diff --git a/registry/index.json b/registry/index.json index 45a132e..a0d0e88 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 1db0490..8cedb10 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,7 +16,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json index ff0accc..7eb62e9 100644 --- a/reports/adaptation_proposals.json +++ b/reports/adaptation_proposals.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md index 2f02219..ab42ec8 100644 --- a/reports/adaptation_proposals.md +++ b/reports/adaptation_proposals.md @@ -1,6 +1,6 @@ # Adaptation Proposals -- Generated at: `2026-06-17T08:08:10Z` +- Generated at: `2026-06-17T08:26:15Z` - Pattern report: `reports/user_patterns.json` - Proposal only: `true` - Writes repository files: `false` diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index d96524c..987aae9 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": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:14Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 07c883c..ed2da22 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -16,9 +16,9 @@ "watch_line_threshold": 720, "early_watch_line_threshold": 600, "block_line_threshold": 1500, - "largest_file_lines": 711, + "largest_file_lines": 718, "watchlist_count": 0, - "early_watchlist_count": 5, + "early_watchlist_count": 6, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -26,7 +26,7 @@ "largest_files": [ { "path": "tests/verify_evidence_consistency.py", - "lines": 711, + "lines": 718, "kind": "test", "severity": "pass", "early_watch": true, @@ -50,7 +50,15 @@ }, { "path": "scripts/render_evidence_consistency.py", - "lines": 659, + "lines": 699, + "kind": "cli-script", + "severity": "pass", + "early_watch": true, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, + { + "path": "scripts/render_benchmark_reproducibility.py", + "lines": 673, "kind": "cli-script", "severity": "pass", "early_watch": true, @@ -111,21 +119,13 @@ "severity": "pass", "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, - { - "path": "scripts/render_review_studio.py", - "lines": 578, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." } ], "watchlist": [], "early_watchlist": [ { "path": "tests/verify_evidence_consistency.py", - "lines": 711, + "lines": 718, "kind": "test", "severity": "pass", "early_watch": true, @@ -149,7 +149,15 @@ }, { "path": "scripts/render_evidence_consistency.py", - "lines": 659, + "lines": 699, + "kind": "cli-script", + "severity": "pass", + "early_watch": true, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, + { + "path": "scripts/render_benchmark_reproducibility.py", + "lines": 673, "kind": "cli-script", "severity": "pass", "early_watch": true, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index f254d8f..9a7b039 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -13,9 +13,9 @@ Generated at: `2026-06-17` - Yao CLI command handlers: `68` - entrypoint command handlers: `18` - command modules: `6` -- largest file lines: `711` +- largest file lines: `718` - early watch threshold lines: `600` -- early watchlist: `5` +- early watchlist: `6` - watch threshold lines: `720` - watchlist: `0` - hotspots: `0` @@ -35,20 +35,22 @@ No near-threshold files found. | File | Lines | Kind | Recommended next split | | --- | ---: | --- | --- | -| `tests/verify_evidence_consistency.py` | `711` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | +| `tests/verify_evidence_consistency.py` | `718` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `tests/verify_world_class_evidence_intake.py` | `703` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `tests/verify_yao_cli.py` | `700` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | -| `scripts/render_evidence_consistency.py` | `659` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | +| `scripts/render_evidence_consistency.py` | `699` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | +| `scripts/render_benchmark_reproducibility.py` | `673` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/render_world_class_operator_runbook.py` | `651` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | ## Largest Files | File | Lines | Kind | Severity | | --- | ---: | --- | --- | -| `tests/verify_evidence_consistency.py` | `711` | `test` | `pass` | +| `tests/verify_evidence_consistency.py` | `718` | `test` | `pass` | | `tests/verify_world_class_evidence_intake.py` | `703` | `test` | `pass` | | `tests/verify_yao_cli.py` | `700` | `test` | `pass` | -| `scripts/render_evidence_consistency.py` | `659` | `cli-script` | `pass` | +| `scripts/render_evidence_consistency.py` | `699` | `cli-script` | `pass` | +| `scripts/render_benchmark_reproducibility.py` | `673` | `cli-script` | `pass` | | `scripts/render_world_class_operator_runbook.py` | `651` | `cli-script` | `pass` | | `tests/verify_output_review_adjudication.py` | `599` | `test` | `pass` | | `scripts/render_skill_overview.py` | `588` | `cli-script` | `pass` | @@ -56,7 +58,6 @@ No near-threshold files found. | `scripts/build_skill_atlas.py` | `586` | `cli-script` | `pass` | | `scripts/optimize_description.py` | `585` | `cli-script` | `pass` | | `scripts/trust_check.py` | `582` | `cli-script` | `pass` | -| `scripts/render_review_studio.py` | `578` | `cli-script` | `pass` | ## Release Rule diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 330ec34..76d62f8 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,43 +3,43 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "git_status": { "available": true, "dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "generated_dirty": true, - "generated_changed_file_count": 30, + "generated_changed_file_count": 32, "source_dirty": false, "source_changed_file_count": 0, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "generated_dirty_prefixes": [ "dist/", @@ -57,8 +57,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -76,14 +76,46 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 + }, + "beta_test_release": { + "ready": true, + "scope": "beta/public test release without superiority, fully-reviewed, or world-class claims", + "blockers": [], + "allowed_deferred_evidence": [ + { + "key": "human-adjudication", + "label": "Human blind-review adjudication", + "reason": "Deferred for beta/public testing; still required before superiority, fully-reviewed, or world-class claims." + }, + { + "key": "provider-ledger-review", + "label": "Independent provider ledger review", + "reason": "Provider source evidence may be complete, but independent ledger acceptance remains formal-claim evidence." + }, + { + "key": "native-permission-enforcement", + "label": "Native permission enforcement evidence", + "reason": "Native enforcement proof is deferred for beta/public testing and remains required for world-class claims." + }, + { + "key": "native-client-telemetry", + "label": "Real client telemetry evidence", + "reason": "Real client telemetry is deferred for beta/public testing and remains required for world-class claims." + } + ], + "policy": "Human blind-review, native permission enforcement, real client telemetry, and ledger acceptance may be deferred for beta/public testing, but public claims must remain blocked until those evidence entries are accepted.", + "required_wording": "Use beta, public test, or technical preview wording; do not claim world-class readiness, fully reviewed quality, or proven superiority over baseline." }, "public_claim": { "ready": false, @@ -97,10 +129,10 @@ }, "release_lock": { "ready": true, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "status_scope": "generation-time status before this report is written", "source_changed_file_count": 0, - "generated_changed_file_count": 30, + "generated_changed_file_count": 32, "reason": "only generated evidence artifacts were dirty at generation time" }, "evidence_bundle": { @@ -109,7 +141,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935" + "sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -218,7 +250,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 137787, - "sha256": "76e0d31fe1e0e0c6f96eaa2321733ca456d8c59d3eb9007a941bb3d8afdbc02e" + "sha256": "cd8289dd2d822739d16f0ed70da2bc592a9326942cbf0b601efee7a158593055" }, { "label": "python_compatibility", @@ -232,7 +264,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3137, - "sha256": "49e2aee07e38a83608504a3a4f79dc07889e4ba899c4b96859721a5a7cb0a856" + "sha256": "2c236f7c2fff1cc0ae4a95464bf354c162457ab13b8b2b94a30a1b739eef571d" }, { "label": "package_verification", @@ -446,7 +478,8 @@ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ], "artifacts": { "json": "reports/benchmark_reproducibility.json", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 4efa5a0..18a8c12 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,11 +1,11 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `d845e9513c67b9572fb6c2a8754d3a0051e735ad` +Commit: `ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789` Working tree dirty at generation: `true` Source tree dirty at generation: `false` Generated evidence dirty at generation: `true` -Evidence bundle SHA256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935` +Evidence bundle SHA256: `c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1` ## Summary @@ -14,7 +14,7 @@ Evidence bundle SHA256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c52 - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `7fc324e26d61` +- source contract sha256: `c39574e9de81` - archive sha256: `7db44f059844` - output cases: `5` - disclosed failure cases: `3` @@ -23,14 +23,35 @@ Evidence bundle SHA256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c52 - human review complete: `false` - world-class ready: `false` - world-class source checks: `11` pass / `19` total; `8` blocked +- beta test ready: `true` +- beta test blockers: `0` +- beta deferred evidence: `4` - public claim ready: `false` - public claim blockers: `3` -- changed files at generation: `30` +- changed files at generation: `32` - source changed files at generation: `0` -- generated changed files at generation: `30` +- generated changed files at generation: `32` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. +## Beta Test Boundary + +- ready: `true` +- scope: beta/public test release without superiority, fully-reviewed, or world-class claims +- policy: Human blind-review, native permission enforcement, real client telemetry, and ledger acceptance may be deferred for beta/public testing, but public claims must remain blocked until those evidence entries are accepted. +- required wording: Use beta, public test, or technical preview wording; do not claim world-class readiness, fully reviewed quality, or proven superiority over baseline. + +| Blocker | +| --- | +| none | + +| Deferred evidence | Reason | +| --- | --- | +| `human-adjudication` | Deferred for beta/public testing; still required before superiority, fully-reviewed, or world-class claims. | +| `provider-ledger-review` | Provider source evidence may be complete, but independent ledger acceptance remains formal-claim evidence. | +| `native-permission-enforcement` | Native enforcement proof is deferred for beta/public testing and remains required for world-class claims. | +| `native-client-telemetry` | Real client telemetry is deferred for beta/public testing and remains required for world-class claims. | + ## Public Claim Boundary - ready: `false` @@ -53,7 +74,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935` +- sha256: `c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1` ## Methodology Sections @@ -80,9 +101,9 @@ This report proves local benchmark reproducibility only. It keeps external provi | review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` | | trigger_scorecard | `reports/route_scorecard.json` | present | `a649547a7d3d` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `76e0d31fe1e0` | +| trust_report | `reports/security_trust_report.json` | present | `cd8289dd2d82` | | python_compatibility | `reports/python_compatibility.json` | present | `d31dc03c74f1` | -| registry_audit | `reports/registry_audit.json` | present | `49e2aee07e38` | +| registry_audit | `reports/registry_audit.json` | present | `2c236f7c2fff` | | package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` | | install_simulation | `reports/install_simulation.json` | present | `c1f1122264b8` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `6362e79a8cfd` | @@ -157,3 +178,4 @@ This report proves local benchmark reproducibility only. It keeps external provi - Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet. - Pending blind-review decisions are visible but do not count as human adjudication. - World-class readiness remains false until external and human evidence gaps close. +- Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims. diff --git a/reports/context_budget.json b/reports/context_budget.json index 52a2c25..1298c92 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": 805, - "other_text_tokens": 1153001, + "other_text_tokens": 1155569, "estimated_initial_load_tokens": 998, - "estimated_total_text_tokens": 1153806, - "deferred_resource_tokens": 523653, + "estimated_total_text_tokens": 1156374, + "deferred_resource_tokens": 525406, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153 }, { @@ -36,7 +36,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153 } ], @@ -59,7 +59,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153, "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 a6e4d38..5ca8c61 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 | 998 | 805 | 523653 | `governed` | scripts:462350 | 140.3 | - | ok | +| root | `.` | `production` | 1000 | 998 | 805 | 525406 | `governed` | scripts:464103 | 140.3 | - | 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 c3dd2f9..87d5ba0 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 998, "skill_body_tokens": 805, - "deferred_resource_tokens": 523653, + "deferred_resource_tokens": 525406, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153, "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 bf04bcf..74dae4b 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -4,14 +4,14 @@ "generated_at": "2026-06-17", "skill_dir": ".", "summary": { - "check_count": 38, - "pass_count": 38, + "check_count": 39, + "pass_count": 39, "warn_count": 0, "fail_count": 0, "decision": "consistent" }, "status_counts": { - "pass": 38, + "pass": 39, "warn": 0, "fail": 0 }, @@ -324,12 +324,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 998/1000; deferred 523653/120000; top deferred scripts 462350; resource governance governed; quality density 140.3", + "detail": "initial load 998/1000; deferred 525406/120000; top deferred scripts 464103; resource governance governed; quality density 140.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 998/1000; deferred 523653/120000; top deferred scripts 462350; resource governance governed; quality density 140.3", + "detail": "initial load 998/1000; deferred 525406/120000; top deferred scripts 464103; resource governance governed; quality density 140.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -357,7 +357,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 28 + "changed_file_count": 30 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -398,8 +398,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", - "actual": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "expected": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", + "actual": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -414,12 +414,15 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3 }, @@ -427,12 +430,15 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3 }, @@ -544,8 +550,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", - "actual": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "expected": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", + "actual": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -560,12 +566,15 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3 }, @@ -573,12 +582,15 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3 }, @@ -1974,6 +1986,32 @@ ], "detail": "Benchmark reproducibility must not overstate public claim readiness." }, + { + "key": "benchmark-beta-public-claim-split", + "label": "Benchmark separates beta testing from public claims", + "status": "pass", + "expected": { + "beta_test_ready": true, + "public_claim_ready": false, + "human_review_complete": false, + "beta_release_ready": true, + "beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims", + "deferred_human_review": true + }, + "actual": { + "beta_test_ready": true, + "public_claim_ready": false, + "human_review_complete": false, + "beta_release_ready": true, + "beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims", + "deferred_human_review": true + }, + "paths": [ + "reports/benchmark_reproducibility.json", + "reports/world_class_evidence_ledger.json" + ], + "detail": "Beta/public testing may proceed with human blind review deferred, but public world-class or superiority claims must remain blocked." + }, { "key": "preflight-world-class-boundary", "label": "Preflight mirrors ledger without accepting evidence", diff --git a/reports/evidence_consistency.md b/reports/evidence_consistency.md index 808d0cb..013fa85 100644 --- a/reports/evidence_consistency.md +++ b/reports/evidence_consistency.md @@ -5,8 +5,8 @@ Generated at: `2026-06-17` ## Summary - decision: `consistent` -- checks: `38` -- pass: `38` +- checks: `39` +- pass: `39` - warn: `0` - fail: `0` @@ -46,6 +46,7 @@ This gate compares generated evidence reports against each other. It does not cr | interpretation has a stable HTML contract | `pass` | Report output paths and language defaults are part of the user-facing contract. | `reports/skill-interpretation.json`, `reports/skill-interpretation.html` | | Coverage report mirrors world-class evidence boundary | `pass` | Blueprint coverage can be locally complete while public world-class evidence remains pending. | `reports/world_class_evidence_ledger.json`, `reports/skill_os2_coverage.json` | | Benchmark report mirrors world-class evidence boundary | `pass` | Benchmark reproducibility must not overstate public claim readiness. | `reports/world_class_evidence_ledger.json`, `reports/benchmark_reproducibility.json` | +| Benchmark separates beta testing from public claims | `pass` | Beta/public testing may proceed with human blind review deferred, but public world-class or superiority claims must remain blocked. | `reports/benchmark_reproducibility.json`, `reports/world_class_evidence_ledger.json` | | Preflight mirrors ledger without accepting evidence | `pass` | Collection preflight may help operators gather evidence, but it must not print secrets or change world-class readiness. | `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_preflight.json` | | Preflight exposes a safe submission-kit handoff | `pass` | Preflight must give operators the exact draft, SHA-prefill, intake, review, ledger, and claim-guard commands without letting drafts, prefill, or submissions count as accepted evidence. | `reports/world_class_evidence_preflight.json`, `reports/world_class_evidence_preflight.html` | | Review Studio mirrors preflight artifact roles | `pass` | The Review Studio world-class action card must carry the same submission-ref versus supporting-evidence contract as the preflight handoff. | `reports/world_class_evidence_preflight.json`, `reports/review-studio.json` | diff --git a/reports/registry_audit.json b/reports/registry_audit.json index f4a68a3..3d744c8 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index e2272c9..d806534 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111` +- Package SHA256: `c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c` - Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index 355b26d..c5bb9c6 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -772,12 +772,12 @@

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 10; 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

3 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

153 scripts scanned; secrets found

Py Compat0

232 files scanned for Python 3.11

Arch Debt0

711 largest lines; 0 watchlist; 5 early; 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 false

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

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

689 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 10; 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

3 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

153 scripts scanned; secrets found

Py Compat0

232 files scanned for Python 3.11

Arch Debt0

718 largest lines; 0 watchlist; 6 early; 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 false

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

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

689 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 10; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 998/1000; deferred 523653/120000; top deferred scripts 462350; resource governance governed; quality density 140.3

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; 153 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 232 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

229 Python files; 0 hotspots; 0 watchlist files; 5 early watch files; 0 blockers; largest 711 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 false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

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 11/19 pass; 8 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 10; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 998/1000; deferred 525406/120000; top deferred scripts 464103; resource governance governed; quality density 140.3

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; 153 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 232 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

229 Python files; 0 hotspots; 0 watchlist files; 6 early watch files; 0 blockers; largest 718 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 false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

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 11/19 pass; 8 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

@@ -844,12 +844,12 @@
-

上下文

initial load 998/1000; deferred 523653/120000; top deferred scripts 462350; resource governance governed; quality density 140.3

+

上下文

initial load 998/1000; deferred 525406/120000; top deferred scripts 464103; resource governance governed; quality density 140.3

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
153
网络脚本
3
Help 失败
0
包体哈希
7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111
+

信任报告

Secret
0
脚本数
153
网络脚本
3
Help 失败
0
包体哈希
c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c

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。

diff --git a/reports/review-studio.json b/reports/review-studio.json index d470844..b45e0fc 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -65,7 +65,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 998/1000; deferred 523653/120000; top deferred scripts 462350; resource governance governed; quality density 140.3", + "detail": "initial load 998/1000; deferred 525406/120000; top deferred scripts 464103; resource governance governed; quality density 140.3", "evidence": "reports/context_budget.json", "link": "context_budget.md", "review_action_id": "", @@ -125,7 +125,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "229 Python files; 0 hotspots; 0 watchlist files; 5 early watch files; 0 blockers; largest 711 lines; 68 CLI handlers; 18 in entrypoint", + "detail": "229 Python files; 0 hotspots; 0 watchlist files; 6 early watch files; 0 blockers; largest 718 lines; 68 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md", "review_action_id": "", @@ -2480,8 +2480,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -2499,22 +2499,26 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 }, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ] }, "runtime_conformance": { @@ -2613,7 +2617,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "skill_atlas": { "skill_count": 12, @@ -2651,7 +2655,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -2783,7 +2787,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, @@ -6331,43 +6335,43 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "git_status": { "available": true, "dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "generated_dirty": true, - "generated_changed_file_count": 30, + "generated_changed_file_count": 32, "source_dirty": false, "source_changed_file_count": 0, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html", - " M reports/skill-interpretation.json" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "generated_dirty_prefixes": [ "dist/", @@ -6385,8 +6389,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -6404,14 +6408,46 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 + }, + "beta_test_release": { + "ready": true, + "scope": "beta/public test release without superiority, fully-reviewed, or world-class claims", + "blockers": [], + "allowed_deferred_evidence": [ + { + "key": "human-adjudication", + "label": "Human blind-review adjudication", + "reason": "Deferred for beta/public testing; still required before superiority, fully-reviewed, or world-class claims." + }, + { + "key": "provider-ledger-review", + "label": "Independent provider ledger review", + "reason": "Provider source evidence may be complete, but independent ledger acceptance remains formal-claim evidence." + }, + { + "key": "native-permission-enforcement", + "label": "Native permission enforcement evidence", + "reason": "Native enforcement proof is deferred for beta/public testing and remains required for world-class claims." + }, + { + "key": "native-client-telemetry", + "label": "Real client telemetry evidence", + "reason": "Real client telemetry is deferred for beta/public testing and remains required for world-class claims." + } + ], + "policy": "Human blind-review, native permission enforcement, real client telemetry, and ledger acceptance may be deferred for beta/public testing, but public claims must remain blocked until those evidence entries are accepted.", + "required_wording": "Use beta, public test, or technical preview wording; do not claim world-class readiness, fully reviewed quality, or proven superiority over baseline." }, "public_claim": { "ready": false, @@ -6425,10 +6461,10 @@ }, "release_lock": { "ready": true, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "status_scope": "generation-time status before this report is written", "source_changed_file_count": 0, - "generated_changed_file_count": 30, + "generated_changed_file_count": 32, "reason": "only generated evidence artifacts were dirty at generation time" }, "evidence_bundle": { @@ -6437,7 +6473,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935" + "sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -6546,7 +6582,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 137787, - "sha256": "76e0d31fe1e0e0c6f96eaa2321733ca456d8c59d3eb9007a941bb3d8afdbc02e" + "sha256": "cd8289dd2d822739d16f0ed70da2bc592a9326942cbf0b601efee7a158593055" }, { "label": "python_compatibility", @@ -6560,7 +6596,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3137, - "sha256": "49e2aee07e38a83608504a3a4f79dc07889e4ba899c4b96859721a5a7cb0a856" + "sha256": "2c236f7c2fff1cc0ae4a95464bf354c162457ab13b8b2b94a30a1b739eef571d" }, { "label": "package_verification", @@ -6774,7 +6810,8 @@ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ], "artifacts": { "json": "reports/benchmark_reproducibility.json", @@ -7396,7 +7433,7 @@ "label": "Evidence Consistency", "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", - "current": "38 consistency checks", + "current": "39 consistency checks", "command": "make ci-test", "test": "tests/verify_evidence_consistency.py", "evidence": [ @@ -12986,7 +13023,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "failures": [], "warnings": [], @@ -17952,9 +17989,9 @@ "watch_line_threshold": 720, "early_watch_line_threshold": 600, "block_line_threshold": 1500, - "largest_file_lines": 711, + "largest_file_lines": 718, "watchlist_count": 0, - "early_watchlist_count": 5, + "early_watchlist_count": 6, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -17962,7 +17999,7 @@ "largest_files": [ { "path": "tests/verify_evidence_consistency.py", - "lines": 711, + "lines": 718, "kind": "test", "severity": "pass", "early_watch": true, @@ -17986,7 +18023,15 @@ }, { "path": "scripts/render_evidence_consistency.py", - "lines": 659, + "lines": 699, + "kind": "cli-script", + "severity": "pass", + "early_watch": true, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, + { + "path": "scripts/render_benchmark_reproducibility.py", + "lines": 673, "kind": "cli-script", "severity": "pass", "early_watch": true, @@ -18047,21 +18092,13 @@ "severity": "pass", "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, - { - "path": "scripts/render_review_studio.py", - "lines": 578, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." } ], "watchlist": [], "early_watchlist": [ { "path": "tests/verify_evidence_consistency.py", - "lines": 711, + "lines": 718, "kind": "test", "severity": "pass", "early_watch": true, @@ -18085,7 +18122,15 @@ }, { "path": "scripts/render_evidence_consistency.py", - "lines": 659, + "lines": 699, + "kind": "cli-script", + "severity": "pass", + "early_watch": true, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, + { + "path": "scripts/render_benchmark_reproducibility.py", + "lines": 673, "kind": "cli-script", "severity": "pass", "early_watch": true, @@ -18115,15 +18160,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 805, - "other_text_tokens": 1153001, + "other_text_tokens": 1155569, "estimated_initial_load_tokens": 998, - "estimated_total_text_tokens": 1153806, - "deferred_resource_tokens": 523653, + "estimated_total_text_tokens": 1156374, + "deferred_resource_tokens": 525406, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153 }, { @@ -18145,7 +18190,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153 } ], @@ -18168,7 +18213,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 462350, + "estimated_tokens": 464103, "file_count": 153, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -20095,7 +20140,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:14Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -20179,7 +20224,7 @@ "daily_skillops": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, @@ -20693,7 +20738,7 @@ "weekly_curator": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", @@ -21158,7 +21203,7 @@ "adaptation_proposals": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, @@ -27591,7 +27636,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -27648,7 +27693,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, @@ -28684,7 +28729,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index bb03b04..63d4906 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -1017,8 +1017,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1036,22 +1036,26 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 }, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ] }, "runtime_conformance": { @@ -1150,7 +1154,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "skill_atlas": { "skill_count": 12, @@ -1188,7 +1192,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1320,7 +1324,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 4ee48fd..908de0b 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": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index c92fbc2..49a7c09 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: `245` -- Package SHA256: `7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111` +- Package SHA256: `c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c` ## Failures diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index e5bf5f5..0377b20 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1021,8 +1021,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1040,22 +1040,26 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 }, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ] }, "runtime_conformance": { @@ -1154,7 +1158,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "skill_atlas": { "skill_count": 12, @@ -1192,7 +1196,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1324,7 +1328,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 80fe173..373243d 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -1016,8 +1016,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "1a1f43932b87e208a18729f742be830c4c6554be2bde13d65591c525cbe51935", - "source_contract_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "evidence_bundle_sha256": "c4403c485ef4483467cef4a9a374a90a03f99f6145e71b62e57916eb918c14f1", + "source_contract_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1035,22 +1035,26 @@ "world_class_source_check_count": 19, "world_class_source_pass_count": 11, "world_class_source_blocked_count": 8, + "beta_test_ready": true, + "beta_test_blocker_count": 0, + "beta_test_deferred_evidence_count": 4, "public_claim_ready": false, "public_claim_blocker_count": 3, "working_tree_dirty": true, - "changed_file_count": 30, + "changed_file_count": 32, "source_tree_dirty": false, "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 30 + "generated_changed_file_count": 32 }, - "commit": "d845e9513c67b9572fb6c2a8754d3a0051e735ad", + "commit": "ed975a2bf25b9ab9b2fd8e62afd4ec7e7bc07789", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.", "Pending blind-review decisions are visible but do not count as human adjudication.", - "World-class readiness remains false until external and human evidence gaps close." + "World-class readiness remains false until external and human evidence gaps close.", + "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims." ] }, "runtime_conformance": { @@ -1149,7 +1153,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 245, - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" }, "skill_atlas": { "skill_count": 12, @@ -1187,7 +1191,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111", + "package_sha256": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1319,7 +1323,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] }, diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 12c834c..8adc38b 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -613,7 +613,7 @@ "label": "Evidence Consistency", "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", - "current": "38 consistency checks", + "current": "39 consistency checks", "command": "make ci-test", "test": "tests/verify_evidence_consistency.py", "evidence": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index bef747d..e857c75 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` | | Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` | | Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` | -| Evidence Consistency | `pass` | 38 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | +| Evidence Consistency | `pass` | 39 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | ## Reference Extension Tracks diff --git a/reports/skillops/daily/2026-06-17.json b/reports/skillops/daily/2026-06-17.json index 7c889a9..b332e7e 100644 --- a/reports/skillops/daily/2026-06-17.json +++ b/reports/skillops/daily/2026-06-17.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, diff --git a/reports/skillops/daily/2026-06-17.md b/reports/skillops/daily/2026-06-17.md index 5766ec2..bbe6177 100644 --- a/reports/skillops/daily/2026-06-17.md +++ b/reports/skillops/daily/2026-06-17.md @@ -1,6 +1,6 @@ # Daily SkillOps Report -Generated at: `2026-06-17T08:08:10Z` +Generated at: `2026-06-17T08:26:15Z` ## Summary diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 6a98f95..8f593d6 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17T08:08:10Z", + "generated_at": "2026-06-17T08:26:15Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index b78002f..3724122 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -1,6 +1,6 @@ # Weekly SkillOps Curator Report -Generated at: `2026-06-17T08:08:10Z` +Generated at: `2026-06-17T08:26:15Z` Week: `2026-W25` ## Summary diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 2773b6a..23bd440 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7fc324e26d614c46b350c2b3e20cb87a86f967d3a74d345bc0baf73d78d8b111" + "to": "c39574e9de8127ce31e5b3f15fd8372278319c342346753480e6ad39904e808c" } ] },