From f135ebcb89c3dff44c9bb83b81f7e12dbe89114e Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 00:30:37 +0800 Subject: [PATCH] Refresh clean release lock --- reports/benchmark_reproducibility.json | 26 ++++++++++---------- reports/benchmark_reproducibility.md | 20 +++++++-------- reports/evidence_consistency.json | 24 +++++++++--------- reports/review-studio.json | 34 +++++++++++++------------- reports/review-viewer.json | 8 +++--- reports/skill-interpretation.json | 8 +++--- reports/skill-overview.json | 8 +++--- 7 files changed, 64 insertions(+), 64 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index e800b756..c0a44cf7 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,7 +3,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "git_status": { "available": true, "dirty": false, @@ -17,9 +17,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -54,7 +54,7 @@ }, "release_lock": { "ready": true, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -64,7 +64,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee" + "sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +137,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "fd7ff9272fce16597e0523309031e0af258f03f3d95962ea8253b8b52fe2c7d0" + "bytes": 7967, + "sha256": "8d9e6fbb2dc55c3eaf7a0b7da723aaa76390bb79acc91be7fdb034a75ca717c2" }, { "label": "blind_review", @@ -173,7 +173,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 109099, - "sha256": "cd5164ceec4c51768492886e5cddcb30da79a9a7e5d56ea3249b2aadf8dbe026" + "sha256": "24c3c8a9132543cd070da131aa88b6f1aa265d26264e1fb454ebe487b82d0c93" }, { "label": "python_compatibility", @@ -187,14 +187,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "19e89a9fcc9093bbfe59ca9747a3f9a358b3081c80ef16b9ee252cdb565a6505" + "sha256": "b649ca39e401773d8692b302e1b4dad52b374358082acd2d5d6aa39cad952863" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "7f80da575f1f076df25ef0633b37daaa5790408009b48abeefeebcb2aed6ee35" + "sha256": "0350e754a2d1f07e0897b38f95da92d951172e1a28acd47f7d18b3b790541059" }, { "label": "install_simulation", @@ -263,8 +263,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 8911, - "sha256": "9deabb025d111a7f00d5a97fe691c7297de45a97057a0f2792be93d9a8059b3b" + "bytes": 15531, + "sha256": "c14b3b9914d3780f4cb32398f299781b76314b79de1b304cd66bcc543a7a77f9" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index bfb99599..b47b0689 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `71f1ebea17749e6bf7c4e06d5134d436fc487257` +Commit: `92ff8bd10f4b1a9d9d810680679e069f8fc4f185` Working tree dirty at generation: `false` -Evidence bundle SHA256: `aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee` +Evidence bundle SHA256: `a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3` ## Summary @@ -12,8 +12,8 @@ Evidence bundle SHA256: `aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `85e86b1f0f77` -- archive sha256: `052aea12dfd4` +- source contract sha256: `365c0b0cafd0` +- archive sha256: `c2e8d9a84e48` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `22` @@ -50,7 +50,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee` +- sha256: `a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3` ## Methodology Sections @@ -72,15 +72,15 @@ 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 | `fd7ff9272fce` | +| output_execution | `reports/output_execution_runs.json` | present | `8d9e6fbb2dc5` | | 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 | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `cd5164ceec4c` | +| trust_report | `reports/security_trust_report.json` | present | `24c3c8a91325` | | python_compatibility | `reports/python_compatibility.json` | present | `471c481ff9f9` | -| registry_audit | `reports/registry_audit.json` | present | `19e89a9fcc90` | -| package_verification | `reports/package_verification.json` | present | `7f80da575f1f` | +| registry_audit | `reports/registry_audit.json` | present | `b649ca39e401` | +| package_verification | `reports/package_verification.json` | present | `0350e754a2d1` | | install_simulation | `reports/install_simulation.json` | present | `28ceb014e202` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `57536bc67370` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` | @@ -90,7 +90,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f5ca32d5ea8b` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `260d5e03c52e` | | world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `9deabb025d11` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `c14b3b9914d3` | ## Reproduction Commands diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index a331f5f6..d255c092 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -53,8 +53,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "71f1ebea17749e6bf7c4e06d5134d436fc487257", - "actual": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "expected": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", + "actual": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -69,8 +69,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -82,8 +82,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -199,8 +199,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "71f1ebea17749e6bf7c4e06d5134d436fc487257", - "actual": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "expected": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", + "actual": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -215,8 +215,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -228,8 +228,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, diff --git a/reports/review-studio.json b/reports/review-studio.json index 85725c3d..01b4f771 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1680,9 +1680,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1704,7 +1704,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "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.", @@ -5299,7 +5299,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "git_status": { "available": true, "dirty": false, @@ -5313,9 +5313,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -5350,7 +5350,7 @@ }, "release_lock": { "ready": true, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -5360,7 +5360,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee" + "sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5433,8 +5433,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "fd7ff9272fce16597e0523309031e0af258f03f3d95962ea8253b8b52fe2c7d0" + "bytes": 7967, + "sha256": "8d9e6fbb2dc55c3eaf7a0b7da723aaa76390bb79acc91be7fdb034a75ca717c2" }, { "label": "blind_review", @@ -5469,7 +5469,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 109099, - "sha256": "cd5164ceec4c51768492886e5cddcb30da79a9a7e5d56ea3249b2aadf8dbe026" + "sha256": "24c3c8a9132543cd070da131aa88b6f1aa265d26264e1fb454ebe487b82d0c93" }, { "label": "python_compatibility", @@ -5483,14 +5483,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "19e89a9fcc9093bbfe59ca9747a3f9a358b3081c80ef16b9ee252cdb565a6505" + "sha256": "b649ca39e401773d8692b302e1b4dad52b374358082acd2d5d6aa39cad952863" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "7f80da575f1f076df25ef0633b37daaa5790408009b48abeefeebcb2aed6ee35" + "sha256": "0350e754a2d1f07e0897b38f95da92d951172e1a28acd47f7d18b3b790541059" }, { "label": "install_simulation", @@ -5559,8 +5559,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 8911, - "sha256": "9deabb025d111a7f00d5a97fe691c7297de45a97057a0f2792be93d9a8059b3b" + "bytes": 15531, + "sha256": "c14b3b9914d3780f4cb32398f299781b76314b79de1b304cd66bcc543a7a77f9" } ], "missing_artifacts": [], diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 24c539ae..8d49b7c0 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -1000,9 +1000,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1024,7 +1024,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 5fa8298c..70d935bd 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1004,9 +1004,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1028,7 +1028,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 7a4a4dbe..110c48cb 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -999,9 +999,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "aac232dbeab719adeffe4c50767d6207f95576e2e34405e02d3b62d7ed2619ee", - "source_contract_sha256": "85e86b1f0f774b8f04a45d0665553bdbacca16655d0a28d16577f53bac48535a", - "archive_sha256": "052aea12dfd456a03c6f0a260a59098da036209eea6a8d5109b951005c29f9d9", + "evidence_bundle_sha256": "a86e6702a7a634afe4ff339666eaf66ac5be9b765a9f9c9a2168f6d1aa3c9cd3", + "source_contract_sha256": "365c0b0cafd05b0239206f84990741005c3699e1e6be3d82ccbaf903372218a0", + "archive_sha256": "c2e8d9a84e48571f8ba8d054fc462328401f64e8d335ab0078d292041d3ffb2e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1023,7 +1023,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "71f1ebea17749e6bf7c4e06d5134d436fc487257", + "commit": "92ff8bd10f4b1a9d9d810680679e069f8fc4f185", "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.",