diff --git a/registry/index.json b/registry/index.json index 3105b4ea..a85b521e 100644 --- a/registry/index.json +++ b/registry/index.json @@ -1,6 +1,6 @@ { "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index e7c938db..aa01ae3c 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": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -53,5 +53,5 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" } diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 27ce6c28..8b264f19 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": "2026-06-14T07:17:33Z", + "generated_at": "2026-06-15T11:07:11Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 91b31983..206372c9 100644 --- a/reports/adoption_drift_report.md +++ b/reports/adoption_drift_report.md @@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Summary - Events: `1` -- Adoption samples: `0` -- Activation events: `0` -- Adoption rate: `0` +- Adoption samples: `1` +- Activation events: `1` +- Adoption rate: `100.0` - Missed trigger signals: `0` - Bad output signals: `0` - Script error signals: `0` @@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | -| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | +| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` +- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 194f2fca..f4b8ac9c 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "python_file_count": 162, @@ -46,6 +46,13 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "tests/verify_review_studio.py", + "lines": 745, + "kind": "test", + "severity": "pass", + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "scripts/yao_cli_parser.py", "lines": 741, @@ -60,13 +67,6 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "tests/verify_review_studio.py", - "lines": 734, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, { "path": "scripts/build_skill_atlas.py", "lines": 730, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 112d36f4..6e98a9c1 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,6 +1,6 @@ # Architecture Maintainability -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -29,9 +29,9 @@ No file-size hotspots found. | `scripts/yao.py` | `881` | `cli-script` | `pass` | | `scripts/skill_report_layout.py` | `805` | `internal-module` | `pass` | | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` | +| `tests/verify_review_studio.py` | `745` | `test` | `pass` | | `scripts/yao_cli_parser.py` | `741` | `internal-module` | `pass` | | `scripts/compile_skill.py` | `734` | `cli-script` | `pass` | -| `tests/verify_review_studio.py` | `734` | `test` | `pass` | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` | | `scripts/optimize_description.py` | `723` | `cli-script` | `pass` | | `scripts/trust_check.py` | `714` | `internal-module` | `pass` | diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index c9eac949..ac903b73 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,22 +3,35 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 38, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/install_simulation.json", + " M reports/install_simulation.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": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021", - "source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56", + "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -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": 38 }, "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": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "ready": false, + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "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": 24, "missing_count": 0, "missing_paths": [], - "sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021" + "sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7964, - "sha256": "ebef496866a9d52e5a4cef5a855a997915b820612d87c777b85e3ed1f0458efc" + "bytes": 7967, + "sha256": "712890e85fdd3334e3196b2597555491be047313728c2e2891134da71e1ca7e8" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 101852, - "sha256": "abe52fcdab2d2345783e353644acd66913995cc9048b3f3e0c758c5fca43672f" + "sha256": "3cd8c1c2d119e2db480411a9839281e0a9e1b03eb4d9d535c9b0138ef72ba6e4" }, { "label": "python_compatibility", @@ -187,7 +201,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "e97001fe6bf7553dfc3f748d67146284d5e363336954bec7991dd0d6add240cb" + "sha256": "9b8e6521f9455e654850975e3625132fb998ba4e03f7ceebaf4eded9ccd32bb5" }, { "label": "package_verification", @@ -200,15 +214,15 @@ "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8604, - "sha256": "d6972a9ab9966a8eff922b175f885b953c6300afd55bd4dc08b5baf20a518c20" + "bytes": 8758, + "sha256": "ee7554d8362d05f2bf6e7389e0524cd6336d42312ab7a05b9c0c6ddacdb0e339" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "cbce716b87a924ea08161d75851d14acb4ce76099f63ae4bc4f7bdf967f9f2fa" + "sha256": "8a7f73832d4da2f63856d7f5be02488db6eac72a3a6149aa26a39c7a15a27053" }, { "label": "world_class_evidence_plan", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index e6231c3d..658e990b 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,18 +1,18 @@ # Benchmark Reproducibility Generated at: `2026-06-15` -Commit: `5f187cdb46510a6881a8353c0c1744b90e0b05bd` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021` +Commit: `7acc6d9cf780e38570c20813186d0efea5ac8ad0` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `0a4768c86c9a` +- source contract sha256: `fe193ec81d0e` - archive sha256: `6852cf91a74d` - output cases: `5` - disclosed failure cases: `3` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd692 - 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: `38` 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: `24` / `24` -- sha256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021` +- sha256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56` ## Methodology Sections @@ -72,17 +73,17 @@ 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 | `ebef496866a9` | +| output_execution | `reports/output_execution_runs.json` | present | `712890e85fdd` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` | -| trust_report | `reports/security_trust_report.json` | present | `abe52fcdab2d` | +| trust_report | `reports/security_trust_report.json` | present | `3cd8c1c2d119` | | python_compatibility | `reports/python_compatibility.json` | present | `5be76147f3cb` | -| registry_audit | `reports/registry_audit.json` | present | `e97001fe6bf7` | +| registry_audit | `reports/registry_audit.json` | present | `9b8e6521f945` | | package_verification | `reports/package_verification.json` | present | `2476ae8ec9c4` | -| install_simulation | `reports/install_simulation.json` | present | `d6972a9ab996` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `cbce716b87a9` | +| install_simulation | `reports/install_simulation.json` | present | `ee7554d8362d` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `8a7f73832d4d` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `933cdb002181` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `5407409841eb` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `b10e1ce0a5a1` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 8eaaac92..003d71dc 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, diff --git a/reports/context_budget.json b/reports/context_budget.json index 8782df85..330fd176 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": 767, - "other_text_tokens": 1260693, + "other_text_tokens": 1265845, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1261460, - "deferred_resource_tokens": 404827, + "estimated_total_text_tokens": 1266612, + "deferred_resource_tokens": 406347, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102 }, { @@ -31,7 +31,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102 } ], @@ -54,7 +54,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102, "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 dbea78ff..1cc283d5 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 | 960 | 767 | 404827 | `governed` | scripts:357091 | 135.4 | - | ok | +| root | `.` | `production` | 1000 | 960 | 767 | 406347 | `governed` | scripts:358611 | 135.4 | - | 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 ba834f04..f969ea4b 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -1,5 +1,5 @@ { - "generated_at": "2026-06-15", + "generated_at": "2026-03-31", "targets": [ { "label": "root", @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 960, "skill_body_tokens": 767, - "deferred_resource_tokens": 404827, + "deferred_resource_tokens": 406347, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/install_simulation.json b/reports/install_simulation.json index f43960ac..ad7559a2 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,11 +1,11 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", - "package_dir": "dist", - "install_root": "dist/install-simulation/simulate-yao-meta-skill", - "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "tests/tmp_review_studio/dist", + "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", + "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, "archive_entry_count": 586, @@ -26,7 +26,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: dist/yao-meta-skill.zip" + "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -272,9 +272,9 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "dist/yao-meta-skill.zip", - "package_manifest": "dist/manifest.json", - "json": "reports/install_simulation.json", - "markdown": "reports/install_simulation.md" + "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", + "package_manifest": "tests/tmp_review_studio/dist/manifest.json", + "json": "tests/tmp_review_studio/install_simulation.json", + "markdown": "tests/tmp_review_studio/install_simulation.md" } } diff --git a/reports/install_simulation.md b/reports/install_simulation.md index 6750e007..b0d16dae 100644 --- a/reports/install_simulation.md +++ b/reports/install_simulation.md @@ -1,7 +1,7 @@ # Install Simulation - OK: `True` -- Package directory: `dist` +- Package directory: `tests/tmp_review_studio/dist` - Archive extracted: `True` - Entrypoint loaded: `True` - Manifest loaded: `True` @@ -16,7 +16,7 @@ | Check | Status | Detail | | --- | --- | --- | -| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip | +| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip | | `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries | | `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill | | `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable | diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 863b1972..281b61fe 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": 33.02, + "duration_ms": 38.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.88, + "duration_ms": 37.27, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.03, + "duration_ms": 39.96, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.76, + "duration_ms": 39.8, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.27, + "duration_ms": 37.28, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.3, + "duration_ms": 34.66, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.36, + "duration_ms": 36.08, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.3, + "duration_ms": 41.08, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.1, + "duration_ms": 34.88, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.83, + "duration_ms": 34.91, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 70166fe9..1710e76e 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 | 33.02 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 32.88 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 36.03 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 32.76 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 30.27 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.3 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.36 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.3 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.1 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.83 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 38.72 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 37.27 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 39.96 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 39.8 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 37.28 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 34.66 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 36.08 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 41.08 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.88 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.91 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 71623276..8fbd7ac4 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 1f33c7bc..7712afb1 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,6 +1,6 @@ # Python Compatibility -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 93810bdd..1795bfe7 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -58,11 +58,11 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 7a87db4d..4c42ce51 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822` +- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5` - Archive SHA256: `6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index 39d9ceff..87416019 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,12 +676,12 @@

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

Blueprint20/20

2.0 coverage; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

102 scripts scanned; secrets found

Py Compat0

165 files scanned for Python 3.11

Arch Debt0

891 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

586 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

Blueprint20/20

2.0 coverage; extensions partial 1, planned 1; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

102 scripts scanned; secrets found

Py Compat0

165 files scanned for Python 3.11

Arch Debt0

891 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

586 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 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4

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

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers

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

reports/adoption_drift_report.json 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 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4

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

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers

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

reports/adoption_drift_report.json 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

@@ -743,12 +743,12 @@
-

上下文

initial load 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4

+

上下文

initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4

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
102
网络脚本
3
Help 失败
0
包体哈希
0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822
+

信任报告

Secret
0
脚本数
102
网络脚本
3
Help 失败
0
包体哈希
fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5

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。

@@ -785,7 +785,7 @@

批准台账

Waiver Count
0
Active Count
0
Expired Count
0
Invalid Count
0
覆盖 Gate
0

批准候选

-
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .
+
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .
@@ -801,13 +801,13 @@
-

蓝图覆盖

项目数
20
模块数
8
建议 PR
12
通过数
20
Warn Count
0
缺失数
0
本地蓝图
世界级
待补证据
4
+

蓝图覆盖

项目数
20
模块数
8
建议 PR
12
通过数
20
Warn Count
0
缺失数
0
Extension Track Count
2
Extension Partial Count
1
Extension Planned Count
1
Adaptive Extension Ready
本地蓝图
世界级
待补证据
4

覆盖边界

蓝图覆盖只证明 2.0 模块、建议 PR、脚本、报告和测试在本地闭环;public world-class 仍以 world-class evidence ledger 的真人和外部证据为准。

-

公开声明

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

声明阻断

+

公开声明

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

声明阻断

diff --git a/reports/review-studio.json b/reports/review-studio.json index 312f89f9..1a7e8838 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4", + "detail": "initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -1672,12 +1672,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021", - "source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d", + "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1696,11 +1696,11 @@ "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": 34 }, - "commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "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.", @@ -1805,7 +1805,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 186, - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" }, "skill_atlas": { "skill_count": 12, @@ -1843,7 +1843,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1880,7 +1880,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" }, "failures": [], "warnings": [] @@ -1975,7 +1975,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, @@ -4342,7 +4342,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.02, + "duration_ms": 33.2, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4370,7 +4370,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.88, + "duration_ms": 32.82, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4393,7 +4393,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.03, + "duration_ms": 33.01, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4421,7 +4421,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.76, + "duration_ms": 32.83, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4444,7 +4444,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.27, + "duration_ms": 30.81, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4472,7 +4472,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.3, + "duration_ms": 35.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4495,7 +4495,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.36, + "duration_ms": 31.19, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4522,7 +4522,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.3, + "duration_ms": 29.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4545,7 +4545,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.1, + "duration_ms": 30.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4574,7 +4574,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.83, + "duration_ms": 30.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5295,22 +5295,35 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 34, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/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" + ], "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": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021", - "source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d", + "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -5329,14 +5342,15 @@ "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": 34 }, "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)", @@ -5345,10 +5359,10 @@ "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": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "ready": false, + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "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)", @@ -5356,7 +5370,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021" + "sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5429,8 +5443,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7964, - "sha256": "ebef496866a9d52e5a4cef5a855a997915b820612d87c777b85e3ed1f0458efc" + "bytes": 7966, + "sha256": "3d279da7e011bd3ed71c389195c0490f7dbb011dff90ebe99ff3db133f4a9fd6" }, { "label": "blind_review", @@ -5465,7 +5479,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 101852, - "sha256": "abe52fcdab2d2345783e353644acd66913995cc9048b3f3e0c758c5fca43672f" + "sha256": "3cd8c1c2d119e2db480411a9839281e0a9e1b03eb4d9d535c9b0138ef72ba6e4" }, { "label": "python_compatibility", @@ -5479,7 +5493,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "e97001fe6bf7553dfc3f748d67146284d5e363336954bec7991dd0d6add240cb" + "sha256": "9b8e6521f9455e654850975e3625132fb998ba4e03f7ceebaf4eded9ccd32bb5" }, { "label": "package_verification", @@ -5492,15 +5506,15 @@ "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8604, - "sha256": "d6972a9ab9966a8eff922b175f885b953c6300afd55bd4dc08b5baf20a518c20" + "bytes": 8758, + "sha256": "ee7554d8362d05f2bf6e7389e0524cd6336d42312ab7a05b9c0c6ddacdb0e339" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "cbce716b87a924ea08161d75851d14acb4ce76099f63ae4bc4f7bdf967f9f2fa" + "sha256": "8a7f73832d4da2f63856d7f5be02488db6eac72a3a6149aa26a39c7a15a27053" }, { "label": "world_class_evidence_plan", @@ -5695,6 +5709,11 @@ "pass_count": 20, "warn_count": 0, "missing_count": 0, + "extension_track_count": 2, + "extension_partial_count": 1, + "extension_planned_count": 1, + "extension_covered_count": 0, + "adaptive_extension_ready": false, "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_evidence_pending_count": 4, @@ -5705,6 +5724,10 @@ "warn": 0, "missing": 0 }, + "extension_status_counts": { + "partial": 1, + "planned": 1 + }, "modules": [ { "key": "skill-ir", @@ -6285,14 +6308,105 @@ "next_action": "Keep this item covered as the implementation evolves." } ], + "reference_extension_tracks": [ + { + "key": "skill-interpretation-report", + "label": "Skill Interpretation Report", + "status": "partial", + "objective": "User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.", + "current": "Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.", + "target": "Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.", + "evidence": [ + { + "path": "reports/skill-overview.html", + "exists": true + }, + { + "path": "reports/skill-overview.json", + "exists": true + }, + { + "path": "scripts/render_skill_overview.py", + "exists": true + }, + { + "path": "scripts/render_skill_interpretation.py", + "exists": false + }, + { + "path": "schemas/skill-interpretation.schema.json", + "exists": false + }, + { + "path": "tests/verify_skill_interpretation.py", + "exists": false + } + ], + "next_action": "Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests." + }, + { + "key": "adaptive-self-iteration", + "label": "Adaptive Self-Iteration", + "status": "planned", + "objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", + "current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + "target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", + "evidence": [ + { + "path": "references/autonomous-adaptation.md", + "exists": false + }, + { + "path": "references/user-memory-policy.md", + "exists": false + }, + { + "path": "schemas/adaptation-proposal.schema.json", + "exists": false + }, + { + "path": "scripts/summarize_user_signals.py", + "exists": false + }, + { + "path": "scripts/propose_adaptation.py", + "exists": false + }, + { + "path": "scripts/apply_adaptation.py", + "exists": false + }, + { + "path": "tests/verify_adaptation_safety.py", + "exists": false + }, + { + "path": "reports/iteration-directions.md", + "exists": true + }, + { + "path": "reports/adoption_drift_report.md", + "exists": true + } + ], + "next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path." + } + ], "next_highest_leverage": [ "Close the four world-class evidence ledger entries with accepted human or external evidence.", + "Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.", + "Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.", "Keep the blueprint coverage report in CI so 2.0 plan drift is visible." ], "source_blueprint": { "title": "Skill Overview / Skill OS 2.0 upgrade plan", "core_module_count": 8, - "recommended_pr_count": 12 + "recommended_pr_count": 12, + "reference_extension_count": 2, + "reference_extensions": [ + "Skill interpretation report", + "Adaptive self-iteration with local preference memory and approval gates" + ] }, "artifacts": { "json": "reports/skill_os2_coverage.json", @@ -10776,7 +10890,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -10816,7 +10930,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -10913,7 +11027,7 @@ { "target": "claude", "status": "pass", - "adapter": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -10995,7 +11109,7 @@ { "target": "generic", "status": "pass", - "adapter": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11077,7 +11191,7 @@ { "target": "vscode", "status": "pass", - "adapter": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11188,7 +11302,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 186, - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" }, "failures": [], "warnings": [], @@ -14796,6 +14910,13 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "tests/verify_review_studio.py", + "lines": 745, + "kind": "test", + "severity": "pass", + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "scripts/yao_cli_parser.py", "lines": 741, @@ -14810,13 +14931,6 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "tests/verify_review_studio.py", - "lines": 734, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, { "path": "scripts/build_skill_atlas.py", "lines": 730, @@ -14868,15 +14982,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1260693, + "other_text_tokens": 1265424, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1261460, - "deferred_resource_tokens": 404827, + "estimated_total_text_tokens": 1266191, + "deferred_resource_tokens": 406347, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102 }, { @@ -14893,7 +15007,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102 } ], @@ -14916,7 +15030,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 357091, + "estimated_tokens": 358611, "file_count": 102, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -15767,7 +15881,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -15952,8 +16066,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, @@ -16616,7 +16730,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 76, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" @@ -16784,7 +16898,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-14T07:17:33Z", + "generated_at": "2026-06-15T11:05:04Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -16869,7 +16983,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-15", "summary": { "waiver_count": 0, "active_count": 0, @@ -16919,7 +17033,7 @@ "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 2027-06-14 --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 2027-06-15 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -19020,7 +19134,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -19057,11 +19171,11 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -19077,7 +19191,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, @@ -19759,11 +19873,11 @@ "install_simulation": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", - "package_dir": "dist", - "install_root": "dist/install-simulation/simulate-yao-meta-skill", - "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "tests/tmp_review_studio/dist", + "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", + "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, "archive_entry_count": 586, @@ -19784,7 +19898,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: dist/yao-meta-skill.zip" + "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -20030,16 +20144,16 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "dist/yao-meta-skill.zip", - "package_manifest": "dist/manifest.json", - "json": "reports/install_simulation.json", - "markdown": "reports/install_simulation.md" + "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", + "package_manifest": "tests/tmp_review_studio/dist/manifest.json", + "json": "tests/tmp_review_studio/install_simulation.json", + "markdown": "tests/tmp_review_studio/install_simulation.md" } }, "upgrade_check": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -20113,7 +20227,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, @@ -20128,8 +20242,8 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "reports/upgrade_check.json", - "markdown": "reports/upgrade_check.md" + "json": "tests/tmp_review_studio/upgrade_check.json", + "markdown": "tests/tmp_review_studio/upgrade_check.md" } }, "manifest": { diff --git a/reports/review-viewer.json b/reports/review-viewer.json index b39ced78..e07f66ed 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -995,12 +995,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021", - "source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56", + "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1019,11 +1019,11 @@ "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": 38 }, - "commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "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.", @@ -1128,7 +1128,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 186, - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" }, "skill_atlas": { "skill_count": 12, @@ -1166,7 +1166,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1203,7 +1203,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" }, "failures": [], "warnings": [] @@ -1298,7 +1298,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 76fadc1f..66f2b1d9 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 95c9fdf9..07eeccbc 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -52,7 +52,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-14 --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 a689bcee..dbc942d1 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -35,7 +35,7 @@ - waiver allowed: `true` - risk: review pending 5; model-executed 0; output failures 0 - evidence: `reports/output_review_adjudication.md` -- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json index 9c2ffd6e..59c9a1a4 100644 --- a/reports/runtime_permission_probes.json +++ b/reports/runtime_permission_probes.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -42,7 +42,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -139,7 +139,7 @@ { "target": "claude", "status": "pass", - "adapter": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -221,7 +221,7 @@ { "target": "generic", "status": "pass", - "adapter": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -303,7 +303,7 @@ { "target": "vscode", "status": "pass", - "adapter": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 02d62be9..9097799c 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": 186, - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 1b2f46b1..bab77b4f 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: `186` -- Package SHA256: `0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822` +- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5` ## Failures diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 837e4663..de418ac2 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -994,12 +994,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021", - "source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56", + "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1018,11 +1018,11 @@ "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": 38 }, - "commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd", + "commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0", "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.", @@ -1127,7 +1127,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 186, - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" }, "skill_atlas": { "skill_count": 12, @@ -1165,7 +1165,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822", + "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1202,7 +1202,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-15" + "generated_at": "2026-06-13" }, "failures": [], "warnings": [] @@ -1297,7 +1297,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index f83ef511..ab1c3de2 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -44,7 +44,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -229,8 +229,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, @@ -893,7 +893,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 76, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index cf078de0..49a4d428 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": "2026-06-15", + "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 8d4479c2..a5cb9801 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Audit -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -30,7 +30,7 @@ Generated at: `2026-06-15` | Registry Distribution | pass | zip entries 586; 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 80b62432..92ec7443 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": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 20, @@ -10,6 +10,11 @@ "pass_count": 20, "warn_count": 0, "missing_count": 0, + "extension_track_count": 2, + "extension_partial_count": 1, + "extension_planned_count": 1, + "extension_covered_count": 0, + "adaptive_extension_ready": false, "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_evidence_pending_count": 4, @@ -20,6 +25,10 @@ "warn": 0, "missing": 0 }, + "extension_status_counts": { + "partial": 1, + "planned": 1 + }, "modules": [ { "key": "skill-ir", @@ -600,14 +609,105 @@ "next_action": "Keep this item covered as the implementation evolves." } ], + "reference_extension_tracks": [ + { + "key": "skill-interpretation-report", + "label": "Skill Interpretation Report", + "status": "partial", + "objective": "User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.", + "current": "Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.", + "target": "Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.", + "evidence": [ + { + "path": "reports/skill-overview.html", + "exists": true + }, + { + "path": "reports/skill-overview.json", + "exists": true + }, + { + "path": "scripts/render_skill_overview.py", + "exists": true + }, + { + "path": "scripts/render_skill_interpretation.py", + "exists": false + }, + { + "path": "schemas/skill-interpretation.schema.json", + "exists": false + }, + { + "path": "tests/verify_skill_interpretation.py", + "exists": false + } + ], + "next_action": "Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests." + }, + { + "key": "adaptive-self-iteration", + "label": "Adaptive Self-Iteration", + "status": "planned", + "objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", + "current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + "target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", + "evidence": [ + { + "path": "references/autonomous-adaptation.md", + "exists": false + }, + { + "path": "references/user-memory-policy.md", + "exists": false + }, + { + "path": "schemas/adaptation-proposal.schema.json", + "exists": false + }, + { + "path": "scripts/summarize_user_signals.py", + "exists": false + }, + { + "path": "scripts/propose_adaptation.py", + "exists": false + }, + { + "path": "scripts/apply_adaptation.py", + "exists": false + }, + { + "path": "tests/verify_adaptation_safety.py", + "exists": false + }, + { + "path": "reports/iteration-directions.md", + "exists": true + }, + { + "path": "reports/adoption_drift_report.md", + "exists": true + } + ], + "next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path." + } + ], "next_highest_leverage": [ "Close the four world-class evidence ledger entries with accepted human or external evidence.", + "Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.", + "Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.", "Keep the blueprint coverage report in CI so 2.0 plan drift is visible." ], "source_blueprint": { "title": "Skill Overview / Skill OS 2.0 upgrade plan", "core_module_count": 8, - "recommended_pr_count": 12 + "recommended_pr_count": 12, + "reference_extension_count": 2, + "reference_extensions": [ + "Skill interpretation report", + "Adaptive self-iteration with local preference memory and approval gates" + ] }, "artifacts": { "json": "reports/skill_os2_coverage.json", diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 1bc7ccab..d2266d5d 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: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -10,6 +10,10 @@ Generated at: `2026-06-15` - pass: `20` / `20` - missing: `0` - warn: `0` +- reference extensions: `2` +- extension partial: `1` +- extension planned: `1` +- adaptive extension ready: `false` - world-class evidence pending: `4` This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, commands, and tests. It does not count pending human review, provider runs, metadata fallbacks, or planned work as public world-class evidence. @@ -44,9 +48,20 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | 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` | +## Reference Extension Tracks + +| Track | Status | Current | Target | Next action | +| --- | --- | --- | --- | --- | +| Skill Interpretation Report | `partial` | Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet. | Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests. | Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests. | +| Adaptive Self-Iteration | `planned` | The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy. | Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan. | Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. | + +These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution. + ## Next Highest-Leverage Moves - Close the four world-class evidence ledger entries with accepted human or external evidence. +- Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer. +- Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default. - Keep the blueprint coverage report in CI so 2.0 plan drift is visible. ## Evidence Detail @@ -190,3 +205,19 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, - status: `pass` - existing evidence: `docs/migration-v2.md`, `reports/skill-os-2-review.md`, `README.md` - next action: Keep this item covered as the implementation evolves. + +### Skill Interpretation Report + +- objective: User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations. +- status: `partial` +- existing evidence: `reports/skill-overview.html`, `reports/skill-overview.json`, `scripts/render_skill_overview.py` +- missing evidence: `scripts/render_skill_interpretation.py`, `schemas/skill-interpretation.schema.json`, `tests/verify_skill_interpretation.py` +- next action: Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests. + +### Adaptive Self-Iteration + +- objective: Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback. +- status: `planned` +- existing evidence: `reports/iteration-directions.md`, `reports/adoption_drift_report.md` +- missing evidence: `references/autonomous-adaptation.md`, `references/user-memory-policy.md`, `schemas/adaptation-proposal.schema.json`, `scripts/summarize_user_signals.py`, `scripts/propose_adaptation.py`, `scripts/apply_adaptation.py`, `tests/verify_adaptation_safety.py` +- next action: Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 3ec35815..c2afb6d4 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822" + "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" } ] }, @@ -90,7 +90,7 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "reports/upgrade_check.json", - "markdown": "reports/upgrade_check.md" + "json": "tests/tmp_review_studio/upgrade_check.json", + "markdown": "tests/tmp_review_studio/upgrade_check.md" } } diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index 29e36b21..edf4d040 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": "2026-06-15", + "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 8c4bc49c..3318385b 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: `2026-06-15` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index c773fa5d..ed002e84 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -307,7 +307,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index bc5fd179..62c2d7ed 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -1,6 +1,6 @@ # World-Class Evidence Intake -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index e245338f..6637eb6e 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": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_entry_count": 4, @@ -14,8 +14,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 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, @@ -351,7 +351,7 @@ "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:///", @@ -388,7 +388,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -409,8 +409,8 @@ "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." }, @@ -426,8 +426,8 @@ } ], "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 1bc98d0c..8ec440ff 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -1,6 +1,6 @@ # World-Class Evidence Ledger -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -8,8 +8,8 @@ Generated at: `2026-06-15` - ready to claim world-class: `false` - entries: `4` - source accepted: `0` -- source checks: `6` pass / `13` total -- source blocked: `7` +- source checks: `7` pass / `13` total +- source blocked: `6` - accepted: `0` - pending: `4` - human pending: `1` @@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. | | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. | | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. | +| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. | ## Provider Holdout @@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` -- source checks: `1` pass / `3` total +- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` +- source checks: `2` pass / `3` total - submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}` ### Provenance Requirements @@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source | Check | Current | Expected | Status | | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | -| Adoption sample | `0` | `>0` | `blocked` | +| Adoption sample | `1` | `>0` | `pass` | | Raw content blocked | `False` | `false` | `pass` | ### Completion Assertions diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index 20b0d4e5..236c40fe 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", @@ -141,7 +141,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -299,7 +299,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index 6af4cf3c..c0db846d 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -1,6 +1,6 @@ # World-Class Evidence Plan -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 | | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 | | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | ## Provider Holdout diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index be9f2679..e239453a 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

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

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

Fast Path

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

Evidence Items

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

Source Runbook

  • python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  • Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -130,8 +130,8 @@

Success Checks

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

Privacy

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

Next Source Actions

-

Source Evidence Snapshot

+

Next Source Actions

+

Source Evidence Snapshot

Boundary

diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index dfb90499..eb0e1857 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -12,8 +12,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -394,7 +394,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "execution_runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -442,7 +442,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -463,8 +463,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -479,10 +479,9 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 2, + "blocked_source_check_count": 1, "next_source_actions": [ - "Import at least one metadata-only event from a real client.", - "Telemetry must include adoption outcome evidence." + "Import at least one metadata-only event from a real client." ], "submission_state": { "status": "missing", diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index 3abb08c3..bef6278b 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -1,6 +1,6 @@ # World-Class Operator Runbook -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials | | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer | | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator | -| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | +| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | ## Provider Holdout @@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission - objective: Import production metadata-only events from a real external client into the local drift loop. - blocking reason: No evidence packet has been submitted for review. -- blocked source checks: `2` +- blocked source checks: `1` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -292,14 +292,13 @@ This runbook coordinates evidence collection only. It does not accept submission ### Next Source Actions - Import at least one metadata-only event from a real client. -- Telemetry must include adoption outcome evidence. ### Source Evidence Snapshot | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 5b79d650..cb10f86b 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": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "review_item_count": 4, @@ -13,8 +13,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 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" @@ -265,7 +265,7 @@ "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 @@ -286,8 +286,8 @@ "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." }, @@ -303,8 +303,8 @@ } ], "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 a896c218..7fe1e470 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -1,6 +1,6 @@ # World-Class Submission Review -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w #### Source Checks - External events: 0 / >0 => blocked -- Adoption sample: 0 / >0 => blocked +- Adoption sample: 1 / >0 => pass - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/scripts/render_review_studio.py b/scripts/render_review_studio.py index bbeb46c9..2914de88 100644 --- a/scripts/render_review_studio.py +++ b/scripts/render_review_studio.py @@ -247,6 +247,10 @@ def render_html(report: dict[str, Any]) -> str: "pass_count", "warn_count", "missing_count", + "extension_track_count", + "extension_partial_count", + "extension_planned_count", + "adaptive_extension_ready", "local_blueprint_ready", "public_world_class_ready", "world_class_evidence_pending_count", diff --git a/scripts/render_skill_os2_coverage.py b/scripts/render_skill_os2_coverage.py index 0786edd0..400d1fbb 100644 --- a/scripts/render_skill_os2_coverage.py +++ b/scripts/render_skill_os2_coverage.py @@ -86,6 +86,30 @@ def build_item( } +def build_extension_track( + *, + key: str, + label: str, + status: str, + objective: str, + current: str, + target: str, + artifact_paths: list[str], + next_action: str, + skill_dir: Path, +) -> dict[str, Any]: + return { + "key": key, + "label": label, + "status": status, + "objective": objective, + "current": current, + "target": target, + "evidence": evidence(skill_dir, artifact_paths), + "next_action": next_action, + } + + def summary_value(payload: dict[str, Any], key: str, default: Any = 0) -> Any: summary = payload.get("summary", {}) return summary.get(key, default) if isinstance(summary, dict) else default @@ -273,6 +297,51 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]: for key, path_a, path_b, path_c, condition, current in recommended_prs ] + extension_tracks = [ + build_extension_track( + key="skill-interpretation-report", + label="Skill Interpretation Report", + status="partial", + objective="User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.", + current="Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.", + target="Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.", + artifact_paths=[ + "reports/skill-overview.html", + "reports/skill-overview.json", + "scripts/render_skill_overview.py", + "scripts/render_skill_interpretation.py", + "schemas/skill-interpretation.schema.json", + "tests/verify_skill_interpretation.py", + ], + next_action="Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests.", + skill_dir=skill_dir, + ), + build_extension_track( + key="adaptive-self-iteration", + label="Adaptive Self-Iteration", + status="planned", + objective="Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", + current="The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + target="Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", + artifact_paths=[ + "references/autonomous-adaptation.md", + "references/user-memory-policy.md", + "schemas/adaptation-proposal.schema.json", + "scripts/summarize_user_signals.py", + "scripts/propose_adaptation.py", + "scripts/apply_adaptation.py", + "tests/verify_adaptation_safety.py", + "reports/iteration-directions.md", + "reports/adoption_drift_report.md", + ], + next_action="Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path.", + skill_dir=skill_dir, + ), + ] + extension_counts: dict[str, int] = {} + for item in extension_tracks: + extension_counts[item["status"]] = extension_counts.get(item["status"], 0) + 1 + items = modules + pr_items counts: dict[str, int] = {"pass": 0, "warn": 0, "missing": 0} for item in items: @@ -287,6 +356,11 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]: "pass_count": counts.get("pass", 0), "warn_count": counts.get("warn", 0), "missing_count": counts.get("missing", 0), + "extension_track_count": len(extension_tracks), + "extension_partial_count": extension_counts.get("partial", 0), + "extension_planned_count": extension_counts.get("planned", 0), + "extension_covered_count": extension_counts.get("covered", 0), + "adaptive_extension_ready": extension_counts.get("planned", 0) == 0, "local_blueprint_ready": local_ready, "public_world_class_ready": public_ready, "world_class_evidence_pending_count": pending_world_class, @@ -299,16 +373,25 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]: "skill_dir": rel_path(skill_dir, ROOT), "summary": summary, "status_counts": counts, + "extension_status_counts": extension_counts, "modules": modules, "recommended_prs": pr_items, + "reference_extension_tracks": extension_tracks, "next_highest_leverage": [ "Close the four world-class evidence ledger entries with accepted human or external evidence.", + "Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.", + "Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.", "Keep the blueprint coverage report in CI so 2.0 plan drift is visible.", ], "source_blueprint": { "title": "Skill Overview / Skill OS 2.0 upgrade plan", "core_module_count": 8, "recommended_pr_count": 12, + "reference_extension_count": len(extension_tracks), + "reference_extensions": [ + "Skill interpretation report", + "Adaptive self-iteration with local preference memory and approval gates", + ], }, "artifacts": { "json": "reports/skill_os2_coverage.json", @@ -351,6 +434,10 @@ def render_markdown(report: dict[str, Any]) -> str: f"- pass: `{summary['pass_count']}` / `{summary['item_count']}`", f"- missing: `{summary['missing_count']}`", f"- warn: `{summary['warn_count']}`", + f"- reference extensions: `{summary['extension_track_count']}`", + f"- extension partial: `{summary['extension_partial_count']}`", + f"- extension planned: `{summary['extension_planned_count']}`", + f"- adaptive extension ready: `{str(summary['adaptive_extension_ready']).lower()}`", f"- world-class evidence pending: `{summary['world_class_evidence_pending_count']}`", "", "This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, commands, and tests. It does not count pending human review, provider runs, metadata fallbacks, or planned work as public world-class evidence.", @@ -363,12 +450,37 @@ def render_markdown(report: dict[str, Any]) -> str: "", *render_table(report["recommended_prs"]), "", + "## Reference Extension Tracks", + "", + "| Track | Status | Current | Target | Next action |", + "| --- | --- | --- | --- | --- |", + ] + for item in report["reference_extension_tracks"]: + lines.append( + "| " + + " | ".join( + [ + item["label"].replace("|", "\\|"), + f"`{item['status']}`", + item["current"].replace("|", "\\|"), + item["target"].replace("|", "\\|"), + item["next_action"].replace("|", "\\|"), + ] + ) + + " |" + ) + lines.extend( + [ + "", + "These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution.", + "", "## Next Highest-Leverage Moves", "", - ] + ] + ) lines.extend(f"- {item}" for item in report["next_highest_leverage"]) lines.extend(["", "## Evidence Detail", ""]) - for item in report["modules"] + report["recommended_prs"]: + for item in report["modules"] + report["recommended_prs"] + report["reference_extension_tracks"]: existing = [entry["path"] for entry in item["evidence"] if entry["exists"]] missing = [entry["path"] for entry in item["evidence"] if not entry["exists"]] lines.append(f"### {item['label']}") diff --git a/scripts/review_studio_data.py b/scripts/review_studio_data.py index 9a677242..581b602c 100644 --- a/scripts/review_studio_data.py +++ b/scripts/review_studio_data.py @@ -147,6 +147,8 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]: output_review = data["output_review_adjudication"].get("summary", {}) benchmark = data["benchmark_reproducibility"].get("summary", {}) blueprint = data["skill_os2_coverage"].get("summary", {}) + extension_partial = int(blueprint.get("extension_partial_count", 0) or 0) + extension_planned = int(blueprint.get("extension_planned_count", 0) or 0) compiled = data["compiled_targets"].get("summary", {}) conformance = data["conformance"].get("summary", {}) runtime_permissions = data["runtime_permissions"].get("summary", {}) @@ -211,7 +213,10 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]: { "label": "Blueprint", "value": f"{blueprint.get('pass_count', 0)}/{blueprint.get('item_count', 0)}", - "detail": f"2.0 coverage; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}", + "detail": ( + f"2.0 coverage; extensions partial {extension_partial}, " + f"planned {extension_planned}; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}" + ), }, { "label": "Runtime", diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 06c43937..50d09246 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -1,6 +1,6 @@ { "workspace_root": ".", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -185,8 +185,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json index 6d864a41..6602e829 100644 --- a/skill_atlas/stale_skills.json +++ b/skill_atlas/stale_skills.json @@ -24,7 +24,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 76, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py index d8a7a505..a7f0a442 100644 --- a/tests/verify_review_studio.py +++ b/tests/verify_review_studio.py @@ -537,6 +537,14 @@ def main() -> None: if full_payload["data"]["skill_os2_coverage"]: assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_track_count"] == 2, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_planned_count"] == 1, full_payload["data"]["skill_os2_coverage"] + extension_tracks = { + item["key"]: item + for item in full_payload["data"]["skill_os2_coverage"]["reference_extension_tracks"] + } + assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks + assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks world_class_entries = full_payload["data"]["world_class_evidence_ledger"]["entries"] assert len(world_class_entries) == 4, world_class_entries assert {item["key"] for item in world_class_entries} == { @@ -644,6 +652,9 @@ def main() -> None: assert "model_executed_count: 0 / >0" in html, html assert "Token usage observed" in html, html assert "蓝图覆盖" in html, html + assert "Extension Track Count" in html, html + assert "Adaptive Extension Ready" in html, html + assert "extensions partial 1, planned 1" in html, html assert "本地蓝图" in html, html assert "public world-class 仍以 world-class evidence ledger" in html, html assert "公开声明" in html, html diff --git a/tests/verify_skill_os2_coverage.py b/tests/verify_skill_os2_coverage.py index 55c9c57d..14883c28 100644 --- a/tests/verify_skill_os2_coverage.py +++ b/tests/verify_skill_os2_coverage.py @@ -44,6 +44,10 @@ def main() -> None: assert summary["pass_count"] == 20, summary assert summary["warn_count"] == 0, summary assert summary["missing_count"] == 0, summary + assert summary["extension_track_count"] == 2, summary + assert summary["extension_partial_count"] == 1, summary + assert summary["extension_planned_count"] == 1, summary + assert summary["adaptive_extension_ready"] is False, summary assert summary["local_blueprint_ready"] is True, summary assert summary["public_world_class_ready"] is False, summary assert summary["world_class_evidence_pending_count"] == 4, summary @@ -81,13 +85,30 @@ def main() -> None: assert any(entry["path"] == "reports/benchmark_reproducibility.json" and entry["exists"] for entry in prs["benchmark-methodology"]["evidence"]) assert payload["source_blueprint"]["core_module_count"] == 8, payload assert payload["source_blueprint"]["recommended_pr_count"] == 12, payload + assert payload["source_blueprint"]["reference_extension_count"] == 2, payload + extension_tracks = {item["key"]: item for item in payload["reference_extension_tracks"]} + assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks + assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks + assert any( + entry["path"] == "reports/skill-overview.html" and entry["exists"] + for entry in extension_tracks["skill-interpretation-report"]["evidence"] + ), extension_tracks["skill-interpretation-report"] + assert any( + entry["path"] == "scripts/summarize_user_signals.py" and not entry["exists"] + for entry in extension_tracks["adaptive-self-iteration"]["evidence"] + ), extension_tracks["adaptive-self-iteration"] assert "Close the four world-class evidence ledger entries" in payload["next_highest_leverage"][0], payload + assert "adaptive self-iteration" in " ".join(payload["next_highest_leverage"]), payload markdown = output_md.read_text(encoding="utf-8") assert "Skill OS 2.0 Blueprint Coverage" in markdown, markdown assert "local blueprint ready: `true`" in markdown, markdown assert "public world-class ready: `false`" in markdown, markdown assert "## Core Modules" in markdown, markdown assert "## Recommended PR Coverage" in markdown, markdown + assert "## Reference Extension Tracks" in markdown, markdown + assert "Skill Interpretation Report" in markdown, markdown + assert "Adaptive Self-Iteration" in markdown, markdown + assert "user-supplied 2.0 reference plan" in markdown, markdown assert "`agent-skills-conformance`" not in markdown, markdown assert "Agent Skills Conformance" in markdown, markdown print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))