From 7ae32ed87e37d6d0beda7da94fbc3d1100308bb6 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Sun, 14 Jun 2026 14:27:15 +0800 Subject: [PATCH] chore: refresh falsey world-class HTML evidence --- registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 6 +- reports/benchmark_reproducibility.json | 58 ++++++---- reports/benchmark_reproducibility.md | 33 +++--- reports/output_execution_runs.json | 20 ++-- reports/output_execution_runs.md | 20 ++-- reports/package_verification.json | 2 +- reports/package_verification.md | 2 +- reports/registry_audit.json | 8 +- reports/registry_audit.md | 4 +- reports/review-studio.html | 12 +-- reports/review-studio.json | 124 ++++++++++++---------- reports/review-viewer.json | 30 +++--- reports/security_trust_report.json | 2 +- reports/security_trust_report.md | 2 +- reports/skill-overview.json | 30 +++--- reports/upgrade_check.json | 4 +- reports/world_class_operator_runbook.html | 10 +- 18 files changed, 199 insertions(+), 170 deletions(-) diff --git a/registry/index.json b/registry/index.json index bb849619..8044d025 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 8c3f7d9e..3689bf12 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index a7caa4b4..f8633cff 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-14", "skill_dir": ".", - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 12, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md", + " M reports/registry_audit.json", + " M reports/registry_audit.md", + " M reports/security_trust_report.json", + " M reports/security_trust_report.md", + " M reports/upgrade_check.json", + " M reports/world_class_operator_runbook.html" + ], "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974", - "source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53", + "source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -37,14 +50,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 12 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -53,10 +67,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "ready": false, + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974" + "sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "2cf2125532768f1508c9315e34da939fad4f1e82d208a8e396448ae566d58e7d" + "bytes": 7965, + "sha256": "d8028784464931bc1d44ce097feb95e531682ee5172f4e9680da7a11f93b2b98" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 99433, - "sha256": "7970e6e10389ab71f62ac9d4fef94156af0190c4f4cd20ba50628c6c20f88730" + "sha256": "7fccfda339c51073eb1c8325ac7740e7c6f44f4067b4ba66cba1afd5f095ac25" }, { "label": "python_compatibility", @@ -187,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "05064b43ac6b246bedf978f8ca7b6d8815598eb2ecf38fe7ff8e2fae0a2540c2" + "sha256": "f919e3f7834aee8891c5cc97a26ea9f8045b30b3c41e0bf6bbe9a1c13ee63d83" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19325, - "sha256": "855a53df171f5265cbe270b753c6b88ca472619053f7daa1aa5c8550da20fb4d" + "sha256": "53af9d5a90682b65f190cd9b0cf99aaa1496cb3d16c7199df06d5bdfa0ded491" }, { "label": "install_simulation", @@ -256,8 +270,8 @@ "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 17601, - "sha256": "fccbe471168acd7f87fb1f0111753d6a2213ad26f41593512f915183a14feddc" + "bytes": 17616, + "sha256": "b94a0e9d92b6609eb6c06e608b52aa17174638bc1422e3b3d306521906bccb01" }, { "label": "world_class_claim_guard", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index fab71ecf..4d793f45 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-14` -Commit: `a5d6a39782c8d990a7203e116ec3ba8f720b2061` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974` +Commit: `fd5a790df90b2b6faad58b671c42171186504bac` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `2911f884e900` -- archive sha256: `a514212a268d` +- source contract sha256: `ec040d5f83c4` +- archive sha256: `2204fd96f426` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `21` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd68 - world-class ready: `false` - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `12` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `true` -- reason: clean generation-time HEAD +- ready: `false` +- reason: working tree was dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974` +- sha256: `5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53` ## Methodology Sections @@ -72,15 +73,15 @@ 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 | `2cf212553276` | +| output_execution | `reports/output_execution_runs.json` | present | `d80287844649` | | 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 | `7970e6e10389` | +| trust_report | `reports/security_trust_report.json` | present | `7fccfda339c5` | | python_compatibility | `reports/python_compatibility.json` | present | `ae16e17266e4` | -| registry_audit | `reports/registry_audit.json` | present | `05064b43ac6b` | -| package_verification | `reports/package_verification.json` | present | `855a53df171f` | +| registry_audit | `reports/registry_audit.json` | present | `f919e3f7834a` | +| package_verification | `reports/package_verification.json` | present | `53af9d5a9068` | | install_simulation | `reports/install_simulation.json` | present | `1ed7ce5266c2` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `6bb2dcb0e1e5` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `164803bb1cea` | @@ -89,7 +90,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_submission_review | `reports/world_class_submission_review.json` | present | `a6d609911ed5` | | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `443e0335d270` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `4bd789775307` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `fccbe471168a` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `b94a0e9d92b6` | | world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `250d616b028c` | ## Reproduction Commands diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 13ec74d1..f0c2da48 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": 26.08, + "duration_ms": 32.05, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.94, + "duration_ms": 32.15, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.49, + "duration_ms": 36.28, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.72, + "duration_ms": 35.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.52, + "duration_ms": 31.6, "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": 31.55, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.79, + "duration_ms": 30.2, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.0, + "duration_ms": 30.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.79, + "duration_ms": 30.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.72, + "duration_ms": 30.65, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 1ef35a33..dd26ee07 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 | 26.08 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 25.94 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 27.49 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.72 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 26.52 | 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 | 26.79 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.0 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.79 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.72 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 32.05 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 32.15 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 36.28 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.12 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 31.6 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.55 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.2 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.67 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.85 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.65 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 487171c2..8207ef20 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "archive_entry_count": 577, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 77fd9f5e..9289a6f1 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c` +- Archive SHA256: `2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 7e0f40ab..c8f140f0 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 78bc9ec7..d3a5d39e 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0` -- Archive SHA256: `a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c` +- Package SHA256: `ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c` +- Archive SHA256: `2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index b48fc12c..3f3f11d0 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -543,7 +543,7 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint20/20

2.0 coverage; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

98 scripts scanned; secrets found

Py Compat0

159 files scanned for Python 3.11

Arch Debt0

891 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

577 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint20/20

2.0 coverage; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

98 scripts scanned; secrets found

Py Compat0

159 files scanned for Python 3.11

Arch Debt0

891 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

577 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

@@ -615,7 +615,7 @@
-

信任报告

Secret
0
脚本数
98
网络脚本
3
Help 失败
0
包体哈希
2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0
+

信任报告

Secret
0
脚本数
98
网络脚本
3
Help 失败
0
包体哈希
ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c

安全边界

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

@@ -673,8 +673,8 @@
-

公开声明

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

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
+

公开声明

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

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
@@ -694,12 +694,12 @@

注册审计

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

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710

发布路线

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

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
577
失败数
0
警告数
0
归档哈希
a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
577
失败数
0
警告数
0
归档哈希
2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710
diff --git a/reports/review-studio.json b/reports/review-studio.json index 6261e7eb..6a0e0d6c 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1332,13 +1332,13 @@ "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974", - "source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53", + "source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -1356,11 +1356,11 @@ "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": 12 }, - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "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.", @@ -1465,7 +1465,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 182, - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" }, "skill_atlas": { "skill_count": 12, @@ -1503,8 +1503,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -1535,7 +1535,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1551,7 +1551,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "archive_entry_count": 577, "failure_count": 0, "warning_count": 0 @@ -1630,12 +1630,12 @@ { "field": "archive_sha256", "from": "", - "to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, @@ -3967,7 +3967,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.08, + "duration_ms": 32.05, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3995,7 +3995,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.94, + "duration_ms": 32.15, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4018,7 +4018,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.49, + "duration_ms": 36.28, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4046,7 +4046,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.72, + "duration_ms": 35.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4069,7 +4069,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.52, + "duration_ms": 31.6, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4097,7 +4097,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.16, + "duration_ms": 31.55, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4120,7 +4120,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.79, + "duration_ms": 30.2, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4147,7 +4147,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.0, + "duration_ms": 30.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4170,7 +4170,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.79, + "duration_ms": 30.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4199,7 +4199,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.72, + "duration_ms": 30.65, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4920,23 +4920,36 @@ "ok": true, "generated_at": "2026-06-14", "skill_dir": ".", - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 12, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md", + " M reports/registry_audit.json", + " M reports/registry_audit.md", + " M reports/security_trust_report.json", + " M reports/security_trust_report.md", + " M reports/upgrade_check.json", + " M reports/world_class_operator_runbook.html" + ], "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974", - "source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53", + "source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -4954,14 +4967,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 12 }, "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)", @@ -4970,10 +4984,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "ready": false, + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "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)", @@ -4981,7 +4995,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974" + "sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5054,8 +5068,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "2cf2125532768f1508c9315e34da939fad4f1e82d208a8e396448ae566d58e7d" + "bytes": 7965, + "sha256": "d8028784464931bc1d44ce097feb95e531682ee5172f4e9680da7a11f93b2b98" }, { "label": "blind_review", @@ -5090,7 +5104,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 99433, - "sha256": "7970e6e10389ab71f62ac9d4fef94156af0190c4f4cd20ba50628c6c20f88730" + "sha256": "7fccfda339c51073eb1c8325ac7740e7c6f44f4067b4ba66cba1afd5f095ac25" }, { "label": "python_compatibility", @@ -5104,14 +5118,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "05064b43ac6b246bedf978f8ca7b6d8815598eb2ecf38fe7ff8e2fae0a2540c2" + "sha256": "f919e3f7834aee8891c5cc97a26ea9f8045b30b3c41e0bf6bbe9a1c13ee63d83" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19325, - "sha256": "855a53df171f5265cbe270b753c6b88ca472619053f7daa1aa5c8550da20fb4d" + "sha256": "53af9d5a90682b65f190cd9b0cf99aaa1496cb3d16c7199df06d5bdfa0ded491" }, { "label": "install_simulation", @@ -5173,8 +5187,8 @@ "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 17601, - "sha256": "fccbe471168acd7f87fb1f0111753d6a2213ad26f41593512f915183a14feddc" + "bytes": 17616, + "sha256": "b94a0e9d92b6609eb6c06e608b52aa17174638bc1422e3b3d306521906bccb01" }, { "label": "world_class_claim_guard", @@ -10813,7 +10827,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 182, - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" }, "failures": [], "warnings": [], @@ -18427,8 +18441,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -18459,7 +18473,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -18484,7 +18498,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, @@ -18507,7 +18521,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "archive_entry_count": 577, "failure_count": 0, "warning_count": 0 @@ -19515,12 +19529,12 @@ { "field": "archive_sha256", "from": "", - "to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 5f2ad6b7..fa26d078 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -919,13 +919,13 @@ "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974", - "source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53", + "source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -943,11 +943,11 @@ "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": 12 }, - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "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.", @@ -1052,7 +1052,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 182, - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" }, "skill_atlas": { "skill_count": 12, @@ -1090,8 +1090,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -1122,7 +1122,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1138,7 +1138,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "archive_entry_count": 577, "failure_count": 0, "warning_count": 0 @@ -1217,12 +1217,12 @@ { "field": "archive_sha256", "from": "", - "to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 45186480..057efc8c 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": 182, - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 0c69bbdf..e3a831f4 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: `182` -- Package SHA256: `2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0` +- Package SHA256: `ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c` ## Failures diff --git a/reports/skill-overview.json b/reports/skill-overview.json index cf5f1fe3..45d41204 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -918,13 +918,13 @@ "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": "28fa814ada12fb6fcdf82d29c37e72284ea33e861b6907a1df3fd683c815c974", - "source_contract_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "evidence_bundle_sha256": "5b5f5e21cf01b206c661c6b6e06a6aebea5e1220f5082f3209cde3c5bd42ce53", + "source_contract_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -942,11 +942,11 @@ "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": 12 }, - "commit": "a5d6a39782c8d990a7203e116ec3ba8f720b2061", + "commit": "fd5a790df90b2b6faad58b671c42171186504bac", "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.", @@ -1051,7 +1051,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 182, - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" }, "skill_atlas": { "skill_count": 12, @@ -1089,8 +1089,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0", - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "package_sha256": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, "compatibility": { "openai": "pass", @@ -1121,7 +1121,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1137,7 +1137,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c", + "archive_sha256": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710", "archive_entry_count": 577, "failure_count": 0, "warning_count": 0 @@ -1216,12 +1216,12 @@ { "field": "archive_sha256", "from": "", - "to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 7b738f49..9fa0eafd 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "a514212a268d5f3ab464940854aea174f3389ae6481fed3191ae609961c2917c" + "to": "2204fd96f426bbc29bdb2537ca952cb1d4f250a514efd3bd7135c1d0aa3dc710" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "2911f884e900178b0361f4d0e7435ec990f0b008636b1ed341a851aeac2d04e0" + "to": "ec040d5f83c4a653c56b8ac2423fe5ff8523083682ea111b4eb42e3ee91e400c" } ] }, diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index 10dd39bb..1b5695e9 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
Ready
Source6/13
Blocked7
Invalid
+
Pending4
Awaiting4
Ready0
Source6/13
Blocked7
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

@@ -76,7 +76,7 @@

Privacy

  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.

Next Source Actions

  • Run provider-backed output-exec with real credentials.
  • Provider execution should return non-estimated token usage.
-

Source Evidence Snapshot

  • Provider model runmodel_executed_count: / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: / >0Provider execution should return non-estimated token usage.
+

Source Evidence Snapshot

  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
human · awaiting-submission

Human Adjudication

No evidence packet has been submitted for review.

@@ -93,7 +93,7 @@

Privacy

  • Reviewer decisions should not include raw user data or private customer detail.
  • Keep the answer key separate until after decisions are recorded.

Next Source Actions

  • Record a reviewer choice for every pair.
  • Every pair needs one valid human judgment.
-

Source Evidence Snapshot

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: / ==0Fix malformed winner/confidence entries.
+

Source Evidence Snapshot

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: 0 / ==0Fix malformed winner/confidence entries.
external · awaiting-submission

Native Permission Enforcement

No evidence packet has been submitted for review.

@@ -110,7 +110,7 @@

Privacy

  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.

Next Source Actions

  • Collect real target-client or external runtime guard proof.
-

Source Evidence Snapshot

  • Native enforcementnative_enforcement_count: / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
+

Source Evidence Snapshot

  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: 0 / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
external · awaiting-submission

Native Client Telemetry

No evidence packet has been submitted for review.

@@ -127,7 +127,7 @@

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

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.

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.