From ad40ed8693324c51dec88d3b1f60d804f18b0462 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Mon, 15 Jun 2026 22:08:46 +0800 Subject: [PATCH] Accept explicit portability report skill path --- registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 2 +- reports/adoption_drift_report.json | 28 +++---- reports/adoption_drift_report.md | 10 +-- reports/architecture_maintainability.json | 2 +- reports/architecture_maintainability.md | 2 +- reports/benchmark_reproducibility.json | 86 +++++++++++++--------- reports/benchmark_reproducibility.md | 49 ++++++------ reports/compiled_targets.json | 2 +- reports/context_budget.json | 12 +-- reports/context_budget.md | 2 +- reports/context_budget_summary.json | 6 +- reports/evidence_consistency.json | 40 +++++----- reports/output_execution_runs.json | 20 ++--- reports/output_execution_runs.md | 20 ++--- reports/python_compatibility.json | 2 +- reports/python_compatibility.md | 2 +- reports/registry_audit.json | 4 +- reports/registry_audit.md | 2 +- reports/review-viewer.json | 20 ++--- reports/review_annotations.json | 2 +- reports/review_waivers.json | 4 +- reports/review_waivers.md | 2 +- reports/security_trust_report.json | 4 +- reports/security_trust_report.md | 2 +- reports/skill-interpretation.html | 4 +- reports/skill-interpretation.json | 65 ++++++++-------- reports/skill-overview.html | 4 +- reports/skill-overview.json | 65 ++++++++-------- reports/upgrade_check.json | 2 +- reports/world_class_claim_guard.json | 2 +- reports/world_class_claim_guard.md | 2 +- reports/world_class_evidence_intake.json | 4 +- reports/world_class_evidence_intake.md | 2 +- reports/world_class_evidence_ledger.json | 18 ++--- reports/world_class_evidence_ledger.md | 14 ++-- reports/world_class_evidence_plan.json | 6 +- reports/world_class_evidence_plan.md | 4 +- reports/world_class_operator_runbook.html | 8 +- reports/world_class_operator_runbook.json | 19 +++-- reports/world_class_operator_runbook.md | 9 +-- reports/world_class_submission_review.json | 16 ++-- reports/world_class_submission_review.md | 4 +- scripts/render_portability_report.py | 14 +++- tests/verify_portability_report.py | 30 +++++--- 45 files changed, 323 insertions(+), 296 deletions(-) diff --git a/registry/index.json b/registry/index.json index 2cca4c5..20efb71 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 4be5e83..6327782 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": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 72d6679..0cc85b7 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": "2026-06-15T13:58:27Z", + "generated_at": "2026-06-15T14:07:59Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 91b3198..206372c 100644 --- a/reports/adoption_drift_report.md +++ b/reports/adoption_drift_report.md @@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Summary - Events: `1` -- Adoption samples: `0` -- Activation events: `0` -- Adoption rate: `0` +- Adoption samples: `1` +- Activation events: `1` +- Adoption rate: `100.0` - Missed trigger signals: `0` - Bad output signals: `0` - Script error signals: `0` @@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | -| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | +| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` +- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 12fd0d1..9f8f1a1 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": 170, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 86e9fe4..8c7686f 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 diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 3529563..ee42e40 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": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "commit": "84b761abce9f0a361ddea7d446d0454666de0885", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 47, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49", - "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "evidence_bundle_sha256": "27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -34,29 +47,30 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "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": 47 }, "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)", - "world-class source checks are not all accepted (6/13 pass, 7 blocked)" + "world-class source checks are not all accepted (7/13 pass, 6 blocked)" ], "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": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "ready": false, + "commit": "84b761abce9f0a361ddea7d446d0454666de0885", "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": "c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49" + "sha256": "27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "d16d8e11c63928e7a6068e46f477b0717e91e8f1b4bc2966c92684bf3cbae4dd" + "bytes": 7966, + "sha256": "0fdf9c4498785556f8bc64f6418aba96d58fda70c40a6d8677cb343988897c63" }, { "label": "blind_review", @@ -172,22 +186,22 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 106775, - "sha256": "12d664865a0a38879dc32db7f38c201cac405939476e0f52eadc4c957384564c" + "bytes": 106773, + "sha256": "6409321f1c0d2a7b9208595e05360de8f3dbb56602c8cee61226fb8c31d61f32" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, "bytes": 22510, - "sha256": "73c6c2a81af9980cc1d8e2d1bb5dfb30bd8daccac48125fe71ec359dbde824dd" + "sha256": "d9a52fb5a8d7fbc8f3e6550d26f44a73f0ffafbc2adc682330b550b0f9fe27f3" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "d5e08cc39a3c5073a9332e990c566960ab8166cbdeb3980a8eb63413da64fe21" + "sha256": "76a55d6dfc15afe8f461e37faa1a3661650a09eb3b2c84a8d7c3b04abae4623e" }, { "label": "package_verification", @@ -215,56 +229,56 @@ "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 19940, - "sha256": "933cdb0021818c0a8c5fc199af7dfa7879777ebf7959ed3a36bba52a0aed9c6c" + "sha256": "b408af112c784fdc3e96ea9ecf374990b9f58a0ebfa4df18394ccd9e93dc5545" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 20006, - "sha256": "5407409841eb8e1174a07ea0af17ddf709155f0c548c897b82c2f75b869b333a" + "bytes": 20003, + "sha256": "cc886713ba5b99bdb2f740217f0979a30312aef7539d2a22af0e96ec5c3e90bf" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 18865, - "sha256": "b10e1ce0a5a17df72462ce8f0c468356f58ff88bd7ceab349c82a1fb3b6697ef" + "sha256": "2fbecc603d8dc6382fde6c61869aaf4b56fc9d1be5afcd07b345c419dce6d55a" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 12413, - "sha256": "3bce5f072d037a6c383cfd597f8530c2bc87ba31781fa90c843a9186dd2f8fea" + "bytes": 12410, + "sha256": "bc690472684dcdb8c77803b730857f98e6b6eb11f1e741d5fcc1aa9303b77e47" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 24021, - "sha256": "d377b8d99831ce297011e4e270fc7287a53727500f5d503dd3dc4b984d26f0ad" + "bytes": 23957, + "sha256": "b4640688026ef9199e96f80bd2d9971aaca3ec6d092d8ecd052a5debc0aa94c7" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 15080, - "sha256": "9f141f09bf485a4299b37eb8c21ebab9f212ea130a0daea8b0d7d5bd7ab020aa" + "bytes": 15025, + "sha256": "3a916ac568377d8df7d612426f7358283eddfa2ab5fedb7ed12db0097a8b3c48" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 21030, - "sha256": "04cc091b113f018072d07a1d71ad142773c415a49e633493689903e7b399b5e6" + "bytes": 20969, + "sha256": "886b915da0f27fb46f4d8cebb6211ab5066a9fd44e1ec2e3206487d9a8abfff2" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 8814, - "sha256": "7e5a2eac1020f4f58688b52d3c59b5df1c74d7bc04f4e599b48e5be4cc23d786" + "sha256": "9420a85386ea9044b679d8a5b8771a34efef19d7c58c84ce10653410e4f13e4b" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index a13a7f7..395d485 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,18 +1,18 @@ # Benchmark Reproducibility Generated at: `2026-06-15` -Commit: `a5dab4779d48b51ea8ace316527d38dd559e6b01` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49` +Commit: `84b761abce9f0a361ddea7d446d0454666de0885` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `278b4ff6c0c7` +- source contract sha256: `4660a11db949` - archive sha256: `6852cf91a74d` - output cases: `5` - disclosed failure cases: `3` @@ -20,10 +20,10 @@ Evidence bundle SHA256: `c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a6 - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- world-class source checks: `6` pass / `13` total; `7` blocked +- world-class source checks: `7` pass / `13` total; `6` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `47` 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. @@ -35,22 +35,23 @@ 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) | -| world-class source checks are not all accepted (6/13 pass, 7 blocked) | +| world-class source checks are not all accepted (7/13 pass, 6 blocked) | ## 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: `c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49` +- sha256: `27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4` ## Methodology Sections @@ -72,25 +73,25 @@ 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 | `d16d8e11c639` | +| output_execution | `reports/output_execution_runs.json` | present | `0fdf9c449878` | | 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 | `12d664865a0a` | -| python_compatibility | `reports/python_compatibility.json` | present | `73c6c2a81af9` | -| registry_audit | `reports/registry_audit.json` | present | `d5e08cc39a3c` | +| trust_report | `reports/security_trust_report.json` | present | `6409321f1c0d` | +| python_compatibility | `reports/python_compatibility.json` | present | `d9a52fb5a8d7` | +| registry_audit | `reports/registry_audit.json` | present | `76a55d6dfc15` | | package_verification | `reports/package_verification.json` | present | `2476ae8ec9c4` | | install_simulation | `reports/install_simulation.json` | present | `490e1f665580` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `a4cf40478f3a` | -| 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` | -| world_class_submission_review | `reports/world_class_submission_review.json` | present | `3bce5f072d03` | -| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `d377b8d99831` | -| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `9f141f09bf48` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `7e5a2eac1020` | +| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `b408af112c78` | +| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `cc886713ba5b` | +| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `2fbecc603d8d` | +| world_class_submission_review | `reports/world_class_submission_review.json` | present | `bc690472684d` | +| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `b4640688026e` | +| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `3a916ac56837` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `886b915da0f2` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `9420a85386ea` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 8f1ef92..1897309 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 e125956..e786825 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": 1332754, + "other_text_tokens": 1332957, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1333521, - "deferred_resource_tokens": 421412, + "estimated_total_text_tokens": 1333724, + "deferred_resource_tokens": 421528, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 372822, + "estimated_tokens": 372938, "file_count": 107 }, { @@ -31,7 +31,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 372822, + "estimated_tokens": 372938, "file_count": 107 } ], @@ -54,7 +54,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 372822, + "estimated_tokens": 372938, "file_count": 107, "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 514daf3..f447ebd 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 | 421412 | `governed` | scripts:372822 | 135.4 | - | ok | +| root | `.` | `production` | 1000 | 960 | 767 | 421528 | `governed` | scripts:372938 | 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 a98d667..fe581f8 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 960, "skill_body_tokens": 767, - "deferred_resource_tokens": 421412, + "deferred_resource_tokens": 421528, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 372822, + "estimated_tokens": 372938, "file_count": 107 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 372822, + "estimated_tokens": 372938, "file_count": 107, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index a6d9d69..3fa99dc 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -37,8 +37,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -48,8 +48,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "a5dab4779d48b51ea8ace316527d38dd559e6b01", - "actual": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "expected": "84b761abce9f0a361ddea7d446d0454666de0885", + "actual": "84b761abce9f0a361ddea7d446d0454666de0885", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -61,7 +61,7 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -71,10 +71,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -84,7 +84,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -194,8 +194,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "a5dab4779d48b51ea8ace316527d38dd559e6b01", - "actual": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "expected": "84b761abce9f0a361ddea7d446d0454666de0885", + "actual": "84b761abce9f0a361ddea7d446d0454666de0885", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -207,7 +207,7 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -217,10 +217,10 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", @@ -230,7 +230,7 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -1324,10 +1324,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], - "file_count": 306, + "file_count": 389, "folder_count": 4, "distribution": [ { @@ -1360,7 +1360,7 @@ }, { "label": "reports", - "value": 132 + "value": 215 } ] }, @@ -1412,10 +1412,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], - "file_count": 306, + "file_count": 389, "folder_count": 4, "distribution": [ { @@ -1448,7 +1448,7 @@ }, { "label": "reports", - "value": 132 + "value": 215 } ] }, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 051ca36..be75241 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": 33.48, + "duration_ms": 36.06, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.57, + "duration_ms": 33.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.37, + "duration_ms": 34.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.21, + "duration_ms": 35.2, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.98, + "duration_ms": 36.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.67, + "duration_ms": 40.88, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.89, + "duration_ms": 64.44, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.74, + "duration_ms": 66.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.47, + "duration_ms": 44.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.37, + "duration_ms": 45.77, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 81a6772..db86bf1 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 | 33.48 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 31.57 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 31.37 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.21 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 30.98 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.67 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.89 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 32.74 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 33.47 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 33.37 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 36.06 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 33.24 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 34.12 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.2 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 36.31 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 40.88 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 64.44 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 66.38 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 44.12 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 45.77 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 3a19430..b3b97e6 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 8fcded0..f1252bb 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 fa059d8..9beb411 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 4295bad..0482d28 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713` +- Package SHA256: `4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306` - Archive SHA256: `6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc` - Install simulated: `True` diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 54f832c..8b51190 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -525,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], - "file_count": 306, + "file_count": 389, "folder_count": 4, "distribution": [ { @@ -561,7 +561,7 @@ }, { "label": "reports", - "value": 132 + "value": 215 } ] }, @@ -695,7 +695,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], "strengths": [ @@ -996,11 +996,11 @@ "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": "c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49", + "evidence_bundle_sha256": "1a11230c3274b89fc877d2e243970b3c15508fa913d7efc8f26d53949395c4a2", "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, @@ -1020,11 +1020,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 16 }, - "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "commit": "84b761abce9f0a361ddea7d446d0454666de0885", "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 76fadc1..66f2b1d 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 3acbd17..07eeccb 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": "2026-06-15", + "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 2027-06-15 --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 2fcb054..dbc942d 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 2027-06-15 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 8566c1a..8097d91 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": 194, - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" }, "failures": [], "warnings": [], @@ -2019,7 +2019,7 @@ "timed_out": false, "passed": true, "has_help_text": true, - "stdout_excerpt": "usage: render_portability_report.py [-h] [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n\nRender a portability score from neutral metadata, contracts, and snapshots.\n\noptions:\n -h, --help ", + "stdout_excerpt": "usage: render_portability_report.py [-h] [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [skill_dir]\n\nRender a portability score from neutral metadata, contracts, a", "stderr_excerpt": "" }, { diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index b4adf6c..7812e00 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: `194` -- Package SHA256: `278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713` +- Package SHA256: `4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306` ## Failures diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 057d43e..d215364 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -919,7 +919,7 @@ -

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks7 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
@@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution306项306 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution389项389 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index f530424..3cb4bda 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -412,7 +412,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 6, + "source_pass_count": 7, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,8 +471,7 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events", - "Adoption sample" + "External events" ] } ] @@ -525,10 +524,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], - "file_count": 306, + "file_count": 389, "folder_count": 4, "distribution": [ { @@ -561,7 +560,7 @@ }, { "label": "reports", - "value": 132 + "value": 215 } ] }, @@ -699,7 +698,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], "strengths": [ @@ -1000,12 +999,12 @@ "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": "c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49", - "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "evidence_bundle_sha256": "27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1021,14 +1020,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "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": 47 }, - "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "commit": "84b761abce9f0a361ddea7d446d0454666de0885", "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.", @@ -1133,7 +1132,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 194, - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" }, "skill_atlas": { "skill_count": 12, @@ -1171,7 +1170,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1303,7 +1302,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "to": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" } ] }, @@ -1320,14 +1319,14 @@ "ok": true, "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, @@ -1336,7 +1335,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1558,7 +1557,7 @@ "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:///", @@ -1610,8 +1609,8 @@ "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, @@ -1947,7 +1946,7 @@ "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:///", @@ -1984,7 +1983,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2005,8 +2004,8 @@ "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." }, @@ -2022,8 +2021,8 @@ } ], "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/skill-overview.html b/reports/skill-overview.html index 2ea02b8..9615b69 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -919,7 +919,7 @@
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
-

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks7 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
@@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution306项306 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution389项389 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 39a4e02..1a1a0bd 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -411,7 +411,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 6, + "source_pass_count": 7, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -470,8 +470,7 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events", - "Adoption sample" + "External events" ] } ] @@ -524,10 +523,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], - "file_count": 306, + "file_count": 389, "folder_count": 4, "distribution": [ { @@ -560,7 +559,7 @@ }, { "label": "reports", - "value": 132 + "value": 215 } ] }, @@ -694,7 +693,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 132 + "file_count": 215 } ], "strengths": [ @@ -995,12 +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": "c3a7eae59138523528287cb2670c2c153ec3c2e27d14d09ab01d5a671cb98f49", - "source_contract_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "evidence_bundle_sha256": "27da0809c59bcea3757a4f60fd43b515a8f51b11ab9ef805ba423b13a22f19e4", + "source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1016,14 +1015,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 6, - "world_class_source_blocked_count": 7, + "world_class_source_pass_count": 7, + "world_class_source_blocked_count": 6, "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": 47 }, - "commit": "a5dab4779d48b51ea8ace316527d38dd559e6b01", + "commit": "84b761abce9f0a361ddea7d446d0454666de0885", "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 +1127,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 194, - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" }, "skill_atlas": { "skill_count": 12, @@ -1166,7 +1165,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713", + "package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1298,7 +1297,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "to": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" } ] }, @@ -1315,14 +1314,14 @@ "ok": true, "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, @@ -1331,7 +1330,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1553,7 +1552,7 @@ "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:///", @@ -1605,8 +1604,8 @@ "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, @@ -1942,7 +1941,7 @@ "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:///", @@ -1979,7 +1978,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2000,8 +1999,8 @@ "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." }, @@ -2017,8 +2016,8 @@ } ], "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/upgrade_check.json b/reports/upgrade_check.json index 6bce04f..28896ba 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "278b4ff6c0c7e8406dfa62e5813013532af58e35d12b22f8bef25d59ac544713" + "to": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306" } ] }, diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index ad0e3b9..2774d79 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 f5142e2..56c163e 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 c773fa5..ed002e8 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 bc5fd17..62c2d7e 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 e245338..6637eb6 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 1bc98d0..8ec440f 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 20b0d4e..236c40f 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 6af4cf3..c0db846 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 be9f267..e239453 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 dfb9049..eb0e185 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 3abb08c..bef6278 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 5b79d65..cb10f86 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 a896c21..7fe1e47 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_portability_report.py b/scripts/render_portability_report.py index dbd8d23..0c76e82 100644 --- a/scripts/render_portability_report.py +++ b/scripts/render_portability_report.py @@ -129,13 +129,21 @@ def render_markdown(report: dict) -> str: def main() -> None: parser = argparse.ArgumentParser(description="Render a portability score from neutral metadata, contracts, and snapshots.") + parser.add_argument("skill_dir", nargs="?", default=str(ROOT), help="Skill directory to inspect. Defaults to this repo root.") parser.add_argument("--output-json", default="reports/portability_score.json") parser.add_argument("--output-md", default="reports/portability_score.md") args = parser.parse_args() - report = build_report(ROOT) - output_json = ROOT / args.output_json - output_md = ROOT / args.output_md + skill_root = Path(args.skill_dir).resolve() + report = build_report(skill_root) + output_json = Path(args.output_json) + output_md = Path(args.output_md) + if not output_json.is_absolute(): + output_json = skill_root / output_json + if not output_md.is_absolute(): + output_md = skill_root / output_md + output_json.parent.mkdir(parents=True, exist_ok=True) + output_md.parent.mkdir(parents=True, exist_ok=True) output_json.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") output_md.write_text(render_markdown(report), encoding="utf-8") print(json.dumps(report, ensure_ascii=False, indent=2)) diff --git a/tests/verify_portability_report.py b/tests/verify_portability_report.py index 7a73e35..f44864a 100644 --- a/tests/verify_portability_report.py +++ b/tests/verify_portability_report.py @@ -10,18 +10,26 @@ SCRIPT = ROOT / "scripts" / "render_portability_report.py" def main() -> None: - proc = subprocess.run( - [sys.executable, str(SCRIPT)], - cwd=ROOT, - capture_output=True, - text=True, - ) - if proc.returncode != 0: - print(proc.stdout) - print(proc.stderr) - raise SystemExit(proc.returncode) + payload = None + for args in ([], [str(ROOT)]): + proc = subprocess.run( + [sys.executable, str(SCRIPT), *args], + cwd=ROOT, + capture_output=True, + text=True, + ) + if proc.returncode != 0: + print(proc.stdout) + print(proc.stderr) + raise SystemExit(proc.returncode) + current_payload = json.loads(proc.stdout) + if payload is None: + payload = current_payload + elif current_payload != payload: + print(json.dumps({"default": payload, "explicit": current_payload}, ensure_ascii=False, indent=2)) + raise SystemExit(2) - payload = json.loads(proc.stdout) + assert payload is not None failures = [] if payload.get("score", 0) < 95: failures.append(f"portability score too low: {payload.get('score')}")
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder