||||
- Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b`
|
||||
- Install simulated: `True`
|
||||
|
||||
|
||||
+15
-15
File diff suppressed because one or more lines are too long
+240
-206
File diff suppressed because it is too large
Load Diff
+30
-29
@@ -412,7 +412,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_pass_count": 6,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -471,7 +471,8 @@
|
||||
"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"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -996,13 +997,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f",
|
||||
"evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379",
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1017,14 +1018,14 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"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.",
|
||||
@@ -1167,7 +1168,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1215,8 +1216,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_entry_count": 658,
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"archive_entry_count": 677,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1299,7 +1300,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1316,14 +1317,14 @@
|
||||
"ok": true,
|
||||
"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,
|
||||
@@ -1332,7 +1333,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -1599,7 +1600,7 @@
|
||||
"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>/",
|
||||
@@ -1652,8 +1653,8 @@
|
||||
"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,
|
||||
@@ -2003,7 +2004,7 @@
|
||||
"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>/",
|
||||
@@ -2040,7 +2041,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -2061,8 +2062,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -2078,8 +2079,8 @@
|
||||
}
|
||||
],
|
||||
"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",
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"generated_at": "2026-06-13",
|
||||
"generated_at": "2026-06-17",
|
||||
"summary": {
|
||||
"waiver_count": 0,
|
||||
"active_count": 0,
|
||||
@@ -92,7 +92,7 @@
|
||||
"Reviewer links output_review_adjudication or output_execution evidence."
|
||||
],
|
||||
"suggested_evidence": "reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --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 2027-06-17 --evidence reports/output_review_adjudication.md",
|
||||
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
|
||||
},
|
||||
{
|
||||
|
||||
@@ -38,7 +38,7 @@
|
||||
- waiver allowed: `true`
|
||||
- risk: review pending 5; model-executed 0; output failures 0
|
||||
- evidence: `reports/output_review_adjudication.md`
|
||||
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --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 2027-06-17 --evidence reports/output_review_adjudication.md`
|
||||
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
|
||||
|
||||
#### Required Review
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"package_dir": "dist",
|
||||
"expected_capabilities": [
|
||||
"file_write",
|
||||
"network",
|
||||
@@ -42,7 +42,7 @@
|
||||
{
|
||||
"target": "openai",
|
||||
"status": "pass",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
|
||||
"adapter": "dist/targets/openai/adapter.json",
|
||||
"permission_model": "metadata-only",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -139,7 +139,7 @@
|
||||
{
|
||||
"target": "claude",
|
||||
"status": "pass",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
|
||||
"adapter": "dist/targets/claude/adapter.json",
|
||||
"permission_model": "neutral-source-plus-adapter",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -221,7 +221,7 @@
|
||||
{
|
||||
"target": "generic",
|
||||
"status": "pass",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
|
||||
"adapter": "dist/targets/generic/adapter.json",
|
||||
"permission_model": "agent-skills-compatible-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -303,7 +303,7 @@
|
||||
{
|
||||
"target": "vscode",
|
||||
"status": "pass",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
|
||||
"adapter": "dist/targets/vscode/adapter.json",
|
||||
"permission_model": "vscode-workspace-trust-plus-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
|
||||
@@ -910,7 +910,7 @@
|
||||
</table>
|
||||
</div>
|
||||
</div>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
@@ -412,7 +412,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_pass_count": 6,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -471,7 +471,8 @@
|
||||
"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"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1000,13 +1001,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f",
|
||||
"evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379",
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1021,14 +1022,14 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"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.",
|
||||
@@ -1171,7 +1172,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1219,8 +1220,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_entry_count": 658,
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"archive_entry_count": 677,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1303,7 +1304,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1320,14 +1321,14 @@
|
||||
"ok": true,
|
||||
"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,
|
||||
@@ -1336,7 +1337,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -1603,7 +1604,7 @@
|
||||
"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>/",
|
||||
@@ -1656,8 +1657,8 @@
|
||||
"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,
|
||||
@@ -2007,7 +2008,7 @@
|
||||
"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>/",
|
||||
@@ -2044,7 +2045,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -2065,8 +2066,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -2082,8 +2083,8 @@
|
||||
}
|
||||
],
|
||||
"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",
|
||||
|
||||
@@ -138,8 +138,8 @@ Next move: add real client or installer permission enforcement integration.
|
||||
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
|
||||
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
|
||||
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `658` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `658` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `677` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `677` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
|
||||
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
|
||||
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
|
||||
|
||||
@@ -910,7 +910,7 @@
|
||||
</table>
|
||||
</div>
|
||||
</div>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
+30
-29
@@ -411,7 +411,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_pass_count": 6,
|
||||
"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": [
|
||||
@@ -470,7 +470,8 @@
|
||||
"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"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -995,13 +996,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f",
|
||||
"evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379",
|
||||
"source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1016,14 +1017,14 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7",
|
||||
"commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
|
||||
"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.",
|
||||
@@ -1166,7 +1167,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
|
||||
"package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1214,8 +1215,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
|
||||
"archive_entry_count": 658,
|
||||
"archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
|
||||
"archive_entry_count": 677,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1298,7 +1299,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1315,14 +1316,14 @@
|
||||
"ok": true,
|
||||
"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,
|
||||
@@ -1331,7 +1332,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -1598,7 +1599,7 @@
|
||||
"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>/",
|
||||
@@ -1651,8 +1652,8 @@
|
||||
"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,
|
||||
@@ -2002,7 +2003,7 @@
|
||||
"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>/",
|
||||
@@ -2039,7 +2040,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -2060,8 +2061,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -2077,8 +2078,8 @@
|
||||
}
|
||||
],
|
||||
"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",
|
||||
|
||||
@@ -273,8 +273,8 @@
|
||||
"report": "reports/adoption_drift_report.json",
|
||||
"risk_band": "low",
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
|
||||
@@ -285,7 +285,7 @@
|
||||
"key": "registry-distribution",
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"current": "zip entries 658; install failures 0; permission failures 0",
|
||||
"current": "zip entries 677; install failures 0; permission failures 0",
|
||||
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -351,7 +351,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -433,7 +433,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
|
||||
@@ -27,10 +27,10 @@ Generated at: `2026-06-17`
|
||||
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
|
||||
| Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
|
||||
| Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
|
||||
| Registry Distribution | pass | zip entries 658; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Registry Distribution | pass | zip entries 677; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
|
||||
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
|
||||
## Open Highest-Leverage Gaps
|
||||
|
||||
|
||||
@@ -7,22 +7,22 @@
|
||||
"item_count": 21,
|
||||
"module_count": 8,
|
||||
"recommended_pr_count": 13,
|
||||
"pass_count": 20,
|
||||
"warn_count": 1,
|
||||
"pass_count": 21,
|
||||
"warn_count": 0,
|
||||
"missing_count": 0,
|
||||
"extension_track_count": 4,
|
||||
"extension_partial_count": 0,
|
||||
"extension_planned_count": 0,
|
||||
"extension_covered_count": 4,
|
||||
"adaptive_extension_ready": true,
|
||||
"local_blueprint_ready": false,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_evidence_pending_count": 4,
|
||||
"decision": "continue-implementation"
|
||||
"decision": "local-blueprint-covered-evidence-pending"
|
||||
},
|
||||
"status_counts": {
|
||||
"pass": 20,
|
||||
"warn": 1,
|
||||
"pass": 21,
|
||||
"warn": 0,
|
||||
"missing": 0
|
||||
},
|
||||
"extension_status_counts": {
|
||||
@@ -204,7 +204,7 @@
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
|
||||
"current": "archive entries 658; install failures 0",
|
||||
"current": "archive entries 677; install failures 0",
|
||||
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
|
||||
"test": "python3 tests/verify_registry_audit.py",
|
||||
"evidence": [
|
||||
@@ -611,7 +611,7 @@
|
||||
"key": "evidence-consistency",
|
||||
"category": "recommended-pr",
|
||||
"label": "Evidence Consistency",
|
||||
"status": "warn",
|
||||
"status": "pass",
|
||||
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
|
||||
"current": "36 consistency checks",
|
||||
"command": "make ci-test",
|
||||
|
||||
@@ -4,12 +4,12 @@ Generated at: `2026-06-17`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `continue-implementation`
|
||||
- local blueprint ready: `false`
|
||||
- decision: `local-blueprint-covered-evidence-pending`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- pass: `20` / `21`
|
||||
- pass: `21` / `21`
|
||||
- missing: `0`
|
||||
- warn: `1`
|
||||
- warn: `0`
|
||||
- reference extensions: `4`
|
||||
- extension covered: `4`
|
||||
- extension partial: `0`
|
||||
@@ -28,7 +28,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
|
||||
| Trust Security | `pass` | 140 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
|
||||
| Registry Distribution | `pass` | archive entries 658; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Registry Distribution | `pass` | archive entries 677; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
|
||||
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
|
||||
|
||||
@@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
|
||||
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
|
||||
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
|
||||
| Evidence Consistency | `warn` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
|
||||
| Evidence Consistency | `pass` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
|
||||
|
||||
## Reference Extension Tracks
|
||||
|
||||
@@ -213,7 +213,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are
|
||||
### Evidence Consistency
|
||||
|
||||
- objective: Recommended Skill OS 2.0 implementation PR from the upgrade plan.
|
||||
- status: `warn`
|
||||
- status: `pass`
|
||||
- existing evidence: `scripts/render_evidence_consistency.py`, `reports/evidence_consistency.json`, `tests/verify_evidence_consistency.py`
|
||||
- next action: Keep this item covered as the implementation evolves.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T16:14:10Z",
|
||||
"generated_at": "2026-06-16T16:24:58Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Daily SkillOps Report
|
||||
|
||||
Generated at: `2026-06-16T16:14:10Z`
|
||||
Generated at: `2026-06-16T16:24:58Z`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"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": true,
|
||||
"release_lock_ready": false,
|
||||
"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": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
|
||||
@@ -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: `true`
|
||||
- release lock ready: `false`
|
||||
- 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.
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"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": true,
|
||||
"release_lock_ready": false,
|
||||
"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": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -13,7 +13,7 @@ Week: `2026-W25`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `True`
|
||||
- release_lock_ready: `False`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-13",
|
||||
"generated_at": "2026-06-17",
|
||||
"previous": {
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.0.0",
|
||||
@@ -75,7 +75,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
|
||||
"to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -90,7 +90,7 @@
|
||||
"artifacts": {
|
||||
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
|
||||
"current_package": "reports/registry_audit.json",
|
||||
"json": "tests/tmp_review_studio/upgrade_check.json",
|
||||
"markdown": "tests/tmp_review_studio/upgrade_check.md"
|
||||
"json": "reports/upgrade_check.json",
|
||||
"markdown": "reports/upgrade_check.md"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -312,7 +312,7 @@
|
||||
"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
|
||||
|
||||
@@ -16,8 +16,8 @@
|
||||
"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,
|
||||
@@ -33,8 +33,8 @@
|
||||
"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,
|
||||
@@ -410,7 +410,7 @@
|
||||
"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>/",
|
||||
@@ -447,7 +447,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -468,8 +468,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -485,8 +485,8 @@
|
||||
}
|
||||
],
|
||||
"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",
|
||||
|
||||
@@ -8,8 +8,8 @@ Generated at: `2026-06-17`
|
||||
- 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`
|
||||
@@ -30,7 +30,7 @@ This ledger records the current evidence state. It requires both passing source
|
||||
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
|
||||
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices 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
|
||||
|
||||
@@ -172,8 +172,8 @@ 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_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "ledger_counts_as_completion": false}`
|
||||
|
||||
### Provenance Requirements
|
||||
@@ -197,7 +197,7 @@ 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
|
||||
|
||||
@@ -146,7 +146,7 @@
|
||||
"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>/",
|
||||
@@ -309,7 +309,7 @@
|
||||
"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>/",
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -65,7 +65,7 @@
|
||||
<span class="eyebrow">Evidence Collection</span>
|
||||
<h1>World-Class Evidence Preflight</h1>
|
||||
<p class="lede">This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.</p>
|
||||
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>7/13</strong></article></div>
|
||||
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>6/13</strong></article></div>
|
||||
</section>
|
||||
<section class="section two-col" id="handoff">
|
||||
<article class="panel">
|
||||
@@ -611,15 +611,15 @@
|
||||
</dl>
|
||||
</article>
|
||||
|
||||
<article class="check-row pass">
|
||||
<article class="check-row blocked">
|
||||
<div>
|
||||
<span>adoption_sample_count</span>
|
||||
<strong>Adoption sample</strong>
|
||||
</div>
|
||||
<dl>
|
||||
<dt>Current</dt><dd><code>1</code></dd>
|
||||
<dt>Current</dt><dd><code>0</code></dd>
|
||||
<dt>Expected</dt><dd><code>>0</code></dd>
|
||||
<dt>Status</dt><dd>pass</dd>
|
||||
<dt>Status</dt><dd>blocked</dd>
|
||||
<dt>Action</dt><dd>Telemetry must include adoption outcome evidence.</dd>
|
||||
</dl>
|
||||
</article>
|
||||
|
||||
@@ -14,8 +14,8 @@
|
||||
"collection_ready_count": 1,
|
||||
"collection_blocked_count": 3,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"pending_count": 4,
|
||||
"ready_to_claim_world_class": false,
|
||||
"credential_value_exposed": false,
|
||||
@@ -535,8 +535,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -891,8 +891,8 @@
|
||||
"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."
|
||||
},
|
||||
|
||||
@@ -10,7 +10,7 @@ Generated at: `2026-06-17`
|
||||
- credential value exposed: `false`
|
||||
- collection ready: `1`
|
||||
- collection blocked: `3`
|
||||
- source checks: `7` pass / `13` total
|
||||
- source checks: `6` pass / `13` total
|
||||
|
||||
This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger.
|
||||
|
||||
@@ -150,7 +150,7 @@ Generate the submission kit after the real provider, human, native-permission, o
|
||||
| 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
|
||||
|
||||
@@ -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://<extension-id>/</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 <YYYY-MM-DD></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 > 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count > 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 / >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 / >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 / >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 / >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>
|
||||
|
||||
@@ -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"
|
||||
@@ -408,7 +408,7 @@
|
||||
"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.",
|
||||
@@ -456,7 +456,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -477,8 +477,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -493,9 +493,10 @@
|
||||
"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",
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -244,7 +244,7 @@ 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`
|
||||
|
||||
@@ -297,13 +297,14 @@ 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
|
||||
|
||||
@@ -14,8 +14,8 @@
|
||||
"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,
|
||||
"review_counts_submission_as_completion": false,
|
||||
"summary": {
|
||||
"review_item_count": 4,
|
||||
@@ -27,8 +27,8 @@
|
||||
"unmatched_submission_count": 0,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 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"
|
||||
@@ -302,7 +302,7 @@
|
||||
"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
|
||||
@@ -323,8 +323,8 @@
|
||||
"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."
|
||||
},
|
||||
@@ -340,8 +340,8 @@
|
||||
}
|
||||
],
|
||||
"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",
|
||||
|
||||
@@ -139,7 +139,7 @@ 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
|
||||
|
||||
@@ -229,8 +229,8 @@
|
||||
"report": "reports/adoption_drift_report.json",
|
||||
"risk_band": "low",
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user