From d5beede0a62dab0f0780be283a274ed8a5be9dc4 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Wed, 17 Jun 2026 01:31:37 +0800 Subject: [PATCH] Stabilize Review Studio panel context reports --- reports/benchmark_reproducibility.json | 17 ++++++++-------- reports/benchmark_reproducibility.md | 10 +++++----- reports/context_budget.json | 4 ++-- reports/evidence_consistency.json | 10 +++++----- reports/review-studio.json | 27 +++++++++++++------------- reports/review-viewer.json | 6 +++--- reports/skill-interpretation.json | 6 +++--- reports/skill-overview.json | 6 +++--- 8 files changed, 42 insertions(+), 44 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index ef8654de..d59db80a 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,14 +3,13 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "git_status": { "available": true, "dirty": true, - "changed_file_count": 2, + "changed_file_count": 1, "sample": [ - " M reports/context_budget.json", - " M reports/context_budget_summary.json" + " M reports/context_budget.json" ], "scope": "generation-time status before this report is written" }, @@ -20,7 +19,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -42,7 +41,7 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, "public_claim": { "ready": false, @@ -58,7 +57,7 @@ }, "release_lock": { "ready": false, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "status_scope": "generation-time status before this report is written", "reason": "working tree was dirty at generation time" }, @@ -68,7 +67,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3" + "sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -240,7 +239,7 @@ "path": "reports/world_class_evidence_preflight.json", "exists": true, "bytes": 41202, - "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960" + "sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454" }, { "label": "world_class_submission_review", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 2c755ae0..911047ae 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `bc74e896e0241c17d25d94e198f91a2e2e7136cf` +Commit: `10114cc4082486e3dab14422678c14aa28a135f9` Working tree dirty at generation: `true` -Evidence bundle SHA256: `e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3` +Evidence bundle SHA256: `5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0` ## Summary @@ -23,7 +23,7 @@ Evidence bundle SHA256: `e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125a - world-class source checks: `7` pass / `13` total; `6` blocked - public claim ready: `false` - public claim blockers: `5` -- changed files at generation: `2` +- changed files at generation: `1` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3` +- sha256: `5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0` ## Methodology Sections @@ -87,7 +87,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `af3c3f101ad9` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `74deeabfac9f` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `69afd0ff3d49` | -| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `97924dd4be88` | +| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `b7fd72d7e754` | | world_class_submission_review | `reports/world_class_submission_review.json` | present | `17def7ba6982` | | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `00bfa998b24a` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `337fb764b98a` | diff --git a/reports/context_budget.json b/reports/context_budget.json index b2d04816..d5dcc52c 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,9 +6,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1083263, + "other_text_tokens": 1083265, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1084060, + "estimated_total_text_tokens": 1084062, "deferred_resource_tokens": 496411, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 44550cb9..c822efaa 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 17 + "changed_file_count": 7 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", - "actual": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "expected": "10114cc4082486e3dab14422678c14aa28a135f9", + "actual": "10114cc4082486e3dab14422678c14aa28a135f9", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", - "actual": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "expected": "10114cc4082486e3dab14422678c14aa28a135f9", + "actual": "10114cc4082486e3dab14422678c14aa28a135f9", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" diff --git a/reports/review-studio.json b/reports/review-studio.json index 01ebe944..52120efa 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1963,7 +1963,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -1985,9 +1985,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "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.", @@ -5650,14 +5650,13 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "git_status": { "available": true, "dirty": true, - "changed_file_count": 2, + "changed_file_count": 1, "sample": [ - " M reports/context_budget.json", - " M reports/context_budget_summary.json" + " M reports/context_budget.json" ], "scope": "generation-time status before this report is written" }, @@ -5667,7 +5666,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -5689,7 +5688,7 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, "public_claim": { "ready": false, @@ -5705,7 +5704,7 @@ }, "release_lock": { "ready": false, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "status_scope": "generation-time status before this report is written", "reason": "working tree was dirty at generation time" }, @@ -5715,7 +5714,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3" + "sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5887,7 +5886,7 @@ "path": "reports/world_class_evidence_preflight.json", "exists": true, "bytes": 41202, - "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960" + "sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454" }, { "label": "world_class_submission_review", @@ -17154,9 +17153,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1083263, + "other_text_tokens": 1083265, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1084060, + "estimated_total_text_tokens": 1084062, "deferred_resource_tokens": 496411, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/review-viewer.json b/reports/review-viewer.json index de630198..e3a97d6a 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -1000,7 +1000,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -1022,9 +1022,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "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 20b281d9..3d89c23f 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1004,7 +1004,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -1026,9 +1026,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "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 f4a344ea..e0fc9363 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -999,7 +999,7 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e6cd7596a1a607513953670b24999725560dc93cc342f26eb8f125ade638c5e3", + "evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0", "source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc", "archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f", "output_case_count": 5, @@ -1021,9 +1021,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 2 + "changed_file_count": 1 }, - "commit": "bc74e896e0241c17d25d94e198f91a2e2e7136cf", + "commit": "10114cc4082486e3dab14422678c14aa28a135f9", "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.",