{ "audit": { "artifact_resolution": { "candidate_run_dirs": [ "evidences" ], "manifest_path_mismatch": false, "primary_failure_code": null, "resolution_mode": "workspace_evidence_root", "scanned_scopes": [ { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/data/workspaces/ws-eval-1784685468326-179011a2", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "status": "resolved" }, "case_id": "top-tidb-p99-latency-nodes-in-saas01-during-latest-window", "contract": { "actual_cluster_id": "10989049060142230334", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "time_window_match": true }, "critical_evidence_verdict": "pass", "evidence_collection_verdict": "pass", "evidence_routing_verdict": "pass", "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "execution_contract_verdict": "pass", "overall_verdict": "pass", "quality_verdict": "pass", "semantic_shadow": { "available": false, "status": "not_available" }, "source": "deterministic_judge", "strategy": "deterministic_trace_heavy_v1", "workflow_verdict": "pass" }, "case_run_id": "evalcase-c3a0bad379324895b0b63f5aacb5f33f", "facts": { "artifact_observations": { "analysis_patch_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "artifacts": { "analysis_patch_path": "", "diagnosis_report_path": "evidences/workspace_evidence_report.json", "evidence_dir": "evidences", "logs_dir": "", "manifest_path": "", "manifest_path_mismatch": false, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "source_root": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f", "source_scope": "audit_dir", "summary_txt_path": "", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "top-tidb-p99-latency-nodes-in-saas01-during-latest-window", "cluster": { "actual_cluster_id": "10989049060142230334", "allowed_cluster_ids": [ "10989049060142230334" ], "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "matched": true }, "contract": { "actual_cluster_id": "10989049060142230334", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "latency_metric_present", "breakdown_metrics_present", "latency_metric_series_nonempty", "output_cluster_id_matches_reference", "output_window_start_matches_reference", "output_window_end_matches_reference", "evidence_sufficient_matches_reference", "cluster_avg_tikv_grpc_matches_reference", "cluster_avg_pd_tso_matches_reference", "top_nodes_match_runtime_reference" ] }, "evidence": { "analysis_patch_path": "", "core_evidence_bundle_present": false, "decoded_plan_indexes_used": null, "events_attempted_implies_artifact_present": true, "events_channel_observed": true, "events_collection_attempted": false, "events_output_file_present": false, "hotspot_detected": false, "infra_clear": false, "kill_query_signal_present": false, "log_error_counts": {}, "logs_channel_observed": false, "logs_dir_present": false, "memory_tracker_panic_present": false, "metric_evidence": [ { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_server_handle_query_duration_seconds_bucket[1m])))", "start": 1784602800, "step": "60" }, "group": "tidb_query_p99_latency", "id": "tidb_query_p99_latency", "metric_group_id": "tidb_query_p99_latency", "name": "tidb_query_p99_latency", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_server_handle_query_duration_seconds_bucket[1m])))", "ref": { "metric_group_id": "tidb_query_p99_latency", "type": "metric" }, "series_summaries": [ { "avg": 0.05109290967670205, "labels": { "instance": "db-tidb-0" }, "max": 0.06216225913621291, "min": 0.019616509960159838, "point_count": 6 }, { "avg": 0.04478012596129785, "labels": { "instance": "db-tidb-0-ac-2006050899364941824" }, "max": 0.05132832177531199, "min": 0.026483621958121373, "point_count": 6 }, { "avg": 0.05264345509482801, "labels": { "instance": "db-tidb-1" }, "max": 0.0639972166349553, "min": 0.021956266666666828, "point_count": 6 }, { "avg": 0.04537120791956991, "labels": { "instance": "db-tidb-1-ac-2006050899364941824" }, "max": 0.05426187258528582, "min": 0.025786157372039854, "point_count": 6 }, { "avg": 0.04448487881636768, "labels": { "instance": "db-tidb-10-ac-2006050899364941824" }, "max": 0.05244008908686008, "min": 0.02429360298030854, "point_count": 6 }, { "avg": 0.044061393955356104, "labels": { "instance": "db-tidb-11-ac-2006050899364941824" }, "max": 0.05168162249680516, "min": 0.024005317992969247, "point_count": 6 }, { "avg": 0.044598354582392204, "labels": { "instance": "db-tidb-12-ac-2006050899364941824" }, "max": 0.05262999080036822, "min": 0.024491655300681987, "point_count": 6 }, { "avg": 0.04456183169367994, "labels": { "instance": "db-tidb-13-ac-2006050899364941824" }, "max": 0.05290723457563454, "min": 0.02598165636588385, "point_count": 6 }, { "avg": 0.04484433138337032, "labels": { "instance": "db-tidb-14-ac-2006050899364941824" }, "max": 0.0526367458113078, "min": 0.02546028985507258, "point_count": 6 }, { "avg": 0.043648224878135904, "labels": { "instance": "db-tidb-15-ac-2006050899364941824" }, "max": 0.052212024735687965, "min": 0.023746099460755524, "point_count": 6 }, { "avg": 0.04379018937980796, "labels": { "instance": "db-tidb-16-ac-2006050899364941824" }, "max": 0.0522230634446907, "min": 0.02445559484567022, "point_count": 6 }, { "avg": 0.04274434851961686, "labels": { "instance": "db-tidb-17-ac-2006050899364941824" }, "max": 0.05088771829565557, "min": 0.022059746192893664, "point_count": 6 }, { "avg": 0.04495100778550918, "labels": { "instance": "db-tidb-19-ac-2006050899364941824" }, "max": 0.05206770984646472, "min": 0.024636583143509118, "point_count": 6 }, { "avg": 0.05286852008128412, "labels": { "instance": "db-tidb-2" }, "max": 0.07111429396477242, "min": 0.02140626506024117, "point_count": 6 }, { "avg": 0.04546776056766111, "labels": { "instance": "db-tidb-2-ac-2006050899364941824" }, "max": 0.05351811807780302, "min": 0.024239184193754017, "point_count": 6 }, { "avg": 0.04387052882938186, "labels": { "instance": "db-tidb-21-ac-2006050899364941824" }, "max": 0.05190664672239366, "min": 0.022499771230503555, "point_count": 6 }, { "avg": 0.0540247839093527, "labels": { "instance": "db-tidb-3" }, "max": 0.07427786224635874, "min": 0.020659363957597293, "point_count": 6 }, { "avg": 0.04690121204583375, "labels": { "instance": "db-tidb-3-ac-2006050899364941824" }, "max": 0.05588488917036101, "min": 0.02422964015585602, "point_count": 6 }, { "avg": 0.0562734618840536, "labels": { "instance": "db-tidb-4" }, "max": 0.07291956532726968, "min": 0.028893788276466145, "point_count": 6 }, { "avg": 0.043218809631787806, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.0501905158104844, "min": 0.024803245641838736, "point_count": 6 }, { "avg": 0.055390565822026866, "labels": { "instance": "db-tidb-42" }, "max": 0.07610631092868214, "min": 0.02710391143911487, "point_count": 6 }, { "avg": 0.05242222803882867, "labels": { "instance": "db-tidb-43" }, "max": 0.06394283840040371, "min": 0.01946769580022706, "point_count": 6 }, { "avg": 0.05167988403801987, "labels": { "instance": "db-tidb-5" }, "max": 0.060536023738872576, "min": 0.022810909090909274, "point_count": 6 }, { "avg": 0.04327722146543856, "labels": { "instance": "db-tidb-5-ac-2006050899364941824" }, "max": 0.0523255327523197, "min": 0.024373767378772525, "point_count": 6 }, { "avg": 0.04548817128229087, "labels": { "instance": "db-tidb-6-ac-2006050899364941824" }, "max": 0.05263686929298236, "min": 0.02354973768394101, "point_count": 6 }, { "avg": 0.05003802782339442, "labels": { "instance": "db-tidb-7" }, "max": 0.06370694543892391, "min": 0.016736581196581547, "point_count": 6 }, { "avg": 0.04431338566631687, "labels": { "instance": "db-tidb-7-ac-2006050899364941824" }, "max": 0.051385629781528816, "min": 0.025161721288116848, "point_count": 6 }, { "avg": 0.05039962772005289, "labels": { "instance": "db-tidb-72" }, "max": 0.06281568181818187, "min": 0.01965640831758112, "point_count": 6 }, { "avg": 0.05200955127445866, "labels": { "instance": "db-tidb-73" }, "max": 0.06399982261640819, "min": 0.02309508860759515, "point_count": 6 }, { "avg": 0.051534099710741764, "labels": { "instance": "db-tidb-74" }, "max": 0.06359465038167945, "min": 0.018792061068702376, "point_count": 6 }, { "avg": 0.05128184797558665, "labels": { "instance": "db-tidb-75" }, "max": 0.06359219152854564, "min": 0.019473388127853843, "point_count": 6 }, { "avg": 0.04401966613572741, "labels": { "instance": "db-tidb-8-ac-2006050899364941824" }, "max": 0.05166151069256433, "min": 0.025646939617084762, "point_count": 6 }, { "avg": 0.05624071249927115, "labels": { "instance": "db-tidb-82" }, "max": 0.06884185578535454, "min": 0.025114254937163707, "point_count": 6 }, { "avg": 0.05231656448498969, "labels": { "instance": "db-tidb-83" }, "max": 0.06490210947930768, "min": 0.029696544315129997, "point_count": 6 }, { "avg": 0.054298230728183045, "labels": { "instance": "db-tidb-84" }, "max": 0.07778099902056954, "min": 0.022136678966789825, "point_count": 6 }, { "avg": 0.05291697096869489, "labels": { "instance": "db-tidb-87" }, "max": 0.06307042524739237, "min": 0.022645737051792805, "point_count": 6 }, { "avg": 0.05648509616612941, "labels": { "instance": "db-tidb-88" }, "max": 0.07655735501355257, "min": 0.024140410846344097, "point_count": 6 }, { "avg": 0.04413507934415375, "labels": { "instance": "db-tidb-9-ac-2006050899364941824" }, "max": 0.052332838427948086, "min": 0.02500673427991932, "point_count": 6 } ], "summary": { "avg": 0.048485375466849855, "max": 0.07778099902056954, "min": 0.016736581196581547, "point_count": 228, "series_count": 38 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket{instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "avg_plan_build_p99_s", "id": "avg_plan_build_p99_s", "metric_group_id": "avg_plan_build_p99_s", "name": "avg_plan_build_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket{instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "ref": { "metric_group_id": "avg_plan_build_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.013470604625591444, "labels": { "instance": "db-tidb-4" }, "max": 0.01855765496183232, "min": 0.007974047706422339, "point_count": 6 }, { "avg": 0.007212863592010611, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.008184099200881778, "min": 0.005072547343841216, "point_count": 6 }, { "avg": 0.013115806607000706, "labels": { "instance": "db-tidb-82" }, "max": 0.020858209523809235, "min": 0.0049962933333333424, "point_count": 6 }, { "avg": 0.012286080473811302, "labels": { "instance": "db-tidb-88" }, "max": 0.01972983292517024, "min": 0.004621255335968367, "point_count": 6 } ], "summary": { "avg": 0.011521338824603515, "max": 0.020858209523809235, "min": 0.004621255335968367, "point_count": 24, "series_count": 4 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_distsql_handle_query_duration_seconds_bucket{instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "avg_distributed_execution_p99_s", "id": "avg_distributed_execution_p99_s", "metric_group_id": "avg_distributed_execution_p99_s", "name": "avg_distributed_execution_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_distsql_handle_query_duration_seconds_bucket{instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "ref": { "metric_group_id": "avg_distributed_execution_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.05113122680198704, "labels": { "instance": "db-tidb-4" }, "max": 0.06749980364656524, "min": 0.029301657458563616, "point_count": 6 }, { "avg": 0.05222857220048569, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.05925235294117648, "min": 0.030402952710496416, "point_count": 6 }, { "avg": 0.05348690234863827, "labels": { "instance": "db-tidb-82" }, "max": 0.07334636363636293, "min": 0.0329766120218583, "point_count": 6 }, { "avg": 0.05040694925810917, "labels": { "instance": "db-tidb-88" }, "max": 0.061776243052982766, "min": 0.039669914040115384, "point_count": 6 } ], "summary": { "avg": 0.051813412652305046, "max": 0.07334636363636293, "min": 0.029301657458563616, "point_count": 24, "series_count": 4 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_tikvclient_request_seconds_bucket{type=\"Get\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "avg_kv_request_p99_s", "id": "avg_kv_request_p99_s", "metric_group_id": "avg_kv_request_p99_s", "name": "avg_kv_request_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_tikvclient_request_seconds_bucket{type=\"Get\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "ref": { "metric_group_id": "avg_kv_request_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.013630361189446544, "labels": { "instance": "db-tidb-4" }, "max": 0.018637157360406453, "min": 0.005470588235294262, "point_count": 6 }, { "avg": 0.01367541018038979, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.018812513966481096, "min": 0.004253498759305391, "point_count": 6 }, { "avg": 0.01368553635424311, "labels": { "instance": "db-tidb-82" }, "max": 0.018039322033898315, "min": 0.004256410256410371, "point_count": 6 }, { "avg": 0.013411444813272952, "labels": { "instance": "db-tidb-88" }, "max": 0.016681951219512384, "min": 0.005138412698412721, "point_count": 6 } ], "summary": { "avg": 0.013600688134338101, "max": 0.018812513966481096, "min": 0.004253498759305391, "point_count": 24, "series_count": 4 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(pd_client_request_handle_requests_duration_seconds_bucket{type=\"tso\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "avg_get_tso_wait_p99_s", "id": "avg_get_tso_wait_p99_s", "metric_group_id": "avg_get_tso_wait_p99_s", "name": "avg_get_tso_wait_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(pd_client_request_handle_requests_duration_seconds_bucket{type=\"tso\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "ref": { "metric_group_id": "avg_get_tso_wait_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.0021630892810104376, "labels": { "instance": "db-tidb-4" }, "max": 0.0037411971830985935, "min": 0.0008532397295891845, "point_count": 6 }, { "avg": 0.0020566807611504434, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.0032681566068515433, "min": 0.0006615538674033161, "point_count": 6 }, { "avg": 0.0026661832696742425, "labels": { "instance": "db-tidb-82" }, "max": 0.003847016574585636, "min": 0.0010183061224489781, "point_count": 6 }, { "avg": 0.0026301412287029952, "labels": { "instance": "db-tidb-88" }, "max": 0.003924773060029278, "min": 0.00099726153808546, "point_count": 6 } ], "summary": { "avg": 0.0023790236351345297, "max": 0.003924773060029278, "min": 0.0006615538674033161, "point_count": 24, "series_count": 4 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(go_gc_pauses_seconds_bucket{component=\"tidb\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "avg_gc_stw_pause_p99_s", "id": "avg_gc_stw_pause_p99_s", "metric_group_id": "avg_gc_stw_pause_p99_s", "name": "avg_gc_stw_pause_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(go_gc_pauses_seconds_bucket{component=\"tidb\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m])))", "ref": { "metric_group_id": "avg_gc_stw_pause_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.03884541618054834, "labels": { "instance": "db-tidb-4" }, "max": 0.09818865663999995, "min": 0.010198712319999999, "point_count": 6 }, { "avg": 0.025480205653333327, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 0.10139729919999997, "min": 0.010282434559999998, "point_count": 6 }, { "avg": 0.010283749677437228, "labels": { "instance": "db-tidb-82" }, "max": 0.01029439488, "min": 0.010267057005714285, "point_count": 6 }, { "avg": 0.023696164636444455, "labels": { "instance": "db-tidb-88" }, "max": 0.09070182400000007, "min": 0.010278447786666664, "point_count": 6 } ], "summary": { "avg": 0.024576384036940836, "max": 0.10139729919999997, "min": 0.010198712319999999, "point_count": 24, "series_count": 4 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tikv_grpc_msg_duration_seconds_bucket{type=\"kv_get\"}[1m])))", "start": 1784602800, "step": "60" }, "group": "cluster_avg_tikv_grpc_request_handle_p99_s", "id": "cluster_avg_tikv_grpc_request_handle_p99_s", "metric_group_id": "cluster_avg_tikv_grpc_request_handle_p99_s", "name": "cluster_avg_tikv_grpc_request_handle_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tikv_grpc_msg_duration_seconds_bucket{type=\"kv_get\"}[1m])))", "ref": { "metric_group_id": "cluster_avg_tikv_grpc_request_handle_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.009666406412123482, "labels": { "instance": "db-tikv-0" }, "max": 0.012683954441913368, "min": 0.0022851343283582654, "point_count": 6 }, { "avg": 0.011036074644047123, "labels": { "instance": "db-tikv-1" }, "max": 0.015561650793650787, "min": 0.0025175873015873926, "point_count": 6 }, { "avg": 0.012054406526901344, "labels": { "instance": "db-tikv-10" }, "max": 0.017339405128205098, "min": 0.0027622988505746683, "point_count": 6 }, { "avg": 0.010055601894699387, "labels": { "instance": "db-tikv-11" }, "max": 0.012859524475524391, "min": 0.003821306930693108, "point_count": 6 }, { "avg": 0.009967316547546604, "labels": { "instance": "db-tikv-12" }, "max": 0.01530540112994338, "min": 0.002136347826086938, "point_count": 6 }, { "avg": 0.016009568708151494, "labels": { "instance": "db-tikv-13" }, "max": 0.022733421633554265, "min": 0.004966537634408555, "point_count": 6 }, { "avg": 0.014382103685490139, "labels": { "instance": "db-tikv-132" }, "max": 0.020551150837988884, "min": 0.00567250632911381, "point_count": 6 }, { "avg": 0.019821973105455058, "labels": { "instance": "db-tikv-133" }, "max": 0.025336195121951174, "min": 0.008226388059701514, "point_count": 6 }, { "avg": 0.01266280057540578, "labels": { "instance": "db-tikv-134" }, "max": 0.01966571751412434, "min": 0.00458514285714284, "point_count": 6 }, { "avg": 0.014734399911196372, "labels": { "instance": "db-tikv-135" }, "max": 0.020576755905511793, "min": 0.005100173913043543, "point_count": 6 }, { "avg": 0.015327482640694577, "labels": { "instance": "db-tikv-136" }, "max": 0.02155827450980381, "min": 0.004081777777777803, "point_count": 6 }, { "avg": 0.015518730011261923, "labels": { "instance": "db-tikv-137" }, "max": 0.02326105849582187, "min": 0.005327627906976766, "point_count": 6 }, { "avg": 0.02209547987567057, "labels": { "instance": "db-tikv-138" }, "max": 0.03387454205607454, "min": 0.008972943820224856, "point_count": 6 }, { "avg": 0.015651497210849016, "labels": { "instance": "db-tikv-139" }, "max": 0.021642691415313046, "min": 0.0037893333333332228, "point_count": 6 }, { "avg": 0.02043171247307712, "labels": { "instance": "db-tikv-14" }, "max": 0.034907193133047236, "min": 0.006134109090909282, "point_count": 6 }, { "avg": 0.020493475755329244, "labels": { "instance": "db-tikv-140" }, "max": 0.02878479693486573, "min": 0.009407319148936276, "point_count": 6 }, { "avg": 0.017849688267407043, "labels": { "instance": "db-tikv-141" }, "max": 0.023418250591016453, "min": 0.007022545454545273, "point_count": 6 }, { "avg": 0.01293814311623969, "labels": { "instance": "db-tikv-143" }, "max": 0.019683862068965302, "min": 0.001399963133640552, "point_count": 6 }, { "avg": 0.01742833503457353, "labels": { "instance": "db-tikv-144" }, "max": 0.022767150743099887, "min": 0.005968326530612279, "point_count": 6 }, { "avg": 0.011895081472205117, "labels": { "instance": "db-tikv-15" }, "max": 0.019808076009501144, "min": 0.0042642962962962175, "point_count": 6 }, { "avg": 0.011851905391431107, "labels": { "instance": "db-tikv-16" }, "max": 0.0168326852248396, "min": 0.004337032258064417, "point_count": 6 }, { "avg": 0.013653810777693473, "labels": { "instance": "db-tikv-17" }, "max": 0.02364316546762591, "min": 0.0017889156626505632, "point_count": 6 }, { "avg": 0.014997006695563498, "labels": { "instance": "db-tikv-18" }, "max": 0.022663710843373625, "min": 0.008007999999999925, "point_count": 6 }, { "avg": 0.012971209109486398, "labels": { "instance": "db-tikv-19" }, "max": 0.016779510791367032, "min": 0.009770666666666719, "point_count": 6 }, { "avg": 0.01698329291682626, "labels": { "instance": "db-tikv-2" }, "max": 0.02384596078431375, "min": 0.002933066666666582, "point_count": 6 }, { "avg": 0.008769965899017367, "labels": { "instance": "db-tikv-20" }, "max": 0.011995256784968699, "min": 0.003931182795698868, "point_count": 6 }, { "avg": 0.01001003572046174, "labels": { "instance": "db-tikv-21" }, "max": 0.01539610256410259, "min": 0.0029069999999999895, "point_count": 6 }, { "avg": 0.012331388502822822, "labels": { "instance": "db-tikv-22" }, "max": 0.018575741100323458, "min": 0.00269116049382712, "point_count": 6 }, { "avg": 0.00980253183906908, "labels": { "instance": "db-tikv-23" }, "max": 0.012668479999999947, "min": 0.002951058823529412, "point_count": 6 }, { "avg": 0.010523102694885258, "labels": { "instance": "db-tikv-24" }, "max": 0.01370880000000013, "min": 0.0019078918918918589, "point_count": 6 }, { "avg": 0.010851866572347671, "labels": { "instance": "db-tikv-25" }, "max": 0.014419767584097848, "min": 0.004946823529411772, "point_count": 6 }, { "avg": 0.015655998266684918, "labels": { "instance": "db-tikv-26" }, "max": 0.02265336986301359, "min": 0.004140873563218395, "point_count": 6 }, { "avg": 0.010632349867202082, "labels": { "instance": "db-tikv-27" }, "max": 0.015114061135370949, "min": 0.004429499999999978, "point_count": 6 }, { "avg": 0.011547950107039897, "labels": { "instance": "db-tikv-28" }, "max": 0.017130979472140553, "min": 0.003077000000000042, "point_count": 6 }, { "avg": 0.0173825651811888, "labels": { "instance": "db-tikv-29" }, "max": 0.02377381602373888, "min": 0.010056629213483218, "point_count": 6 }, { "avg": 0.014088710580084436, "labels": { "instance": "db-tikv-3" }, "max": 0.021202017271157204, "min": 0.005586360655737722, "point_count": 6 }, { "avg": 0.014568251648021606, "labels": { "instance": "db-tikv-30" }, "max": 0.02161690947368414, "min": 0.0014250899742930573, "point_count": 6 }, { "avg": 0.009508464639050179, "labels": { "instance": "db-tikv-31" }, "max": 0.013124694980695052, "min": 0.00433706666666663, "point_count": 6 }, { "avg": 0.011370476784961572, "labels": { "instance": "db-tikv-32" }, "max": 0.014696595936794643, "min": 0.00317812244897959, "point_count": 6 }, { "avg": 0.015791496105335482, "labels": { "instance": "db-tikv-33" }, "max": 0.02183554098360649, "min": 0.004239012345679128, "point_count": 6 }, { "avg": 0.011431434166103269, "labels": { "instance": "db-tikv-34" }, "max": 0.019728662721893348, "min": 0.002256000000000001, "point_count": 6 }, { "avg": 0.011040940233116065, "labels": { "instance": "db-tikv-35" }, "max": 0.01640202816901422, "min": 0.0059549090909091365, "point_count": 6 }, { "avg": 0.01826685716674446, "labels": { "instance": "db-tikv-36" }, "max": 0.022223360000000122, "min": 0.011618656126482229, "point_count": 6 }, { "avg": 0.01202336592979638, "labels": { "instance": "db-tikv-37" }, "max": 0.018571974193548446, "min": 0.0027637894736842767, "point_count": 6 }, { "avg": 0.011878696766441571, "labels": { "instance": "db-tikv-38" }, "max": 0.017373658536585086, "min": 0.0035001518987342645, "point_count": 6 }, { "avg": 0.009128849032717065, "labels": { "instance": "db-tikv-39" }, "max": 0.013132350877192988, "min": 0.002193355932203412, "point_count": 6 }, { "avg": 0.017769647295577024, "labels": { "instance": "db-tikv-4" }, "max": 0.023108511013215816, "min": 0.0045321904761904275, "point_count": 6 }, { "avg": 0.012874759375292038, "labels": { "instance": "db-tikv-40" }, "max": 0.01805255890410966, "min": 0.005286657718120917, "point_count": 6 }, { "avg": 0.01095995526348241, "labels": { "instance": "db-tikv-41" }, "max": 0.016883056179775157, "min": 0.0021328695652174288, "point_count": 6 }, { "avg": 0.01329680292409082, "labels": { "instance": "db-tikv-42" }, "max": 0.02052871391076109, "min": 0.003615051851851846, "point_count": 6 } ], "summary": { "avg": 0.01318817764422275, "max": 0.034907193133047236, "min": 0.0010399407407407327, "point_count": 630, "series_count": 105 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(pd_server_handle_tso_duration_seconds_bucket[1m])))", "start": 1784602800, "step": "60" }, "group": "cluster_avg_pd_tso_request_handle_p99_s", "id": "cluster_avg_pd_tso_request_handle_p99_s", "metric_group_id": "cluster_avg_pd_tso_request_handle_p99_s", "name": "cluster_avg_pd_tso_request_handle_p99_s", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(pd_server_handle_tso_duration_seconds_bucket[1m])))", "ref": { "metric_group_id": "cluster_avg_pd_tso_request_handle_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.0004952272491124351, "labels": { "instance": "db-pd-0" }, "max": 0.0004954715726226751, "min": 0.0004950074856158754, "point_count": 6 } ], "summary": { "avg": 0.0004952272491124351, "max": 0.0004954715726226751, "min": 0.0004950074856158754, "point_count": 6, "series_count": 1 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" } ], "panic_signal_artifact_present": false, "query_evidence": { "slow_query": [], "topsql": [] }, "query_or_metric_channel_observed": true, "slow_query_top_digest": "", "ticket_context_channel_observed": false, "topsql_collection_error_recorded": false }, "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "output": { "analyze_primary_culprit_asserted": false, "claims_panic_not_confirmable": false, "diagnosis_cpu_hotspot_asserted": false, "diagnosis_kill_query_chain_asserted": false, "diagnosis_memory_tracker_panic_asserted": false, "diagnosis_plan_stats_issue_asserted": false, "diagnosis_single_instance_panic_restart_asserted": false, "fake_alarm_primary_asserted": false, "focuses_on_missing_index": false, "mentions_cpu_saturation": false, "mentions_est_act_divergence": false, "mentions_idle_transaction": false, "mentions_intermediate_result_explosion": false, "mentions_kill_query": false, "mentions_memory_tracker_consume": false, "mentions_p99_latency_spike": false, "mentions_rollback_cleanup": false, "mentions_statistics_uninitialized": false, "mentions_v8_5_2": false, "mentions_v8_5_3_or_fixed_release": false, "mentions_without_fix": false, "missing_index_primary_root_cause_asserted": false, "puller_or_source_side_primary_root_cause_asserted": false, "query_only_primary_root_cause_asserted": false, "wide_scan_primary_root_cause_asserted": false }, "routing": { "analysis_event_items_present": false, "analysis_has_key_evidence": false, "analysis_has_supporting_evidence": false, "analysis_items_shape_valid": false, "analysis_log_items_present": false, "analysis_log_or_event_channel_resolvable": true, "analysis_metric_refs_required": false, "analysis_metric_refs_resolvable": true, "analysis_patch_present": false, "analysis_patch_valid_json": false, "analysis_query_refs_required": false, "analysis_query_refs_resolvable": true, "classification_contract_valid": false, "diagnosis_analyst_contract_present": false, "fault_classification_contract_valid": false, "primary_fault_class_component_restart_or_panic": false, "primary_fault_class_resource_control_or_capacity": false, "primary_fault_class_service_unavailability_or_worker_failure": false, "primary_fault_class_sql_plan_or_query": false, "primary_fault_class_storage_or_infra_io": false, "primary_fault_class_tidb_cpu_gc_or_memory": false, "primary_fault_class_tikv_read_hotspot": false, "primary_fault_class_unknown_insufficient_evidence": false, "selected_diagnosis_skills_present": false, "signal_tags_contract_valid": false }, "runtime_context_present": true, "window": { "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_end_ts": 1784603100, "expected_start_ts": 1784602800, "matched_allowed_window": true }, "workflow": { "architecture_context_loaded": false, "collect_evidence_invoked": false, "diagnosis_run_initialized": true, "direct_conclusion_by_investigator": false, "evidence_collection_completed": true, "evidence_collection_started": false, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": false, "premise_verification_recorded": false, "summary_read_completed": false, "targeted_panic_log_query_completed": false } }, "id": "evaljudge-a9a1a98af6df49e0be472942e70c439a", "invalid_subtype": null, "judged_at": "2026-07-22T01:58:35.755234+00:00", "judgment_verdict": "pass", "packet": { "artifact_resolution": { "candidate_run_dirs": [ "evidences" ], "manifest_path_mismatch": false, "primary_failure_code": null, "resolution_mode": "workspace_evidence_root", "scanned_scopes": [ { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/data/workspaces/ws-eval-1784685468326-179011a2", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "status": "resolved" }, "contract": { "checks": [ { "description": "Actual diagnosis cluster scope matches the expected cluster id.", "id": "cluster_scope_match", "match": "all_of", "passed": true, "required": true, "rules": [ { "allowed": [], "matched": true, "matched_keys": [ "cluster_scope_match" ], "matcher": "bool_true", "path": "cluster_scope_match", "source": "trace_fact", "value": "" } ], "snippet": "matched trace facts: cluster_scope_match" } ], "status": "pass" }, "critical_evidence": { "checks": [ { "artifact_paths": [ "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/workspace_evidence_report.json" ], "description": "Evidence includes the TiDB P99 latency metric family for this request.", "earned_score": 4, "id": "latency_metric_present", "match": "any_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "tidb_server_handle_query_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "y_p99_latency\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_server_handle_query_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 228, \"min\": 0.0167365811", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "tidb_server_handle_query_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "y_p99_latency\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_server_handle_query_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 228, \"min\": 0.0167365811", "source": "artifact_json" } ], "snippet": "y_p99_latency\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_server_handle_query_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 228, \"min\": 0.0167365811" }, { "artifact_paths": [ "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json" ], "description": "Evidence includes the five node-level breakdown metric families and the two cluster-level service-side metric families needed for this request.", "earned_score": 6, "id": "breakdown_metrics_present", "match": "all_of", "max_score": 6, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "tidb_session_compile_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "n_build_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket{instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}[1m])))\", \"unit\": \"", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "tidb_distsql_handle_query_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "ecution_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_distsql_handle_query_duration_seconds_bucket{instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}[1m])))\", \"unit\": \"", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "tidb_tikvclient_request_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "request_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_tikvclient_request_seconds_bucket{type=\\\"Get\\\",instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}[1m]))", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "type=\"Get\"", "matcher": "json_text_contains_any", "snippet": "antile(0.99, sum by (le, instance) (rate(tidb_tikvclient_request_seconds_bucket{type=\"Get\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m]))) seconds 24 0.", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "pd_client_request_handle_requests_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "so_wait_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(pd_client_request_handle_requests_duration_seconds_bucket{type=\\\"tso\\\",instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}[1m]))", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "type=\"tso\"", "matcher": "json_text_contains_any", "snippet": "(le, instance) (rate(pd_client_request_handle_requests_duration_seconds_bucket{type=\"tso\",instance=~\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\"}[1m]))) seconds 24 0.", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "go_gc_pauses_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "w_pause_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(go_gc_pauses_seconds_bucket{component=\\\"tidb\\\",instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "tikv_grpc_msg_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "_handle_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tikv_grpc_msg_duration_seconds_bucket{type=\\\"kv_get\\\"}[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 630, \"m", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "type=\"kv_get\"", "matcher": "json_text_contains_any", "snippet": "uantile(0.99, sum by (le, instance) (rate(tikv_grpc_msg_duration_seconds_bucket{type=\"kv_get\"}[1m]))) seconds 630 0.0010399407407407327 0.034907193133047236 0.01318817764422", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "pd_server_handle_tso_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "_handle_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(pd_server_handle_tso_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 6, \"min\": 0.000495007485", "source": "artifact_json" } ], "snippet": "n_build_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket{instance=~\\\"^(db-tidb-88|db-tidb-4|db-tidb-82)($|[-.:].*)\\\"}[1m])))\", \"unit\": \"" }, { "artifact_paths": [ "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json" ], "description": "Metric evidence includes at least one non-empty time-series payload instead of an all-empty metrics bundle.", "earned_score": 6, "id": "latency_metric_series_nonempty", "match": "all_of", "max_score": 6, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": null, "matcher": "json_values_nonempty", "snippet": "[[1784602800, \"0.019616509960159838\"], [1784602860, \"0.05240516377649357\"], [1784602920, \"0.06216225913621291\"], [1784602980, \"0.060824412111679056\"], [1784603040, \"0.05791496327387218\"], [1784603100, \"0.053634149801794734\"]]", "source": "artifact_json" } ], "snippet": "[[1784602800, \"0.019616509960159838\"], [1784602860, \"0.05240516377649357\"], [1784602920, \"0.06216225913621291\"], [1784602980, \"0.060824412111679056\"], [1784603040, \"0.05791496327387218\"], [1784603100, \"0.053634149801794734\"]]" }, { "artifact_paths": [], "description": "Output JSON cluster_id matches the runtime reference.", "earned_score": 4, "id": "output_cluster_id_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"10989049060142230334\"", "source": "output_json" } ], "snippet": "\"10989049060142230334\"" }, { "artifact_paths": [], "description": "Output JSON window.start matches the runtime reference.", "earned_score": 4, "id": "output_window_start_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:00:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:00:00Z\"" }, { "artifact_paths": [], "description": "Output JSON window.end matches the runtime reference.", "earned_score": 4, "id": "output_window_end_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:05:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:05:00Z\"" }, { "artifact_paths": [], "description": "Output JSON evidence_sufficient matches the runtime reference.", "earned_score": 4, "id": "evidence_sufficient_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "true", "source": "output_json" } ], "snippet": "true" }, { "artifact_paths": [], "description": "Output JSON cluster_avg_tikv_grpc_request_handle_p99_s matches the runtime reference.", "earned_score": 4, "id": "cluster_avg_tikv_grpc_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "0.013188", "source": "output_json" } ], "snippet": "0.013188" }, { "artifact_paths": [], "description": "Output JSON cluster_avg_pd_tso_request_handle_p99_s matches the runtime reference.", "earned_score": 4, "id": "cluster_avg_pd_tso_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "0.000495", "source": "output_json" } ], "snippet": "0.000495" }, { "artifact_paths": [], "description": "Output JSON ranked TiDB nodes and their P99 breakdown match the runtime reference ordering and values.", "earned_score": 10, "id": "top_nodes_match_runtime_reference", "match": "all_of", "max_score": 10, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_array_matches_reference", "snippet": "[{\"node\": \"db-tidb-88\", \"avg_p99_latency_s\": 0.056485, \"avg_plan_build_p99_s\": 0.012286, \"avg_distributed_execution_p99_s\": 0.050407, \"avg_kv_request_p99_s\": 0.013411, \"avg_get_tso_wait_p99_s\": 0.00263, \"avg_gc_stw_pause_p99_s\": 0.023696}, ", "source": "output_json" } ], "snippet": "[{\"node\": \"db-tidb-88\", \"avg_p99_latency_s\": 0.056485, \"avg_plan_build_p99_s\": 0.012286, \"avg_distributed_execution_p99_s\": 0.050407, \"avg_kv_request_p99_s\": 0.013411, \"avg_get_tso_wait_p99_s\": 0.00263, \"avg_gc_stw_pause_p99_s\": 0.023696}, " } ], "max_score": 80, "raw_max_score": 50, "raw_score": 50, "score": 80, "status": "pass" }, "critical_evidence_verdict": "pass", "diagnosis": { "checks": [ { "description": "identify_known_bug_63956", "id": "identify_known_bug_63956", "passed": false, "snippet": null }, { "description": "identify_kill_query_idle_txn_chain", "id": "identify_kill_query_idle_txn_chain", "passed": false, "snippet": null }, { "description": "identify_version_without_fix", "id": "identify_version_without_fix", "passed": false, "snippet": null }, { "description": "recommend_fixed_version_upgrade", "id": "recommend_fixed_version_upgrade", "passed": false, "snippet": null } ], "hard_gate_passed": true, "max_score": 0, "raw_score": 0, "score": 0, "semantic_shadow": { "available": false, "checks": [], "packet_path": "/data/eval_audits/evalrun-6d3259e4b7624c89b6ac9c20e86209b0/evalcase-c3a0bad379324895b0b63f5aacb5f33f/semantic_packet_v1.json", "reason": "semantic_packet_missing", "status": "not_available", "summary": { "disagreement_flags": [], "shadow_max_score": 0, "shadow_score": 0 } }, "status": "pass" }, "evidence_collection": { "checks": [ { "description": "Workspace diagnosis report is present and readable.", "earned_score": 2, "id": "required_report_present", "match": "all_of", "max_score": 2, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched collection facts: diagnosis_report_present" }, { "description": "Query or metric evidence is observed for this ad-hoc request.", "earned_score": 2, "id": "query_or_metric_channel_observed", "match": "all_of", "max_score": 2, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched collection facts: query_or_metric" }, { "description": "If an events collection query is attempted, an events output file is persisted even when the result set is empty.", "earned_score": 2, "id": "attempted_events_collection_persisted", "match": "all_of", "max_score": 2, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "events_attempted_implies_artifact_present" ], "matcher": "bool_true", "path": "events_attempted_implies_artifact_present", "paths": [], "source": "evidence_fact", "threshold": null } ], "snippet": "matched collection facts: events_attempted_implies_artifact_present" } ], "max_score": 5, "raw_max_score": 6, "raw_score": 6, "score": 5, "status": "pass" }, "evidence_collection_verdict": "pass", "evidence_routing": { "checks": [ { "description": "Analysis patch is only required to be valid when it exists.", "earned_score": 0, "id": "analysis_patch_valid_when_present", "match": "any_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "analysis_patch_present" ], "matcher": "bool_false", "path": "analysis_patch_present", "paths": [], "source": "routing_fact" }, { "matched": false, "matched_keys": [], "matcher": "bool_true", "path": "analysis_patch_valid_json", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" } ], "max_score": 0, "raw_max_score": 0, "raw_score": 0, "score": 0, "status": "pass" }, "evidence_routing_verdict": "pass", "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "execution_contract_verdict": "pass", "ground_truth_root_cause": "Correctly answering this case requires collecting TiDB P99 latency metrics for the exact cluster and resolved window, then ranking TiDB pods by their average 1-minute P99 latency over the full 5-minute window. After identifying the top 3 TiDB pods, the answer must also provide the same-window average P99 breakdown for plan building, distributed execution, TiDB-client-side TiKV request latency, TiDB-client-side PD TSO request latency, and Go GC pause latency on those same nodes. In addition, it must provide two cluster-level averages computed over all relevant server nodes: TiKV-side gRPC request handle latency and PD-side TSO request handle latency. If the primary latency metric is absent, only yields empty series, or any required node-level or cluster-level signal is missing, evidence must be marked insufficient instead of fabricating a ranking.", "overall_verdict": "pass", "quality_verdict": "pass", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 100, "hard_gate_passed": true, "normalized_total_score": 100, "passing_hard_gate_score_floor": 70, "raw_total_score": 85, "total_max_score": 85 }, "strategy": "deterministic_trace_heavy_v1", "workflow": { "checks": [ { "description": "Final answer is emitted for the ad-hoc query.", "earned_score": 0, "id": "final_answer_emitted", "match": "all_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "bool_true", "path": "final_answer_emitted", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "earned_score": 0, "id": "collect_evidence_not_used", "match": "all_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_invoked" ], "matcher": "bool_false", "path": "collect_evidence_invoked", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: collect_evidence_invoked" } ], "max_score": 0, "raw_max_score": 0, "raw_score": 0, "score": 0, "status": "pass" }, "workflow_verdict": "pass" }, "passed_checks": 0, "primary_failure_code": null, "score": 100, "total_checks": 0 }