diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json index fe972dec..594c30d5 100644 --- a/reports/adaptation_proposals.json +++ b/reports/adaptation_proposals.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-17", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md index 51376659..974c14dc 100644 --- a/reports/adaptation_proposals.md +++ b/reports/adaptation_proposals.md @@ -1,6 +1,6 @@ # Adaptation Proposals -- Generated at: `2026-06-16T16:14:10Z` +- Generated at: `2026-06-17` - Pattern report: `reports/user_patterns.json` - Proposal only: `true` - Writes repository files: `false` diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index ffa10b94..cc4b39cf 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": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-16T16:15:39Z", "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 2fdf79fa..f9d05869 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "python_file_count": 215, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index acade6a2..421450a2 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,6 +1,6 @@ # Architecture Maintainability -Generated at: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 74e93d92..622e59c7 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,24 +3,24 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "git_status": { "available": true, "dirty": true, - "changed_file_count": 30, + "changed_file_count": 18, "sample": [ " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", - " M reports/adoption_drift_report.json", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/context_budget.md", " M reports/context_budget_summary.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md" + " M reports/evidence_consistency.json", + " M reports/python_compatibility.json", + " M reports/python_compatibility.md", + " M reports/review-studio.html", + " M reports/review-studio.json", + " M reports/review-viewer.json" ], "scope": "generation-time status before this report is written" }, @@ -30,7 +30,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -52,7 +52,7 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, "public_claim": { "ready": false, @@ -68,7 +68,7 @@ }, "release_lock": { "ready": false, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "status_scope": "generation-time status before this report is written", "reason": "working tree was dirty at generation time" }, @@ -78,7 +78,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c" + "sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -194,7 +194,7 @@ "path": "reports/python_compatibility.json", "exists": true, "bytes": 28298, - "sha256": "8b48340618cc702a8d8f5aaf6ce6d05a1a5463a8008d06a28809671632b212da" + "sha256": "b223212ec521b782c479ace75a0e93866e09aff7f2637fdd181e8906bb4b0376" }, { "label": "registry_audit", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index c9a0240a..5e34bb14 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `500f8cc34ef5ff9a3c8125a72509faabbe95ac9a` +Commit: `3961b60341a893464c1ea96f9921f804809f37f9` Working tree dirty at generation: `true` -Evidence bundle SHA256: `c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c` +Evidence bundle SHA256: `678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77` ## Summary @@ -23,7 +23,7 @@ Evidence bundle SHA256: `c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c2 - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` - public claim blockers: `5` -- changed files at generation: `30` +- changed files at generation: `18` 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. @@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c` +- sha256: `678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77` ## Methodology Sections @@ -79,7 +79,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | | trust_report | `reports/security_trust_report.json` | present | `0d60cae96105` | -| python_compatibility | `reports/python_compatibility.json` | present | `8b48340618cc` | +| python_compatibility | `reports/python_compatibility.json` | present | `b223212ec521` | | registry_audit | `reports/registry_audit.json` | present | `e75a341d15e4` | | package_verification | `reports/package_verification.json` | present | `a27941fdb865` | | install_simulation | `reports/install_simulation.json` | present | `e29ae26bc97c` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 7f67b42d..78d28a9b 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, diff --git a/reports/context_budget.json b/reports/context_budget.json index 951489c3..8b2a36ec 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,9 +6,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1076748, + "other_text_tokens": 1076786, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1077545, + "estimated_total_text_tokens": 1077583, "deferred_resource_tokens": 495216, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 03a62aa7..f26e9312 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -1,5 +1,5 @@ { - "generated_at": "2026-06-17", + "generated_at": "2026-03-31", "targets": [ { "label": "root", diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 2dccc8b4..7dac20a0 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": false, - "actual": false, + "expected": true, + "actual": true, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", - "actual": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "expected": "3961b60341a893464c1ea96f9921f804809f37f9", + "actual": "3961b60341a893464c1ea96f9921f804809f37f9", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,7 +261,7 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", @@ -271,10 +271,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", @@ -284,7 +284,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", - "actual": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "expected": "3961b60341a893464c1ea96f9921f804809f37f9", + "actual": "3961b60341a893464c1ea96f9921f804809f37f9", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,7 +407,7 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", @@ -417,10 +417,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", @@ -430,7 +430,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", diff --git a/reports/install_simulation.json b/reports/install_simulation.json index 0b08c03f..b80aaab5 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,14 +1,14 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skill_dir": ".", - "package_dir": "dist", - "install_root": "dist/install-simulation/simulate-yao-meta-skill", - "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "tests/tmp_review_studio/dist", + "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", + "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 658, + "archive_entry_count": 677, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -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 154db789..ff45db38 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": 25.96, + "duration_ms": 26.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.2, + "duration_ms": 28.28, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.36, + "duration_ms": 29.37, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.09, + "duration_ms": 29.8, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.43, + "duration_ms": 29.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.16, + "duration_ms": 28.55, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.55, + "duration_ms": 26.89, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.86, + "duration_ms": 26.9, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.87, + "duration_ms": 26.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.17, + "duration_ms": 26.51, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index c27422ae..8cb1af25 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 | 25.96 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 26.2 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 26.36 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.09 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 26.43 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.16 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.55 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.86 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.87 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.17 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 26.12 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 28.28 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 29.37 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.8 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 29.59 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.55 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.89 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.9 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.03 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.51 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 1c479960..207c59b9 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 03a8bf61..1289f5d7 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,6 +1,6 @@ # Python Compatibility -Generated at: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/reports/registry_audit.json b/reports/registry_audit.json index ac844f70..8385d17a 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad", + "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -58,11 +58,11 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-16" + "generated_at": "2026-06-13" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad" + "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index e14f045b..5783d3ed 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad` +- Package SHA256: `d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69` - Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index 172d9f42..42dfb23a 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

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

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 140 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

215 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

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

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

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

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

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

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

意图画布

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

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 140 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

215 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

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

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

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

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

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

@@ -842,14 +842,14 @@
-

运营回路

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

+

运营回路

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

漂移信号

事件数
1
采用率
0
漏触发
0
Bad Output Count
0
风险带
low
-

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
否
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
-

周度队列

决策
curator-review
Week Id
2026-W25
日报数
2
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
否
Writes Source Files
否
Auto Patch Enabled
否
+

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
是
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
+

周度队列

决策
curator-review
Week Id
2026-W25
日报数
2
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
是
Writes Source Files
否
Auto Patch Enabled
否
diff --git a/reports/review-studio.json b/reports/review-studio.json index 48d6391f..ad952ca1 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -108,7 +108,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly", "link": "adoption_drift_report.md" }, @@ -1972,7 +1972,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -1994,9 +1994,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "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.", @@ -5659,24 +5659,24 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "git_status": { "available": true, "dirty": true, - "changed_file_count": 30, + "changed_file_count": 18, "sample": [ " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", - " M reports/adoption_drift_report.json", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/context_budget.json", - " M reports/context_budget.md", " M reports/context_budget_summary.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md" + " M reports/evidence_consistency.json", + " M reports/python_compatibility.json", + " M reports/python_compatibility.md", + " M reports/review-studio.html", + " M reports/review-studio.json", + " M reports/review-viewer.json" ], "scope": "generation-time status before this report is written" }, @@ -5686,7 +5686,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -5708,7 +5708,7 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, "public_claim": { "ready": false, @@ -5724,7 +5724,7 @@ }, "release_lock": { "ready": false, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "status_scope": "generation-time status before this report is written", "reason": "working tree was dirty at generation time" }, @@ -5734,7 +5734,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c" + "sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5850,7 +5850,7 @@ "path": "reports/python_compatibility.json", "exists": true, "bytes": 28298, - "sha256": "8b48340618cc702a8d8f5aaf6ce6d05a1a5463a8008d06a28809671632b212da" + "sha256": "b223212ec521b782c479ace75a0e93866e09aff7f2637fdd181e8906bb4b0376" }, { "label": "registry_audit", @@ -15408,7 +15408,7 @@ "python_compatibility": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", @@ -16869,9 +16869,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1076748, + "other_text_tokens": 1076737, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1077545, + "estimated_total_text_tokens": 1077534, "deferred_resource_tokens": 495216, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ @@ -18922,7 +18922,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18939,7 +18939,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -19388,7 +19388,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true }, "actions": [ @@ -19423,7 +19423,7 @@ "weekly_curator": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", @@ -19437,7 +19437,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19457,7 +19457,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19710,7 +19710,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -19888,7 +19888,7 @@ "adaptation_proposals": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-17", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 2e026fc7..9ea2cdd3 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -1001,7 +1001,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -1023,9 +1023,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "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.", 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 1ec9a128..a994e852 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": "2026-06-17", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -92,7 +92,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --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 90ddd5bd..df7cc049 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -38,7 +38,7 @@ - waiver allowed: `true` - risk: review pending 5; model-executed 0; output failures 0 - evidence: `reports/output_review_adjudication.md` -- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json index 9c2ffd6e..59c9a1a4 100644 --- a/reports/runtime_permission_probes.json +++ b/reports/runtime_permission_probes.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -42,7 +42,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -139,7 +139,7 @@ { "target": "claude", "status": "pass", - "adapter": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -221,7 +221,7 @@ { "target": "generic", "status": "pass", - "adapter": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -303,7 +303,7 @@ { "target": "vscode", "status": "pass", - "adapter": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index bf842b96..158ad245 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1005,7 +1005,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -1027,9 +1027,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "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.", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 929a4e46..375ea301 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -1000,7 +1000,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c", + "evidence_bundle_sha256": "678c3839e1d41692b4fb991e542e7d6ef60fbca5248dab2e3f313e138aedde77", "source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, @@ -1022,9 +1022,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 18 }, - "commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a", + "commit": "3961b60341a893464c1ea96f9921f804809f37f9", "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.", diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index 0ac9d8aa..b6329407 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -44,7 +44,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -64,6 +64,8 @@ "vscode" ], "resources": [ + "scripts/adaptation_patch_safety.py", + "scripts/adaptation_report_contracts.py", "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", "scripts/build_confusion_matrix.py", @@ -96,6 +98,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/output_review_privacy.py", "scripts/prepare_output_review_kit.py", "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", @@ -148,6 +151,7 @@ "scripts/review_studio_actions.py", "scripts/review_studio_data.py", "scripts/review_studio_formatting.py", + "scripts/review_studio_gate_contract.py", "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", @@ -175,11 +179,16 @@ "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", "scripts/trust_check.py", + "scripts/trust_check_scripts.py", "scripts/upgrade_check.py", "scripts/validate_skill.py", "scripts/verify_package.py", "scripts/world_class_evidence_contract.py", + "scripts/world_class_human_evidence.py", + "scripts/world_class_native_permission_evidence.py", + "scripts/world_class_native_telemetry_evidence.py", "scripts/world_class_preflight_layout.py", + "scripts/world_class_provider_evidence.py", "scripts/world_class_source_checks.py", "scripts/world_class_submission_kit_rendering.py", "scripts/world_class_submission_matrix.py", @@ -264,8 +273,8 @@ "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 } }, @@ -928,7 +937,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 77, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 6d1055e3..d9dd5461 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": "2026-06-17", + "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 215d2269..74eb8e26 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Audit -Generated at: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -30,7 +30,7 @@ Generated at: `2026-06-17` | Registry Distribution | pass | zip entries 658; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | | 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 24bc4cee..e598eec9 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": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 21, diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index fd915be0..83966a1b 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/reports/skillops/daily/2026-06-17.json b/reports/skillops/daily/2026-06-17.json index 7ee010c4..07080fcd 100644 --- a/reports/skillops/daily/2026-06-17.json +++ b/reports/skillops/daily/2026-06-17.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-17.md b/reports/skillops/daily/2026-06-17.md index 5d6c937a..65caad51 100644 --- a/reports/skillops/daily/2026-06-17.md +++ b/reports/skillops/daily/2026-06-17.md @@ -14,7 +14,7 @@ Generated at: `2026-06-17` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `false` +- release lock ready: `true` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index ef438131..8f21344c 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -288,7 +288,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index 6bcefe10..a52113b7 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -1,6 +1,6 @@ # Weekly SkillOps Curator Report -Generated at: `2026-06-16T16:14:10Z` +Generated at: `2026-06-17` Week: `2026-W25` ## Summary @@ -13,7 +13,7 @@ Week: `2026-W25` - top_score: `88` - skill_count: `12` - actionable_portfolio_issue_count: `0` -- release_lock_ready: `False` +- release_lock_ready: `True` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index d86c8320..f92ef125 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad" + "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" } ] }, @@ -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 22da9491..fe24ca0b 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": "2026-06-17", + "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 d2d4d668..5315b99a 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index bbfc6f87..df978d9e 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": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -312,7 +312,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index 440128cd..297677c7 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index 5765d1b3..ef380d20 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": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -16,8 +16,8 @@ "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, @@ -33,8 +33,8 @@ "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, @@ -410,7 +410,7 @@ "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:///", @@ -447,7 +447,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -468,8 +468,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -485,8 +485,8 @@ } ], "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 6920d900..eb8c1650 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -8,8 +8,8 @@ Generated at: `2026-06-17` - 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` @@ -30,7 +30,7 @@ This ledger records the current evidence state. It requires both passing source | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. | | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. | | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 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 @@ -172,8 +172,8 @@ This ledger records the current evidence state. It requires both passing source - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 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_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "ledger_counts_as_completion": false}` ### Provenance Requirements @@ -197,7 +197,7 @@ This ledger records the current evidence state. It requires both passing source | Check | Current | Expected | Status | | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | -| Adoption sample | `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 dc133c76..50908b39 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": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", @@ -146,7 +146,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -309,7 +309,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index a7bc5eb2..3a1b0962 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 | | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 | | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | ## Provider Holdout diff --git a/reports/world_class_evidence_preflight.html b/reports/world_class_evidence_preflight.html index 6c8d1665..88f28e2d 100644 --- a/reports/world_class_evidence_preflight.html +++ b/reports/world_class_evidence_preflight.html @@ -65,7 +65,7 @@ Evidence Collection

World-Class Evidence Preflight

This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.

-
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source6/13
+
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source7/13
@@ -611,15 +611,15 @@
-
+
adoption_sample_count Adoption sample
-
Current
0
+
Current
1
Expected
>0
-
Status
blocked
+
Status
pass
Action
Telemetry must include adoption outcome evidence.
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index 600a442f..4a7eaf7a 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -14,8 +14,8 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "pending_count": 4, "ready_to_claim_world_class": false, "credential_value_exposed": false, @@ -535,8 +535,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -891,8 +891,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 52a3d2ac..e487d321 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -1,6 +1,6 @@ # World-Class Evidence Preflight -Generated at: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -10,7 +10,7 @@ Generated at: `2026-06-17` - credential value exposed: `false` - collection ready: `1` - collection blocked: `3` -- source checks: `6` pass / `13` total +- source checks: `7` pass / `13` total This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger. @@ -150,7 +150,7 @@ Generate the submission kit after the real provider, human, native-permission, o | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index a3b8b9fa..9fa92ced 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

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

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

Fast Path

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

Evidence Items

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

Source Runbook

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

Success Checks

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

Privacy

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

Next Source Actions

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

Source Evidence Snapshot

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

Next Source Actions

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

Source Evidence Snapshot

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

Boundary

  • Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.
  • Valid intake means ready for submission review; ledger review still requires passing source evidence.
  • The world-class ledger and claim guard remain the source of truth.
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index 2ccccdc6..03f7b4a1 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": "2026-06-17", + "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" @@ -408,7 +408,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 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.", @@ -456,7 +456,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -477,8 +477,8 @@ "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." }, @@ -493,10 +493,9 @@ "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 9118e3af..8ba17d83 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials | | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer | | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator | -| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | +| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | ## Provider Holdout @@ -244,7 +244,7 @@ This runbook coordinates evidence collection only. It does not accept submission - objective: Import production metadata-only events from a real external client into the local drift loop. - blocking reason: No evidence packet has been submitted for review. -- blocked source checks: `2` +- blocked source checks: `1` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -297,14 +297,13 @@ This runbook coordinates evidence collection only. It does not accept submission ### Next Source Actions - Import at least one metadata-only event from a real client. -- Telemetry must include adoption outcome evidence. ### Source Evidence Snapshot | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 57e35727..8abee31b 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": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -14,8 +14,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -27,8 +27,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -302,7 +302,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -323,8 +323,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -340,8 +340,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index 4d0deed1..21bd5b52 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: `2026-06-17` +Generated at: `2026-06-13` ## Summary @@ -139,7 +139,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w #### Source Checks - External events: 0 / >0 => blocked -- Adoption sample: 0 / >0 => blocked +- Adoption sample: 1 / >0 => pass - Raw content blocked: False / false => pass #### Completion Assertions