{ "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-9ca3e149083040cfa6e5a554382fc030/evalcase-953d68b097254344af2acf6e28f4724e", "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-1784628628244-6b238c69", "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-cpu-overload-nodes-and-log-patterns-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": true, "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-953d68b097254344af2acf6e28f4724e", "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-9ca3e149083040cfa6e5a554382fc030/evalcase-953d68b097254344af2acf6e28f4724e", "source_scope": "audit_dir", "summary_txt_path": "", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "top-cpu-overload-nodes-and-log-patterns-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": [ "output_cluster_id_matches_reference", "output_window_start_matches_reference", "output_window_end_matches_reference", "evidence_sufficient_matches_reference", "ranked_nodes_identity_matches_reference", "ranked_nodes_numeric_fields_match_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": true, "logs_dir_present": false, "memory_tracker_panic_present": false, "metric_evidence": [ { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tidb\"}[1m]))", "start": 1784602800, "step": "60" }, "group": "tidb_cpu_rate", "id": "tidb_cpu_rate", "metric_group_id": "tidb_cpu_rate", "name": "tidb_cpu_rate", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tidb\"}[1m]))", "ref": { "metric_group_id": "tidb_cpu_rate", "type": "metric" }, "series_summaries": [ { "avg": 13.874500000000829, "labels": { "instance": "db-tidb-0" }, "max": 19.920000000049672, "min": 4.718499999990066, "point_count": 6 }, { "avg": 20.994944444443615, "labels": { "instance": "db-tidb-0-ac-2006050899364941824" }, "max": 23.81566666662693, "min": 12.465833333258827, "point_count": 6 }, { "avg": 12.619555555573768, "labels": { "instance": "db-tidb-1" }, "max": 17.119833333293595, "min": 4.303333333383004, "point_count": 6 }, { "avg": 21.570222222225535, "labels": { "instance": "db-tidb-1-ac-2006050899364941824" }, "max": 24.921499999985098, "min": 13.51150000008444, "point_count": 6 }, { "avg": 21.85780555556218, "labels": { "instance": "db-tidb-10-ac-2006050899364941824" }, "max": 24.80666666676601, "min": 12.954166666666667, "point_count": 6 }, { "avg": 20.988388888889716, "labels": { "instance": "db-tidb-11-ac-2006050899364941824" }, "max": 25.0125, "min": 11.277999999995034, "point_count": 6 }, { "avg": 20.814749999985928, "labels": { "instance": "db-tidb-12-ac-2006050899364941824" }, "max": 24.525500000019868, "min": 10.679499999930462, "point_count": 6 }, { "avg": 19.209083333342438, "labels": { "instance": "db-tidb-13-ac-2006050899364941824" }, "max": 21.95633333325386, "min": 10.838666666671633, "point_count": 6 }, { "avg": 20.3830833333234, "labels": { "instance": "db-tidb-14-ac-2006050899364941824" }, "max": 23.2928333333383, "min": 11.79249999995033, "point_count": 6 }, { "avg": 19.25108333333499, "labels": { "instance": "db-tidb-15-ac-2006050899364941824" }, "max": 22.490833333383005, "min": 11.250666666651766, "point_count": 6 }, { "avg": 20.985944444458518, "labels": { "instance": "db-tidb-16-ac-2006050899364941824" }, "max": 27.193000000094376, "min": 11.700666666651765, "point_count": 6 }, { "avg": 21.923166666655906, "labels": { "instance": "db-tidb-17-ac-2006050899364941824" }, "max": 25.045000000049672, "min": 13.12283333328863, "point_count": 6 }, { "avg": 20.80649999998924, "labels": { "instance": "db-tidb-19-ac-2006050899364941824" }, "max": 23.7446666666617, "min": 12.857999999945362, "point_count": 6 }, { "avg": 16.018916666673288, "labels": { "instance": "db-tidb-2" }, "max": 22.285500000044703, "min": 5.03650000008444, "point_count": 6 }, { "avg": 21.441472222221392, "labels": { "instance": "db-tidb-2-ac-2006050899364941824" }, "max": 24.989000000059605, "min": 10.8875, "point_count": 6 }, { "avg": 21.41688888888392, "labels": { "instance": "db-tidb-21-ac-2006050899364941824" }, "max": 24.210166666656733, "min": 12.301000000039737, "point_count": 6 }, { "avg": 14.810472222231327, "labels": { "instance": "db-tidb-3" }, "max": 19.996333333353203, "min": 4.379666666686535, "point_count": 6 }, { "avg": 25.46447222220401, "labels": { "instance": "db-tidb-3-ac-2006050899364941824" }, "max": 30.15849999996523, "min": 14.260999999940395, "point_count": 6 }, { "avg": 18.18191666667246, "labels": { "instance": "db-tidb-4" }, "max": 23.904833333318432, "min": 6.307333333417773, "point_count": 6 }, { "avg": 19.09883333332837, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 23.31116666669647, "min": 11.316999999930461, "point_count": 6 }, { "avg": 15.67675000000745, "labels": { "instance": "db-tidb-42" }, "max": 20.008166666701435, "min": 5.639833333343267, "point_count": 6 }, { "avg": 15.316805555547276, "labels": { "instance": "db-tidb-43" }, "max": 20.864499999955296, "min": 4.692499999950329, "point_count": 6 }, { "avg": 13.657944444442789, "labels": { "instance": "db-tidb-5" }, "max": 17.515333333363134, "min": 4.828500000014901, "point_count": 6 }, { "avg": 19.52386111110035, "labels": { "instance": "db-tidb-5-ac-2006050899364941824" }, "max": 23.56466666671137, "min": 10.601333333303531, "point_count": 6 }, { "avg": 21.768999999989237, "labels": { "instance": "db-tidb-6-ac-2006050899364941824" }, "max": 25.45233333334327, "min": 11.664666666587193, "point_count": 6 }, { "avg": 15.515611111124358, "labels": { "instance": "db-tidb-7" }, "max": 18.9838333333532, "min": 4.446166666721305, "point_count": 6 }, { "avg": 21.141444444428718, "labels": { "instance": "db-tidb-7-ac-2006050899364941824" }, "max": 24.20983333326876, "min": 12.630333333338301, "point_count": 6 }, { "avg": 11.686361111121045, "labels": { "instance": "db-tidb-72" }, "max": 14.352999999995033, "min": 3.587166666736205, "point_count": 6 }, { "avg": 12.563722222236295, "labels": { "instance": "db-tidb-73" }, "max": 15.975500000019869, "min": 4.407666666681568, "point_count": 6 }, { "avg": 14.190888888885576, "labels": { "instance": "db-tidb-74" }, "max": 20.552833333363136, "min": 4.15316666662693, "point_count": 6 }, { "avg": 14.580194444436993, "labels": { "instance": "db-tidb-75" }, "max": 19.40966666676104, "min": 4.744333333273729, "point_count": 6 }, { "avg": 19.790888888906274, "labels": { "instance": "db-tidb-8-ac-2006050899364941824" }, "max": 22.864166666691503, "min": 12.82533333338797, "point_count": 6 }, { "avg": 17.5112777777844, "labels": { "instance": "db-tidb-82" }, "max": 22.57400000008444, "min": 4.37400000008444, "point_count": 6 }, { "avg": 13.70249999999586, "labels": { "instance": "db-tidb-83" }, "max": 17.425666666651765, "min": 5.290166666731238, "point_count": 6 }, { "avg": 15.747249999994205, "labels": { "instance": "db-tidb-84" }, "max": 23.763166666651767, "min": 4.658166666701436, "point_count": 6 }, { "avg": 16.53833333334575, "labels": { "instance": "db-tidb-87" }, "max": 22.967333333318432, "min": 3.5728333334128064, "point_count": 6 }, { "avg": 16.016638888873988, "labels": { "instance": "db-tidb-88" }, "max": 25.16733333331843, "min": 5.267999999970198, "point_count": 6 }, { "avg": 20.58125, "labels": { "instance": "db-tidb-9-ac-2006050899364941824" }, "max": 24.079999999950328, "min": 11.854500000054637, "point_count": 6 } ], "summary": { "avg": 18.084808479532143, "max": 30.15849999996523, "min": 3.5728333334128064, "point_count": 228, "series_count": 38 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "max by (pod, instance) (tidb_server_maxprocs)", "start": 1784602800, "step": "60" }, "group": "tidb_cpu_quota", "id": "tidb_cpu_quota", "metric_group_id": "tidb_cpu_quota", "name": "tidb_cpu_quota", "promql": "max by (pod, instance) (tidb_server_maxprocs)", "ref": { "metric_group_id": "tidb_cpu_quota", "type": "metric" }, "series_summaries": [ { "avg": 64.0, "labels": { "instance": "db-tidb-0" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-0-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-1" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-1-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-10-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-11-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-12-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-13-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-14-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-15-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-16-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-17-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-19-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-2" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-2-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-21-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-3" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-3-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-4" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-4-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-42" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-43" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-5" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-5-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-6-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-7" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-7-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-72" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-73" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-74" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-75" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-8-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-82" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-83" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-84" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-87" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-88" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-tidb-9-ac-2006050899364941824" }, "max": 64.0, "min": 64.0, "point_count": 6 } ], "summary": { "avg": 64.0, "max": 64.0, "min": 64.0, "point_count": 228, "series_count": 38 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tikv\"}[1m]))", "start": 1784602800, "step": "60" }, "group": "tikv_cpu_rate", "id": "tikv_cpu_rate", "metric_group_id": "tikv_cpu_rate", "name": "tikv_cpu_rate", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tikv\"}[1m]))", "ref": { "metric_group_id": "tikv_cpu_rate", "type": "metric" }, "series_summaries": [ { "avg": 15.716666666666667, "labels": { "instance": "db-tikv-0" }, "max": 19.883333333333333, "min": 6.45, "point_count": 6 }, { "avg": 16.108333333333334, "labels": { "instance": "db-tikv-1" }, "max": 19.766666666666666, "min": 6.416666666666667, "point_count": 6 }, { "avg": 16.28611111111111, "labels": { "instance": "db-tikv-10" }, "max": 20.2, "min": 7.216666666666667, "point_count": 6 }, { "avg": 16.030555555555555, "labels": { "instance": "db-tikv-11" }, "max": 19.433333333333334, "min": 6.666666666666667, "point_count": 6 }, { "avg": 13.941666666666668, "labels": { "instance": "db-tikv-12" }, "max": 17.2, "min": 6.033333333333333, "point_count": 6 }, { "avg": 15.75, "labels": { "instance": "db-tikv-13" }, "max": 19.2, "min": 6.716666666666667, "point_count": 6 }, { "avg": 15.194444444444445, "labels": { "instance": "db-tikv-132" }, "max": 17.866666666666667, "min": 6.95, "point_count": 6 }, { "avg": 15.736111111111112, "labels": { "instance": "db-tikv-133" }, "max": 19.6, "min": 6.633333333333334, "point_count": 6 }, { "avg": 14.830555555555556, "labels": { "instance": "db-tikv-134" }, "max": 17.966666666666665, "min": 6.5, "point_count": 6 }, { "avg": 15.938888888888888, "labels": { "instance": "db-tikv-135" }, "max": 20.083333333333332, "min": 6.683333333333334, "point_count": 6 }, { "avg": 15.722222222222221, "labels": { "instance": "db-tikv-136" }, "max": 19.083333333333332, "min": 6.466666666666667, "point_count": 6 }, { "avg": 15.174999999999999, "labels": { "instance": "db-tikv-137" }, "max": 17.9, "min": 6.833333333333333, "point_count": 6 }, { "avg": 17.152777777777775, "labels": { "instance": "db-tikv-138" }, "max": 20.666666666666668, "min": 6.816666666666666, "point_count": 6 }, { "avg": 15.625, "labels": { "instance": "db-tikv-139" }, "max": 19.1, "min": 6.616666666666666, "point_count": 6 }, { "avg": 16.841666666666665, "labels": { "instance": "db-tikv-14" }, "max": 21.633333333333333, "min": 7.366666666666666, "point_count": 6 }, { "avg": 15.955555555555556, "labels": { "instance": "db-tikv-140" }, "max": 19.016666666666666, "min": 7.0, "point_count": 6 }, { "avg": 15.680555555555555, "labels": { "instance": "db-tikv-141" }, "max": 20.05, "min": 6.5, "point_count": 6 }, { "avg": 14.972222222222221, "labels": { "instance": "db-tikv-143" }, "max": 19.516666666666666, "min": 6.116666666666666, "point_count": 6 }, { "avg": 15.213888888888889, "labels": { "instance": "db-tikv-144" }, "max": 18.966666666666665, "min": 6.166666666666667, "point_count": 6 }, { "avg": 15.113888888888889, "labels": { "instance": "db-tikv-15" }, "max": 18.75, "min": 5.833333333333333, "point_count": 6 }, { "avg": 15.283333333333333, "labels": { "instance": "db-tikv-16" }, "max": 18.266666666666666, "min": 6.666666666666667, "point_count": 6 }, { "avg": 16.008333333333333, "labels": { "instance": "db-tikv-17" }, "max": 21.166666666666668, "min": 6.283333333333333, "point_count": 6 }, { "avg": 16.083333333333332, "labels": { "instance": "db-tikv-18" }, "max": 20.0, "min": 6.966666666666667, "point_count": 6 }, { "avg": 15.866666666666667, "labels": { "instance": "db-tikv-19" }, "max": 19.566666666666666, "min": 8.066666666666666, "point_count": 6 }, { "avg": 15.838888888888889, "labels": { "instance": "db-tikv-2" }, "max": 18.95, "min": 5.916666666666667, "point_count": 6 }, { "avg": 14.908333333333333, "labels": { "instance": "db-tikv-20" }, "max": 18.866666666666667, "min": 6.433333333333334, "point_count": 6 }, { "avg": 14.71111111111111, "labels": { "instance": "db-tikv-21" }, "max": 18.533333333333335, "min": 6.6, "point_count": 6 }, { "avg": 15.341666666666667, "labels": { "instance": "db-tikv-22" }, "max": 19.133333333333333, "min": 6.766666666666667, "point_count": 6 }, { "avg": 14.688888888888888, "labels": { "instance": "db-tikv-23" }, "max": 17.866666666666667, "min": 6.783333333333333, "point_count": 6 }, { "avg": 15.622222222222222, "labels": { "instance": "db-tikv-24" }, "max": 19.1, "min": 6.966666666666667, "point_count": 6 }, { "avg": 14.177777777777777, "labels": { "instance": "db-tikv-25" }, "max": 17.383333333333333, "min": 6.216666666666667, "point_count": 6 }, { "avg": 16.77777777777778, "labels": { "instance": "db-tikv-26" }, "max": 20.533333333333335, "min": 7.233333333333333, "point_count": 6 }, { "avg": 14.97777777777778, "labels": { "instance": "db-tikv-27" }, "max": 18.633333333333333, "min": 6.25, "point_count": 6 }, { "avg": 15.294444444444444, "labels": { "instance": "db-tikv-28" }, "max": 18.45, "min": 6.4, "point_count": 6 }, { "avg": 15.622222222222222, "labels": { "instance": "db-tikv-29" }, "max": 19.333333333333332, "min": 6.9, "point_count": 6 }, { "avg": 15.78888888888889, "labels": { "instance": "db-tikv-3" }, "max": 19.616666666666667, "min": 6.9, "point_count": 6 }, { "avg": 17.51666666666667, "labels": { "instance": "db-tikv-30" }, "max": 21.166666666666668, "min": 7.05, "point_count": 6 }, { "avg": 15.191666666666665, "labels": { "instance": "db-tikv-31" }, "max": 19.333333333333332, "min": 6.183333333333334, "point_count": 6 }, { "avg": 15.758333333333333, "labels": { "instance": "db-tikv-32" }, "max": 19.2, "min": 6.716666666666667, "point_count": 6 }, { "avg": 14.880555555555555, "labels": { "instance": "db-tikv-33" }, "max": 18.766666666666666, "min": 6.516666666666667, "point_count": 6 }, { "avg": 15.497222222222222, "labels": { "instance": "db-tikv-34" }, "max": 18.9, "min": 6.0, "point_count": 6 }, { "avg": 15.708333333333334, "labels": { "instance": "db-tikv-35" }, "max": 19.083333333333332, "min": 7.4, "point_count": 6 }, { "avg": 15.883333333333333, "labels": { "instance": "db-tikv-36" }, "max": 19.366666666666667, "min": 7.1, "point_count": 6 }, { "avg": 15.136111111111111, "labels": { "instance": "db-tikv-37" }, "max": 19.083333333333332, "min": 6.15, "point_count": 6 }, { "avg": 16.336111111111112, "labels": { "instance": "db-tikv-38" }, "max": 19.9, "min": 6.733333333333333, "point_count": 6 }, { "avg": 14.85277777777778, "labels": { "instance": "db-tikv-39" }, "max": 18.683333333333334, "min": 6.216666666666667, "point_count": 6 }, { "avg": 16.633333333333333, "labels": { "instance": "db-tikv-4" }, "max": 20.616666666666667, "min": 7.016666666666667, "point_count": 6 }, { "avg": 15.269444444444444, "labels": { "instance": "db-tikv-40" }, "max": 18.45, "min": 6.65, "point_count": 6 }, { "avg": 15.53888888888889, "labels": { "instance": "db-tikv-41" }, "max": 19.0, "min": 6.633333333333334, "point_count": 6 }, { "avg": 15.558333333333332, "labels": { "instance": "db-tikv-42" }, "max": 19.383333333333333, "min": 6.516666666666667, "point_count": 6 } ], "summary": { "avg": 15.503280423280424, "max": 21.8, "min": 5.816666666666666, "point_count": 630, "series_count": 105 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "max by (pod, instance) (tikv_server_cpu_cores_quota)", "start": 1784602800, "step": "60" }, "group": "tikv_cpu_quota", "id": "tikv_cpu_quota", "metric_group_id": "tikv_cpu_quota", "name": "tikv_cpu_quota", "promql": "max by (pod, instance) (tikv_server_cpu_cores_quota)", "ref": { "metric_group_id": "tikv_cpu_quota", "type": "metric" }, "series_summaries": [ { "avg": 32.0, "labels": { "instance": "db-tikv-0" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-1" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-10" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-11" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-12" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-13" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-132" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-133" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-134" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-135" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-136" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-137" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-138" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-139" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-14" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-140" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-141" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-143" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-144" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-15" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-16" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-17" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-18" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-19" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-2" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-20" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-21" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-22" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-23" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-24" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-25" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-26" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-27" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-28" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-29" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-3" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-30" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-31" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-32" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-33" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-34" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-35" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-36" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-37" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-38" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-39" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-4" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-40" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-41" }, "max": 32.0, "min": 32.0, "point_count": 6 }, { "avg": 32.0, "labels": { "instance": "db-tikv-42" }, "max": 32.0, "min": 32.0, "point_count": 6 } ], "summary": { "avg": 32.0, "max": 32.0, "min": 32.0, "point_count": 630, "series_count": 105 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"pd\"}[1m]))", "start": 1784602800, "step": "60" }, "group": "pd_cpu_rate", "id": "pd_cpu_rate", "metric_group_id": "pd_cpu_rate", "name": "pd_cpu_rate", "promql": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"pd\"}[1m]))", "ref": { "metric_group_id": "pd_cpu_rate", "type": "metric" }, "series_summaries": [ { "avg": 12.7705833333234, "labels": { "instance": "db-pd-0" }, "max": 17.355333333214123, "min": 8.414833333094915, "point_count": 6 }, { "avg": 3.3281944444506535, "labels": { "instance": "db-pd-1" }, "max": 4.422999999982616, "min": 1.9480000000447035, "point_count": 6 }, { "avg": 3.1558888888814383, "labels": { "instance": "db-pd-2" }, "max": 4.046166666721304, "min": 1.7928333333383004, "point_count": 6 } ], "summary": { "avg": 6.418222222218497, "max": 17.355333333214123, "min": 1.7928333333383004, "point_count": 18, "series_count": 3 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "max by (pod, instance) (pd_service_maxprocs)", "start": 1784602800, "step": "60" }, "group": "pd_cpu_quota", "id": "pd_cpu_quota", "metric_group_id": "pd_cpu_quota", "name": "pd_cpu_quota", "promql": "max by (pod, instance) (pd_service_maxprocs)", "ref": { "metric_group_id": "pd_cpu_quota", "type": "metric" }, "series_summaries": [ { "avg": 64.0, "labels": { "instance": "db-pd-0" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-pd-1" }, "max": 64.0, "min": 64.0, "point_count": 6 }, { "avg": 64.0, "labels": { "instance": "db-pd-2" }, "max": 64.0, "min": 64.0, "point_count": 6 } ], "summary": { "avg": 64.0, "max": 64.0, "min": 64.0, "point_count": 18, "series_count": 3 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "cores" } ], "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": true, "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-dd36c2728f2c4b0590e4d2a4bc3e9616", "invalid_subtype": null, "judged_at": "2026-07-21T10:11:37.287654+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-9ca3e149083040cfa6e5a554382fc030/evalcase-953d68b097254344af2acf6e28f4724e", "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-1784628628244-6b238c69", "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": [], "description": "Output JSON cluster_id matches the runtime reference.", "earned_score": 6, "id": "output_cluster_id_matches_reference", "match": "all_of", "max_score": 6, "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": 5, "id": "output_window_start_matches_reference", "match": "all_of", "max_score": 5, "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": 5, "id": "output_window_end_matches_reference", "match": "all_of", "max_score": 5, "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 ranked_nodes ordering and identity fields match the runtime reference.", "earned_score": 30, "id": "ranked_nodes_identity_matches_reference", "match": "all_of", "max_score": 30, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_array_matches_reference", "snippet": "[{\"component\": \"tidb\", \"rank\": 1, \"node\": \"db-tidb-3-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3979, \"error_warn_log_count\": 0}, {\"component\": \"tidb\", \"rank\": 2, \"node\": \"db-tidb-17-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3425, ", "source": "output_json" } ], "snippet": "[{\"component\": \"tidb\", \"rank\": 1, \"node\": \"db-tidb-3-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3979, \"error_warn_log_count\": 0}, {\"component\": \"tidb\", \"rank\": 2, \"node\": \"db-tidb-17-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3425, " }, { "artifact_paths": [], "description": "Output JSON ranked_nodes numeric fields match the runtime reference.", "earned_score": 30, "id": "ranked_nodes_numeric_fields_match_reference", "match": "all_of", "max_score": 30, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_array_matches_reference", "snippet": "[{\"component\": \"tidb\", \"rank\": 1, \"node\": \"db-tidb-3-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3979, \"error_warn_log_count\": 0}, {\"component\": \"tidb\", \"rank\": 2, \"node\": \"db-tidb-17-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3425, ", "source": "output_json" } ], "snippet": "[{\"component\": \"tidb\", \"rank\": 1, \"node\": \"db-tidb-3-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3979, \"error_warn_log_count\": 0}, {\"component\": \"tidb\", \"rank\": 2, \"node\": \"db-tidb-17-ac-2006050899364941824\", \"avg_cpu_overload\": 0.3425, " } ], "max_score": 80, "raw_max_score": 80, "raw_score": 80, "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-9ca3e149083040cfa6e5a554382fc030/evalcase-953d68b097254344af2acf6e28f4724e/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": 3, "id": "query_or_metric_channel_observed", "match": "all_of", "max_score": 3, "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": 7, "raw_score": 7, "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": true, "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 ad-hoc case requires ranking the top three CPU-overload nodes per component in the runtime-resolved Beijing 11:00-11:05 window and counting the total ERROR/WARN log lines for each selected node in the same 5-minute window.", "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 }