diff --git a/registry/index.json b/registry/index.json index d7222bb..3580ec5 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 26538c6..d09d5ec 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 30bf5b4..93ae295 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": "2026-06-16T07:12:10Z", + "generated_at": "2026-06-16T07:18:20Z", "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 91b3198..206372c 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 c9b4d1b..44108cd 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": 196, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 5ceee15..7c8d7fd 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 diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 1314429..fe82ee8 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": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 26, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/install_simulation.json", + " M reports/install_simulation.md", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md" + ], "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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": 26 }, "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": "026efd17e382dd925526d04fd0ac29a75990d4df", + "ready": false, + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961" + "sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "93beb4bf94e08e6b75f35ff6f1a2029a9b9092717d691f42cf507b09bc590572" + "bytes": 7967, + "sha256": "04aef19563f053de353bff888ecf7faa938668f7c2edefe36c4ce95b31879066" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "034e530e2efdd5c28f7e6ff97b2c7621aa88f8d6899df4d2b7f73048277f5541" + "sha256": "b4ae0799ef42fe9699136b8cc49c09f96ee1c71b61e3a903f4383ef79af1b564" }, { "label": "python_compatibility", @@ -187,21 +201,21 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "eede973e03cdf2193a94efffbff49edaba48a65c86821fa78e0538eeb4c3d4b5" + "sha256": "25fb76ad9aa86162a6554b0f2aacfe824d93d5117908efe78889c2342541ba0a" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "892a8e8364a25b1035518bfe69cf3a381e5755235b83f54f4942fa2cee31ccd9" + "sha256": "05ba9ffcca16b69f2a1b4cc0e57f4325758db3048091ae15d1e9af5db325a78f" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "50c23ac052b288665d10c81e80f79c7b1c3437c815012816815715d07cc0d0fc" + "bytes": 8604, + "sha256": "1c3fdea61d50ae05224bc7ebeffcf4ec205de213ab0755f6c6593ef76ad59726" }, { "label": "skill_os2_audit", @@ -235,8 +249,8 @@ "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 41208, - "sha256": "d50e4ed44a4576b5967001fe82c8d09f317bdcbaeb50723e64a88af6c898f04b" + "bytes": 41202, + "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960" }, { "label": "world_class_submission_review", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index dad58e9..2035c85 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `026efd17e382dd925526d04fd0ac29a75990d4df` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961` +Commit: `355a3cce361da21fe0aab010e6643c05ad98429e` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `8fcd68d90682` -- archive sha256: `11c535377813` +- source contract sha256: `918e8741fc7b` +- archive sha256: `872d0ea85c10` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `7d33c2082209f18d4e9530e53fc574eae34fe148316947b16640742 - 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: `26` 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: `7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961` +- sha256: `b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801` ## Methodology Sections @@ -72,21 +73,21 @@ 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 | `93beb4bf94e0` | +| output_execution | `reports/output_execution_runs.json` | present | `04aef19563f0` | | 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 | `034e530e2efd` | +| trust_report | `reports/security_trust_report.json` | present | `b4ae0799ef42` | | python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` | -| registry_audit | `reports/registry_audit.json` | present | `eede973e03cd` | -| package_verification | `reports/package_verification.json` | present | `892a8e8364a2` | -| install_simulation | `reports/install_simulation.json` | present | `50c23ac052b2` | +| registry_audit | `reports/registry_audit.json` | present | `25fb76ad9aa8` | +| package_verification | `reports/package_verification.json` | present | `05ba9ffcca16` | +| install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `c0e499f9f051` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `b8976c340da4` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `7f502f722ff1` | -| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `d50e4ed44a45` | +| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `97924dd4be88` | | world_class_submission_review | `reports/world_class_submission_review.json` | present | `6aaf868374ba` | | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `2f2c896a14b8` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `e9b66ef084e6` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index eeb3e74..78d28a9 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 3c48625..aa1e809 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,15 +6,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1051064, + "other_text_tokens": 1051041, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1051861, - "deferred_resource_tokens": 486718, + "estimated_total_text_tokens": 1051838, + "deferred_resource_tokens": 486754, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125 }, { @@ -36,7 +36,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125 } ], @@ -59,7 +59,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/context_budget.md b/reports/context_budget.md index d918bd6..4d8e813 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 990 | 797 | 486718 | `governed` | scripts:426601 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 486754 | `governed` | scripts:426637 | 131.3 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 777132d..de7a0c4 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", @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 486718, + "deferred_resource_tokens": 486754, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index ceded38..cdda075 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 486718/120000; top deferred scripts 426601; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486754/120000; top deferred scripts 426637; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 486718/120000; top deferred scripts 426601; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486754/120000; top deferred scripts 426637; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -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" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "026efd17e382dd925526d04fd0ac29a75990d4df", - "actual": "026efd17e382dd925526d04fd0ac29a75990d4df", + "expected": "355a3cce361da21fe0aab010e6643c05ad98429e", + "actual": "355a3cce361da21fe0aab010e6643c05ad98429e", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,30 +261,30 @@ "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": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "026efd17e382dd925526d04fd0ac29a75990d4df", - "actual": "026efd17e382dd925526d04fd0ac29a75990d4df", + "expected": "355a3cce361da21fe0aab010e6643c05ad98429e", + "actual": "355a3cce361da21fe0aab010e6643c05ad98429e", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,30 +407,30 @@ "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": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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/output_execution_runs.json b/reports/output_execution_runs.json index f9675a1..fb92919 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": 36.18, + "duration_ms": 37.75, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.3, + "duration_ms": 35.84, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 42.52, + "duration_ms": 37.3, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 52.72, + "duration_ms": 39.77, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 40.07, + "duration_ms": 40.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 60.34, + "duration_ms": 39.49, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 50.43, + "duration_ms": 39.5, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 54.34, + "duration_ms": 41.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.83, + "duration_ms": 46.76, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.93, + "duration_ms": 41.32, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 698304b..1947741 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 | 36.18 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 37.3 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 42.52 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 52.72 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 40.07 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 60.34 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 50.43 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 54.34 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 45.83 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 45.93 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 37.75 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 35.84 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 37.3 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 39.77 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 40.85 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 39.49 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 39.5 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 41.42 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 46.76 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 41.32 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 85d8e3e..3e183f7 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": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 69ced74..fc3cdbe 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: `11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e` +- Archive SHA256: `872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index f4fd071..46c1786 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 c4b85fb..9057917 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 71fffd1..70b5b6d 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 28af278..1d61707 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b` -- Archive SHA256: `11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e` +- Package SHA256: `918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee` +- Archive SHA256: `872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index b77cfe4..d5a7cb7 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

852 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

852 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 486718/120000; top deferred scripts 426601; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 852 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

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

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

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

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 486754/120000; top deferred scripts 426637; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 852 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

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

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

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

@@ -812,12 +812,12 @@
-

上下文

initial load 990/1000; deferred 486718/120000; top deferred scripts 426601; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 486754/120000; top deferred scripts 426637; resource governance governed; quality density 131.3

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b
+

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

@@ -882,8 +882,8 @@
-

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

@@ -903,12 +903,12 @@

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
11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e
+

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
872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0

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
652
失败数
0
警告数
0
归档哈希
11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0
diff --git a/reports/review-studio.json b/reports/review-studio.json index 1ca0b14..dc6b680 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -44,7 +44,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 486718/120000; top deferred scripts 426601; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486754/120000; top deferred scripts 426637; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -1968,13 +1968,13 @@ "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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1992,11 +1992,11 @@ "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": 26 }, - "commit": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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.", @@ -2101,7 +2101,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "skill_atlas": { "skill_count": 12, @@ -2139,8 +2139,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -2171,12 +2171,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -2187,7 +2187,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -2266,12 +2266,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, @@ -4688,7 +4688,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.18, + "duration_ms": 31.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4716,7 +4716,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.3, + "duration_ms": 31.22, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4739,7 +4739,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 42.52, + "duration_ms": 33.81, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4767,7 +4767,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 52.72, + "duration_ms": 34.49, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4790,7 +4790,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 40.07, + "duration_ms": 32.87, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4818,7 +4818,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 60.34, + "duration_ms": 31.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4841,7 +4841,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 50.43, + "duration_ms": 30.83, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4868,7 +4868,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 54.34, + "duration_ms": 31.27, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4891,7 +4891,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.83, + "duration_ms": 30.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4920,7 +4920,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.93, + "duration_ms": 31.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5646,23 +5646,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 26, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/install_simulation.json", + " M reports/install_simulation.md", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md" + ], "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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5680,14 +5693,15 @@ "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": 26 }, "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)", @@ -5696,10 +5710,10 @@ "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": "026efd17e382dd925526d04fd0ac29a75990d4df", + "ready": false, + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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)", @@ -5707,7 +5721,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961" + "sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5780,8 +5794,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "93beb4bf94e08e6b75f35ff6f1a2029a9b9092717d691f42cf507b09bc590572" + "bytes": 7967, + "sha256": "04aef19563f053de353bff888ecf7faa938668f7c2edefe36c4ce95b31879066" }, { "label": "blind_review", @@ -5816,7 +5830,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "034e530e2efdd5c28f7e6ff97b2c7621aa88f8d6899df4d2b7f73048277f5541" + "sha256": "b4ae0799ef42fe9699136b8cc49c09f96ee1c71b61e3a903f4383ef79af1b564" }, { "label": "python_compatibility", @@ -5830,21 +5844,21 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "eede973e03cdf2193a94efffbff49edaba48a65c86821fa78e0538eeb4c3d4b5" + "sha256": "25fb76ad9aa86162a6554b0f2aacfe824d93d5117908efe78889c2342541ba0a" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "892a8e8364a25b1035518bfe69cf3a381e5755235b83f54f4942fa2cee31ccd9" + "sha256": "05ba9ffcca16b69f2a1b4cc0e57f4325758db3048091ae15d1e9af5db325a78f" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "50c23ac052b288665d10c81e80f79c7b1c3437c815012816815715d07cc0d0fc" + "bytes": 8604, + "sha256": "1c3fdea61d50ae05224bc7ebeffcf4ec205de213ab0755f6c6593ef76ad59726" }, { "label": "skill_os2_audit", @@ -5878,8 +5892,8 @@ "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 41208, - "sha256": "d50e4ed44a4576b5967001fe82c8d09f317bdcbaeb50723e64a88af6c898f04b" + "bytes": 41202, + "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960" }, { "label": "world_class_submission_review", @@ -11679,7 +11693,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -11719,7 +11733,7 @@ { "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, @@ -11816,7 +11830,7 @@ { "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, @@ -11898,7 +11912,7 @@ { "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, @@ -11980,7 +11994,7 @@ { "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, @@ -12091,7 +12105,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "failures": [], "warnings": [], @@ -16515,15 +16529,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1051064, + "other_text_tokens": 1050992, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1051861, - "deferred_resource_tokens": 486718, + "estimated_total_text_tokens": 1051789, + "deferred_resource_tokens": 486754, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125 }, { @@ -16545,7 +16559,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125 } ], @@ -16568,7 +16582,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426601, + "estimated_tokens": 426637, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -17419,7 +17433,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skills": [ { "name": "yao-meta-skill", @@ -17633,8 +17647,8 @@ "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 } }, @@ -18297,7 +18311,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 74, + "age_days": 77, "allowed_days": 31, "actionable": false, "scope": "example" @@ -18465,7 +18479,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T07:12:10Z", + "generated_at": "2026-06-16", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -23459,8 +23473,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -23491,16 +23505,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "package_count": 1, "packages": [ { @@ -23516,7 +23530,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, @@ -23539,7 +23553,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -24198,11 +24212,11 @@ "install_simulation": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "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": 652, @@ -24223,7 +24237,7 @@ { "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", @@ -24469,16 +24483,16 @@ "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" } }, "upgrade_check": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -24547,12 +24561,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, @@ -24567,8 +24581,8 @@ "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" } }, "manifest": { diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 3fa3ca9..c13815f 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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": 26 }, - "commit": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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.", @@ -1130,7 +1130,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "skill_atlas": { "skill_count": 12, @@ -1168,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -1200,12 +1200,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1295,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 76fadc1..66f2b1d 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 d88d2a1..a994e85 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, @@ -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 \"\" --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 46be463..df7cc04 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -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 "" --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/security_trust_report.json b/reports/security_trust_report.json index e84ccb3..ab76643 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index cee7549..c6a120a 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `216` -- Package SHA256: `8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b` +- Package SHA256: `918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee` ## Failures diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index ca75c98..c7a244f 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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": 26 }, - "commit": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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.", @@ -1134,7 +1134,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "skill_atlas": { "skill_count": 12, @@ -1172,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -1204,12 +1204,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1299,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 43269f7..e483c60 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": "7d33c2082209f18d4e9530e53fc574eae34fe148316947b166407426922c9961", - "source_contract_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "evidence_bundle_sha256": "b2a63bb337332a25879de627f67aed0d5f75dd8278c1c08d0018a03175e64801", + "source_contract_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "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": 26 }, - "commit": "026efd17e382dd925526d04fd0ac29a75990d4df", + "commit": "355a3cce361da21fe0aab010e6643c05ad98429e", "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.", @@ -1129,7 +1129,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b", - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "package_sha256": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, "compatibility": { "openai": "pass", @@ -1199,12 +1199,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e", + "archive_sha256": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index fe5def6..6e200f1 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 ee9676e..b0645b0 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 652; 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 9a554d2..aa96739 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 cfeba86..eda84e3 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 992f8a4..94148cd 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "11c535377813c5424308dbb30a57bbedde6b9acefffbfe0456364b00f130b89e" + "to": "872d0ea85c10af1825c529f2f2f2b1b9a4e41723caba6afcb7091872b502e4f0" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8fcd68d906823c7bcd96d21c765555ab7d53183876b34806a6b5bc29e817154b" + "to": "918e8741fc7b1a61b460ad7ca075d189b0d70eb65175329ecd40372245255aee" } ] }, diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index 18f8d5e..d67c56c 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 e33c953..c389e49 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 a94086f..df978d9 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, @@ -312,7 +312,7 @@ "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 c5a01fa..297677c 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 4296221..34a900c 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, @@ -398,7 +398,7 @@ "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:///", @@ -435,7 +435,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -456,8 +456,8 @@ "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." }, @@ -473,8 +473,8 @@ } ], "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 af5bb21..94cd207 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 @@ -171,8 +171,8 @@ 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 @@ -196,7 +196,7 @@ 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 7c8a7bc..50908b3 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", @@ -146,7 +146,7 @@ "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:///", @@ -309,7 +309,7 @@ "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 f3cdfe0..3a1b096 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_evidence_preflight.html b/reports/world_class_evidence_preflight.html index 6c8d166..88f28e2 100644 --- a/reports/world_class_evidence_preflight.html +++ b/reports/world_class_evidence_preflight.html @@ -65,7 +65,7 @@ Evidence Collection

World-Class Evidence Preflight

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.

-
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source6/13
+
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source7/13
@@ -611,15 +611,15 @@
-
+
adoption_sample_count Adoption sample
-
Current
0
+
Current
1
Expected
>0
-
Status
blocked
+
Status
pass
Action
Telemetry must include adoption outcome evidence.
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index aecc149..4a7eaf7 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.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, @@ -14,8 +14,8 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "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": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "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": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 696f261..e487d32 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -1,6 +1,6 @@ # World-Class Evidence Preflight -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary @@ -10,7 +10,7 @@ Generated at: `2026-06-16` - credential value exposed: `false` - collection ready: `1` - collection blocked: `3` -- source checks: `6` pass / `13` total +- source checks: `7` 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 | `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_operator_runbook.html b/reports/world_class_operator_runbook.html index a3b8b9f..9fa92ce 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 0803f4f..6108ef7 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" @@ -399,7 +399,7 @@ "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.", @@ -447,7 +447,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -468,8 +468,8 @@ "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." }, @@ -484,10 +484,9 @@ "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 e65b9a3..8ba17d8 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 @@ -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: `2` +- blocked source checks: `1` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -297,14 +297,13 @@ 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 43a75d2..8abee31 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" @@ -302,7 +302,7 @@ "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 @@ -323,8 +323,8 @@ "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." }, @@ -340,8 +340,8 @@ } ], "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 7d625fc..21bd5b5 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 @@ -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: 0 / >0 => blocked +- Adoption sample: 1 / >0 => pass - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/scripts/render_review_studio.py b/scripts/render_review_studio.py index 05783e6..63951d5 100644 --- a/scripts/render_review_studio.py +++ b/scripts/render_review_studio.py @@ -7,7 +7,7 @@ from typing import Any from review_studio_actions import build_review_actions, render_review_actions from review_studio_data import evidence_paths, insight_cards, load_review_data -from review_studio_formatting import registry_package_summary, render_kv_grid +from review_studio_formatting import registry_package_summary, render_gate_contract_panel, render_kv_grid from review_studio_gates import add_blockers_from_gate, build_gates, gate_contract, status_label, weighted_score from review_studio_layout import render_review_nav, review_studio_css from review_studio_output_review import render_output_review_section @@ -123,19 +123,7 @@ def render_html(report: dict[str, Any]) -> str: description = overview.get("description") or frontmatter.get("description", "") nav_html = render_review_nav() gates_html = render_gate_list(gates) - gate_contract_panel = render_kv_grid( - report.get("gate_contract", {}), - [ - "ok", - "expected_gate_count", - "actual_gate_count", - "missing_gate_keys", - "unknown_gate_keys", - "duplicate_gate_keys", - "unweighted_gate_keys", - ], - "gate contract missing", - ) + gate_contract_panel = render_gate_contract_panel(report.get("gate_contract", {})) metrics_html = render_insights(insights) blockers_html = render_issue_list("阻断事项", blockers) warnings_html = render_issue_list("关注事项", warnings) diff --git a/scripts/review_studio_formatting.py b/scripts/review_studio_formatting.py index bf460ca..a6d3134 100644 --- a/scripts/review_studio_formatting.py +++ b/scripts/review_studio_formatting.py @@ -169,6 +169,22 @@ def render_kv_grid( return "
" + "".join(rows) + "
" +def render_gate_contract_panel(contract: dict[str, Any]) -> str: + return render_kv_grid( + contract, + [ + "ok", + "expected_gate_count", + "actual_gate_count", + "missing_gate_keys", + "unknown_gate_keys", + "duplicate_gate_keys", + "unweighted_gate_keys", + ], + "gate contract missing", + ) + + def registry_package_summary(package: dict[str, Any]) -> dict[str, Any]: if not package: return {}