diff --git a/registry/index.json b/registry/index.json index a9f4f97e..8fcc5cce 100644 --- a/registry/index.json +++ b/registry/index.json @@ -1,6 +1,6 @@ { "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index ff6ab5f0..bcd03d4d 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -17,7 +17,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -48,10 +48,10 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-16" + "generated_at": "2026-06-13" } diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index da12292f..a1c933cc 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T20:28:46Z", + "generated_at": "2026-06-15T20:34:53Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 91b31983..206372c9 100644 --- a/reports/adoption_drift_report.md +++ b/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: `0` -- Activation events: `0` -- Adoption rate: `0` +- Adoption samples: `1` +- Activation events: `1` +- Adoption rate: `100.0` - 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 | 0 | 0 | 0 | 0 | 0 | 0 | +| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` +- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 47a12e55..a54a6733 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "python_file_count": 181, @@ -66,7 +66,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 766, + "lines": 767, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -152,7 +152,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 766, + "lines": 767, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index cd0a19aa..6a552a1a 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,6 +1,6 @@ # Architecture Maintainability -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -35,7 +35,7 @@ No file-size hotspots found. | `scripts/skill_report_layout.py` | `808` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `tests/verify_world_class_evidence_intake.py` | `795` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | -| `tests/verify_review_studio.py` | `766` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | +| `tests/verify_review_studio.py` | `767` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/prepare_world_class_submission_kit.py` | `724` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/compile_skill.py` | `723` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | @@ -51,7 +51,7 @@ No file-size hotspots found. | `scripts/skill_report_layout.py` | `808` | `internal-module` | `pass` | | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` | | `tests/verify_world_class_evidence_intake.py` | `795` | `test` | `pass` | -| `tests/verify_review_studio.py` | `766` | `test` | `pass` | +| `tests/verify_review_studio.py` | `767` | `test` | `pass` | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` | | `scripts/prepare_world_class_submission_kit.py` | `724` | `cli-script` | `pass` | | `scripts/compile_skill.py` | `723` | `cli-script` | `pass` | diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index b45d4bbd..778c1e81 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 22, + "sample": [ + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -37,14 +50,15 @@ "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": 22 }, "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)", @@ -53,10 +67,10 @@ "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": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "ready": false, + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd" + "sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "6fa9f0b5a294f5373de752e5881c1e6c1a996b65995bd83517a10e691c5e4abd" + "bytes": 7965, + "sha256": "d789a1a2920a2388769c78ccc1e786d5bc4e5f85d2f7af11cb134e8f3a8efa0c" }, { "label": "blind_review", @@ -187,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "ba8c24683f0e4d89d3d77f90c3cce8fa9dea52c93f8da8f23da127abe634eda3" + "sha256": "c7520ea9cfb612de8da2d38f03948e9d89f068496ce7466857243235128ce7bb" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "667250d991ae62ae20562fe195a7ebc8357d55e723e17a084c94fd432420da8e" + "sha256": "e46eaa920aca5a6394897610f743372bcc3e81fc17f1e3cd9eb552ddb6ed4945" }, { "label": "install_simulation", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 09edb1c6..3c774ec7 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd` +Commit: `e65ee917b74da20b0b8802451a50b5837ba6d9ac` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` - source contract sha256: `b6abceeea0f2` -- archive sha256: `a521b75a29e5` +- archive sha256: `7e55b9259f9a` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa - world-class ready: `false` - 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: `22` 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. @@ -35,6 +35,7 @@ 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) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## 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: `4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd` +- sha256: `22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2` ## Methodology Sections @@ -72,15 +73,15 @@ 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 | `6fa9f0b5a294` | +| output_execution | `reports/output_execution_runs.json` | present | `d789a1a2920a` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | | trust_report | `reports/security_trust_report.json` | present | `ba3b69b8eb33` | | python_compatibility | `reports/python_compatibility.json` | present | `aa89183f58b2` | -| registry_audit | `reports/registry_audit.json` | present | `ba8c24683f0e` | -| package_verification | `reports/package_verification.json` | present | `667250d991ae` | +| registry_audit | `reports/registry_audit.json` | present | `c7520ea9cfb6` | +| package_verification | `reports/package_verification.json` | present | `e46eaa920aca` | | install_simulation | `reports/install_simulation.json` | present | `df390c157451` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `e12318b1e083` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 8032bb49..6287c4d6 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, diff --git a/reports/context_budget.json b/reports/context_budget.json index 9039b665..e932d8b4 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,9 +6,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1001284, + "other_text_tokens": 1001355, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1002051, + "estimated_total_text_tokens": 1002122, "deferred_resource_tokens": 461032, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 4ebdf1f5..4d0a791e 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -1,5 +1,5 @@ { - "generated_at": "2026-06-16", + "generated_at": "2026-03-31", "targets": [ { "label": "root", diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 7b68a1ca..6babb3c3 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -202,8 +202,8 @@ "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" ], @@ -243,8 +243,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", - "actual": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "expected": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", + "actual": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -256,30 +256,30 @@ "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": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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", @@ -389,8 +389,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", - "actual": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "expected": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", + "actual": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -402,30 +402,30 @@ "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": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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", diff --git a/reports/install_simulation.json b/reports/install_simulation.json index fe6b31c1..6c1bff83 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,11 +1,11 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", - "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", + "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", "summary": { "archive_present": true, "archive_entry_count": 630, @@ -26,7 +26,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: dist/yao-meta-skill.zip" + "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -272,9 +272,9 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "dist/yao-meta-skill.zip", - "package_manifest": "dist/manifest.json", - "json": "reports/install_simulation.json", - "markdown": "reports/install_simulation.md" + "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" } } diff --git a/reports/install_simulation.md b/reports/install_simulation.md index 6750e007..b0d16dae 100644 --- a/reports/install_simulation.md +++ b/reports/install_simulation.md @@ -1,7 +1,7 @@ # Install Simulation - OK: `True` -- Package directory: `dist` +- Package directory: `tests/tmp_review_studio/dist` - Archive extracted: `True` - Entrypoint loaded: `True` - Manifest loaded: `True` @@ -16,7 +16,7 @@ | Check | Status | Detail | | --- | --- | --- | -| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip | +| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/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 | diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 54e058be..98cf7158 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.59, + "duration_ms": 45.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.63, + "duration_ms": 38.0, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.48, + "duration_ms": 35.96, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.32, + "duration_ms": 35.66, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.47, + "duration_ms": 32.56, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.93, + "duration_ms": 31.61, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.1, + "duration_ms": 32.27, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.64, + "duration_ms": 32.29, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 34.96, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.96, + "duration_ms": 31.68, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 25000e36..551a753f 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -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 | 26.59 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 26.63 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 26.48 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.32 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 26.47 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.93 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.1 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.64 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.21 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.96 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 45.97 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 38.0 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 35.96 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.66 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 32.56 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.61 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 32.27 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 32.29 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.96 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.68 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index e5437749..d8d2a1d8 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 4cb26b4a..f7c5884f 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0` +- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index c97d415f..e326221c 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index f81138a7..a0719a7d 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,6 +1,6 @@ # Python Compatibility -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary diff --git a/reports/registry_audit.json b/reports/registry_audit.json index a1ae29b5..bda0cabc 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -22,7 +22,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -53,16 +53,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-16" + "generated_at": "2026-06-13" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { diff --git a/reports/registry_audit.md b/reports/registry_audit.md index e980e7cc..49dbb1d9 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -7,7 +7,7 @@ - Owner: `Yao Team` - License: `MIT` - Package SHA256: `b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083` -- Archive SHA256: `a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0` +- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index cd879c34..57a71be9 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,7 +676,7 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

115 scripts scanned; secrets found

Py Compat0

184 files scanned for Python 3.11

Arch Debt0

899 largest lines; 11 watchlist; 66 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

178 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

630 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

115 scripts scanned; secrets found

Py Compat0

184 files scanned for Python 3.11

Arch Debt0

899 largest lines; 11 watchlist; 66 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

178 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

630 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

@@ -806,8 +806,8 @@
-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

@@ -827,12 +827,12 @@

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
630
失败数
0
警告数
0
归档哈希
a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
630
失败数
0
警告数
0
归档哈希
7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed
diff --git a/reports/review-studio.json b/reports/review-studio.json index 3efc3fc5..e5b43450 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1678,13 +1678,13 @@ "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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1702,11 +1702,11 @@ "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": 22 }, - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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.", @@ -1850,7 +1850,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -1881,7 +1881,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1897,7 +1897,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 @@ -1976,7 +1976,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", @@ -4348,7 +4348,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.59, + "duration_ms": 45.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4376,7 +4376,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.63, + "duration_ms": 38.0, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4399,7 +4399,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.48, + "duration_ms": 35.96, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4427,7 +4427,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.32, + "duration_ms": 35.66, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4450,7 +4450,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.47, + "duration_ms": 32.56, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4478,7 +4478,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.93, + "duration_ms": 31.61, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4501,7 +4501,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.1, + "duration_ms": 32.27, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4528,7 +4528,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.64, + "duration_ms": 32.29, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4551,7 +4551,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 34.96, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4580,7 +4580,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.96, + "duration_ms": 31.68, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5301,23 +5301,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 22, + "sample": [ + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5335,14 +5348,15 @@ "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": 22 }, "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)", @@ -5351,10 +5365,10 @@ "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": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "ready": false, + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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)", @@ -5362,7 +5376,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd" + "sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5435,8 +5449,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "6fa9f0b5a294f5373de752e5881c1e6c1a996b65995bd83517a10e691c5e4abd" + "bytes": 7965, + "sha256": "d789a1a2920a2388769c78ccc1e786d5bc4e5f85d2f7af11cb134e8f3a8efa0c" }, { "label": "blind_review", @@ -5485,14 +5499,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "ba8c24683f0e4d89d3d77f90c3cce8fa9dea52c93f8da8f23da127abe634eda3" + "sha256": "c7520ea9cfb612de8da2d38f03948e9d89f068496ce7466857243235128ce7bb" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "667250d991ae62ae20562fe195a7ebc8357d55e723e17a084c94fd432420da8e" + "sha256": "e46eaa920aca5a6394897610f743372bcc3e81fc17f1e3cd9eb552ddb6ed4945" }, { "label": "install_simulation", @@ -6493,7 +6507,7 @@ "compiled_targets": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, @@ -15670,7 +15684,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 766, + "lines": 767, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -15756,7 +15770,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 766, + "lines": 767, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -15805,9 +15819,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1001284, + "other_text_tokens": 1001304, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1002051, + "estimated_total_text_tokens": 1002071, "deferred_resource_tokens": 461032, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ @@ -17736,7 +17750,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T20:28:46Z", + "generated_at": "2026-06-16", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -20872,7 +20886,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -20903,7 +20917,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -20951,7 +20965,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 @@ -21959,7 +21973,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 0299e45e..b37c2d99 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -997,13 +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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,11 +1021,11 @@ "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": 22 }, - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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.", @@ -1169,7 +1169,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -1200,7 +1200,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 @@ -1295,7 +1295,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 76fadc1f..66f2b1d9 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index aa2558e7..07eeccbc 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -52,7 +52,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --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", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { diff --git a/reports/review_waivers.md b/reports/review_waivers.md index 6c8d594c..dbc942d1 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -35,7 +35,7 @@ - waiver allowed: `true` - risk: review pending 5; model-executed 0; output failures 0 - evidence: `reports/output_review_adjudication.md` -- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --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` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json index 9c2ffd6e..59c9a1a4 100644 --- a/reports/runtime_permission_probes.json +++ b/reports/runtime_permission_probes.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -42,7 +42,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/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": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/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": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/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": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 9b806ee1..25aeb4ba 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1001,13 +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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,11 +1025,11 @@ "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": 22 }, - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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.", @@ -1173,7 +1173,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -1204,7 +1204,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 @@ -1299,7 +1299,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index d0675e58..425468e4 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -996,13 +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": "4e46ec51849a179cd6db9ea908a7d49df080b3f10463d4a98e54aaa5968e37cd", + "evidence_bundle_sha256": "22c574f08fad83840f2b9e1d71f987a1c9bba1c929a0aa03a883e336933af2a2", "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1020,11 +1020,11 @@ "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": 22 }, - "commit": "5e72c0c8f8227c5c92d9f289a62f675cbf6d8b82", + "commit": "e65ee917b74da20b0b8802451a50b5837ba6d9ac", "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.", @@ -1168,7 +1168,7 @@ "license": "MIT", "checksums": { "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0", + "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", "archive_entry_count": 630, "failure_count": 0, "warning_count": 0 @@ -1294,7 +1294,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index ca6de4a8..a7e76ce2 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -44,7 +44,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -244,8 +244,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, @@ -908,7 +908,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 77, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 5ef6a807..91211d40 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 15, @@ -351,7 +351,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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 0", + "current": "external source events 0; adoption samples 1", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 106717e6..2ced448a 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Audit -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -30,7 +30,7 @@ Generated at: `2026-06-16` | Registry Distribution | pass | zip entries 630; 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 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. | +| 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. | ## Open Highest-Leverage Gaps diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index fb135df5..83370704 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 21, diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index a68bd477..469e9215 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Blueprint Coverage -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 706ec20f..41d8914e 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -70,7 +70,7 @@ { "field": "archive_sha256", "from": "", - "to": "a521b75a29e5761e4a90df6055d0c0316e615add8d32168960f80bf89a99c8a0" + "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" }, { "field": "package_sha256", @@ -90,7 +90,7 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "reports/upgrade_check.json", - "markdown": "reports/upgrade_check.md" + "json": "tests/tmp_review_studio/upgrade_check.json", + "markdown": "tests/tmp_review_studio/upgrade_check.md" } } diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index a4f2f9c3..e578865f 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index ee6c3083..01cef197 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -1,6 +1,6 @@ # World-Class Claim Guard -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index 396b0c9a..ed002e84 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -307,7 +307,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index 33297ad1..62c2d7ed 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -1,6 +1,6 @@ # World-Class Evidence Intake -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index 7c395391..58110595 100644 --- a/reports/world_class_evidence_ledger.json +++ b/reports/world_class_evidence_ledger.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -15,8 +15,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -31,8 +31,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -393,7 +393,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -430,7 +430,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -451,8 +451,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -468,8 +468,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index 9f5a3944..8ec440ff 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -1,6 +1,6 @@ # World-Class Evidence Ledger -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -8,8 +8,8 @@ Generated at: `2026-06-16` - ready to claim world-class: `false` - entries: `4` - source accepted: `0` -- source checks: `6` pass / `13` total -- source blocked: `7` +- source checks: `7` pass / `13` total +- source blocked: `6` - accepted: `0` - pending: `4` - human pending: `1` @@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. | | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. | | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | 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 1 | Install a real client against the native host and import production metadata-only events. | ## Provider Holdout @@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` -- source checks: `1` pass / `3` total +- 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 - submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}` ### Provenance Requirements @@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source | Check | Current | Expected | Status | | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | -| Adoption sample | `0` | `>0` | `blocked` | +| Adoption sample | `1` | `>0` | `pass` | | Raw content blocked | `False` | `false` | `pass` | ### Completion Assertions diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index afaae4db..236c40fe 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", @@ -141,7 +141,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -299,7 +299,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index e97adc90..c0db846d 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -1,6 +1,6 @@ # World-Class Evidence Plan -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 | | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 | | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | ## Provider Holdout diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index be9f2679..e239453a 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.

-
Pending4
Awaiting4
Ready0
Source6/13
Blocked7
Invalid0
+
Pending4
Awaiting4
Ready0
Source7/13
Blocked6
Invalid0

Fast Path

  1. Run the real external or human work for one evidence item.
  2. Generate and fill the matching submission draft.
  3. Validate intake and inspect the submission review queue.
  4. Refresh the ledger and run the claim guard before making any completion claim.

Evidence Items

@@ -120,7 +120,7 @@
Owner
Browser/Chrome/IDE/provider client integrator
Ledger
pending
-
Blocked
2
+
Blocked
1
Submission
evidence/world_class/submissions/native-client-telemetry.json

Source 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.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • 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.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -130,8 +130,8 @@

Success Checks

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

Privacy

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
-

Next Source Actions

  • Import at least one metadata-only event from a real client.
  • Telemetry must include adoption outcome evidence.
-

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
+

Next Source Actions

  • Import at least one metadata-only event from a real client.
+

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 1 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.

Boundary

diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index 1ad88b47..eb0e1857 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -12,8 +12,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -394,7 +394,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -442,7 +442,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -463,8 +463,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -479,10 +479,9 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 2, + "blocked_source_check_count": 1, "next_source_actions": [ - "Import at least one metadata-only event from a real client.", - "Telemetry must include adoption outcome evidence." + "Import at least one metadata-only event from a real client." ], "submission_state": { "status": "missing", diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index 715b410a..bef6278b 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -1,6 +1,6 @@ # World-Class Operator Runbook -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials | | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer | | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator | -| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | 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` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | ## Provider Holdout @@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission - objective: Import production metadata-only events from a real external client into the local drift loop. - blocking reason: No evidence packet has been submitted for review. -- blocked source checks: `2` +- blocked source checks: `1` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -292,14 +292,13 @@ 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 | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 867863f1..9df3045c 100644 --- a/reports/world_class_submission_review.json +++ b/reports/world_class_submission_review.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -14,8 +14,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "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": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -301,7 +301,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -322,8 +322,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -339,8 +339,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index 899b7aa1..7fe1e470 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -1,6 +1,6 @@ # World-Class Submission Review -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w #### Source Checks - External events: 0 / >0 => blocked -- Adoption sample: 0 / >0 => blocked +- Adoption sample: 1 / >0 => pass - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 29e6f30d..fac24783 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -1,6 +1,6 @@ { "workspace_root": ".", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -200,8 +200,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json index b57d361d..6602e829 100644 --- a/skill_atlas/stale_skills.json +++ b/skill_atlas/stale_skills.json @@ -24,7 +24,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 77, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py index 36abae84..0e0c3259 100644 --- a/tests/verify_review_studio.py +++ b/tests/verify_review_studio.py @@ -551,10 +551,10 @@ def main() -> None: if full_payload["data"]["skill_os2_coverage"]: assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"] - assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_track_count"] == 2, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_track_count"] == 3, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_partial_count"] == 0, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_planned_count"] == 0, full_payload["data"]["skill_os2_coverage"] - assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_covered_count"] == 2, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_covered_count"] == 3, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["adaptive_extension_ready"] is True, full_payload["data"]["skill_os2_coverage"] extension_tracks = { item["key"]: item @@ -562,6 +562,7 @@ def main() -> None: } assert extension_tracks["skill-interpretation-report"]["status"] == "covered", extension_tracks assert extension_tracks["adaptive-self-iteration"]["status"] == "covered", extension_tracks + assert extension_tracks["daily-skillops-report"]["status"] == "covered", extension_tracks world_class_entries = full_payload["data"]["world_class_evidence_ledger"]["entries"] assert len(world_class_entries) == 4, world_class_entries assert {item["key"] for item in world_class_entries} == { @@ -672,7 +673,7 @@ def main() -> None: assert "Extension Track Count" in html, html assert "Adaptive Extension Ready" in html, html assert "
Extension Partial Count
0
" in html, html - assert "
Extension Covered Count
2
" in html, html + assert "
Extension Covered Count
3
" in html, html assert "
Extension Planned Count
0
" in html, html assert "Adaptive Extension Ready" in html, html assert "本地蓝图" in html, html