{ "audit_json": { "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": "10748116073341772391", "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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10748116073341772391", "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-1784618349255-46bfa596", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10748116073341772391", "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": "10748116073341772391", "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-premium-cluster-during-latest-window", "contract": { "actual_cluster_id": "10748116073341772391", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10748116073341772391", "expected_parent_id": "2026948324023603200", "time_window_match": true }, "critical_evidence_verdict": "partial", "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": "fail", "quality_verdict": "pass", "semantic_shadow": { "available": false, "status": "not_available" }, "source": "deterministic_judge", "strategy": "deterministic_trace_heavy_v1", "workflow_verdict": "pass" }, "facts_json": { "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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01", "source_scope": "audit_dir", "summary_txt_path": "", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "top-tidb-p99-latency-nodes-in-premium-cluster-during-latest-window", "cluster": { "actual_cluster_id": "10748116073341772391", "allowed_cluster_ids": [ "10748116073341772391", "2026948324023603200" ], "expected_cluster_id": "10748116073341772391", "expected_parent_id": "2026948324023603200", "matched": true }, "contract": { "actual_cluster_id": "10748116073341772391", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10748116073341772391", "expected_parent_id": "2026948324023603200", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "latency_metric_present", "latency_metric_series_nonempty", "output_cluster_id_matches_reference", "output_window_start_matches_reference", "output_window_end_matches_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": "10748116073341772391", "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": 0.013353121944125487, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.013550077787381203, "min": 0.013060386660222308, "point_count": 6 }, { "avg": 0.013570646661709332, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.013677805396932054, "min": 0.013418371282051353, "point_count": 6 }, { "avg": 0.012631991557226658, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.01284352995819777, "min": 0.012417321493735612, "point_count": 6 }, { "avg": 0.013188897232814889, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.013428127240143415, "min": 0.01304297620377614, "point_count": 6 }, { "avg": 0.012991077342248613, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.013131053665910847, "min": 0.012762604783329481, "point_count": 6 }, { "avg": 0.011999096799649209, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.012278757846052198, "min": 0.011849998702141505, "point_count": 6 }, { "avg": 0.011423270521935392, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.011586468096734555, "min": 0.011198683084899618, "point_count": 6 }, { "avg": 0.012074717901640811, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.01228072286111477, "min": 0.011906645848119238, "point_count": 6 }, { "avg": 0.011869039822721824, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.012085974995940944, "min": 0.011634819212088554, "point_count": 6 }, { "avg": 0.013322554495110217, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.013561302065103347, "min": 0.013222057814796816, "point_count": 6 } ], "summary": { "avg": 0.012642441427918242, "max": 0.013677805396932054, "min": 0.011198683084899618, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket[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[1m])))", "ref": { "metric_group_id": "avg_plan_build_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.0012458398338999193, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.0012497666756256815, "min": 0.0012415691931445432, "point_count": 6 }, { "avg": 0.0012531946669120503, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.0012564020504058104, "min": 0.0012481739295136306, "point_count": 6 }, { "avg": 0.0012594023140094306, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.001260627915800885, "min": 0.0012566233416283338, "point_count": 6 }, { "avg": 0.0012467942387946196, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.001249869151589872, "min": 0.0012425337375849455, "point_count": 6 }, { "avg": 0.0012372481709678341, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.0012440899344039816, "min": 0.0012321694520085512, "point_count": 6 }, { "avg": 0.0012570183371675098, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.0012633132725802104, "min": 0.001247399279214986, "point_count": 6 }, { "avg": 0.0012526332246507196, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.00126110176844079, "min": 0.0012473785087789894, "point_count": 6 }, { "avg": 0.0012562242893442103, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.001260850716953713, "min": 0.0012537100696481873, "point_count": 6 }, { "avg": 0.0012510864322881953, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.0012578403400659004, "min": 0.0012455990675661363, "point_count": 6 }, { "avg": 0.0012450957049240227, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.0012508564500111172, "min": 0.0012421581064035025, "point_count": 6 } ], "summary": { "avg": 0.0012504537212958513, "max": 0.0012633132725802104, "min": 0.0012321694520085512, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_distsql_handle_query_duration_seconds_bucket[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[1m])))", "ref": { "metric_group_id": "avg_distributed_execution_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.00392483392195387, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.003970172254908911, "min": 0.0038921857218723946, "point_count": 6 }, { "avg": 0.003916794306834466, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.0039369292858396215, "min": 0.00390516802610114, "point_count": 6 }, { "avg": 0.003938724662742044, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.003957493162564202, "min": 0.003931037222919282, "point_count": 6 }, { "avg": 0.003923906816293951, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.003944433811802241, "min": 0.00390396999062208, "point_count": 6 }, { "avg": 0.003917180010567947, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.003944873358348965, "min": 0.0039014728536539596, "point_count": 6 }, { "avg": 0.003924863231353483, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.003938556613756615, "min": 0.003907653463362503, "point_count": 6 }, { "avg": 0.003901932159255356, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.003934642028637707, "min": 0.003885865549419164, "point_count": 6 }, { "avg": 0.003931769006805341, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.0039493205404346945, "min": 0.0039053842893472797, "point_count": 6 }, { "avg": 0.0038991737999118925, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.003949756656169484, "min": 0.0038717981535879133, "point_count": 6 }, { "avg": 0.003917573411552311, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.003940314737718567, "min": 0.003899964049350442, "point_count": 6 } ], "summary": { "avg": 0.003919675132727066, "max": 0.003970172254908911, "min": 0.0038717981535879133, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(tidb_tikvclient_request_seconds_bucket{type=\"Get\"}[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\"}[1m])))", "ref": { "metric_group_id": "avg_kv_request_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.002632079847224278, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.0031392000000000538, "min": 0.0020050000000000237, "point_count": 6 }, { "avg": 0.0024554666463889392, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.003079545454545479, "min": 0.001996601307189544, "point_count": 6 }, { "avg": 0.002268848464066849, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.0024337500000000552, "min": 0.0020266666666667182, "point_count": 6 }, { "avg": 0.0026513570243482574, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.0032261538461539185, "min": 0.002226428571428657, "point_count": 6 }, { "avg": 0.0025196058767822595, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.0030911111111112267, "min": 0.001994029850746269, "point_count": 6 }, { "avg": 0.0024920232286321695, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.003169444444444529, "min": 0.002046250000000044, "point_count": 6 }, { "avg": 0.0028492890353833985, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.0035544999999999978, "min": 0.0021400000000000507, "point_count": 6 }, { "avg": 0.00269122277976578, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.0029557142857143384, "min": 0.0021889999999999674, "point_count": 6 }, { "avg": 0.0030358927219268604, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.0032008510638298158, "min": 0.00284190476190483, "point_count": 6 }, { "avg": 0.0022969478518341424, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.002688780487804905, "min": 0.0019963962065331926, "point_count": 6 } ], "summary": { "avg": 0.0025892733476352934, "max": 0.0035544999999999978, "min": 0.001994029850746269, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "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\"}[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\"}[1m])))", "ref": { "metric_group_id": "avg_get_tso_wait_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.0019178280034407886, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.001921927133269415, "min": 0.0019151546526867621, "point_count": 6 }, { "avg": 0.0019705139495889957, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.0019721188818455785, "min": 0.0019693156149912907, "point_count": 6 }, { "avg": 0.0018220263883001872, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.0018301256499133455, "min": 0.0018137906479943028, "point_count": 6 }, { "avg": 0.001930197365266793, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.0019346181209458043, "min": 0.0019280682601700752, "point_count": 6 }, { "avg": 0.0019327868485835887, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.0019363542405512197, "min": 0.0019262063697261726, "point_count": 6 }, { "avg": 0.000985560594835774, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.0009861268274397102, "min": 0.000984875760512572, "point_count": 6 }, { "avg": 0.0004956274044716915, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.0004957102215575454, "min": 0.0004955590073845819, "point_count": 6 }, { "avg": 0.0009841653689598745, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.000984550355305072, "min": 0.0009838410956609146, "point_count": 6 }, { "avg": 0.0009600444909211413, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.0009617233380135521, "min": 0.0009577231939657981, "point_count": 6 }, { "avg": 0.0019218999506544277, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.0019254869303724272, "min": 0.0019178079939286621, "point_count": 6 } ], "summary": { "avg": 0.0014920650365023262, "max": 0.0019721188818455785, "min": 0.0004955590073845819, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "end": 1784603100, "kind": "promql_range", "promql": "histogram_quantile(0.99, sum by (le, instance) (rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[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\"}[1m])))", "ref": { "metric_group_id": "avg_gc_stw_pause_p99_s", "type": "metric" }, "series_summaries": [ { "avg": 0.000907861879349901, "labels": { "instance": "db-2027220408993841152-tidb-2j6dju" }, "max": 0.0009086417454545453, "min": 0.0009073576228571426, "point_count": 6 }, { "avg": 0.0009086321662282647, "labels": { "instance": "db-2027220408993841152-tidb-4pf3vl" }, "max": 0.0009090367487999999, "min": 0.0009083243447887321, "point_count": 6 }, { "avg": 0.0009088713675412027, "labels": { "instance": "db-2027220408993841152-tidb-79yuza" }, "max": 0.0009090423898734175, "min": 0.0009085758421917806, "point_count": 6 }, { "avg": 0.0019959683104738505, "labels": { "instance": "db-2027220408993841152-tidb-7gleep" }, "max": 0.004362076160000014, "min": 0.000908463255081967, "point_count": 6 }, { "avg": 0.0009077681659254655, "labels": { "instance": "db-2027220408993841152-tidb-7qc8pe" }, "max": 0.0009082448259459458, "min": 0.0009073576228571426, "point_count": 6 }, { "avg": 0.0009084956451125598, "labels": { "instance": "db-2027220408993841152-tidb-7sixuh" }, "max": 0.0009090133883870968, "min": 0.0009076949704347825, "point_count": 6 }, { "avg": 0.0009085093774781656, "labels": { "instance": "db-2027220408993841152-tidb-glddbi" }, "max": 0.0009088726927472526, "min": 0.0009078425599999999, "point_count": 6 }, { "avg": 0.00122908335450519, "labels": { "instance": "db-2027220408993841152-tidb-jvlne6" }, "max": 0.002831155199999923, "min": 0.0009083682815999998, "point_count": 6 }, { "avg": 0.0009084296547527313, "labels": { "instance": "db-2027220408993841152-tidb-krx4fy" }, "max": 0.0009089339076923075, "min": 0.0009075902915254236, "point_count": 6 }, { "avg": 0.0009083438618471013, "labels": { "instance": "db-2027220408993841152-tidb-p1s0s2" }, "max": 0.0009087740179104475, "min": 0.0009079911975384614, "point_count": 6 } ], "summary": { "avg": 0.0010491963783214433, "max": 0.004362076160000014, "min": 0.0009073576228571426, "point_count": 60, "series_count": 10 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "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": [], "summary": { "point_count": 0, "series_count": 0 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10748116073341772391", "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": [], "summary": { "point_count": 0, "series_count": 0 }, "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 } }, "invalid_subtype": null, "judgment_verdict": "fail", "packet_json": { "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": "10748116073341772391", "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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10748116073341772391", "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-1784618349255-46bfa596", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10748116073341772391", "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": "10748116073341772391", "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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/evidences/metrics.json", "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\": 60, \"min\": 0.01119868308", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\": 60, \"min\": 0.01119868308", "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\": 60, \"min\": 0.01119868308" }, { "artifact_paths": [ "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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": 0, "id": "breakdown_metrics_present", "match": "all_of", "max_score": 6, "passed": false, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60, \"min\": 0.00123216945", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60, \"min\": 0.00387179815", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\\\"}[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60, \"min\":", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "metrics", "workspace_report" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\\\"}[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60, \"min\":", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "metrics", "workspace_report" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\\\"}[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60,", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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\": 0, \"ser", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "metrics", "workspace_report" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/evidences/metrics.json", "artifacts": [ "metrics", "workspace_report" ], "matched": true, "matched_keyword": "handle_tso_duration_seconds_bucket", "matcher": "json_text_contains_any", "snippet": "9_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(pd_server_handle_tso_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 0, \"series_count\": 0}, \"", "source": "artifact_json" } ], "snippet": "n_build_p99_s\", \"promql\": \"histogram_quantile(0.99, sum by (le, instance) (rate(tidb_session_compile_duration_seconds_bucket[1m])))\", \"unit\": \"seconds\", \"summary\": {\"point_count\": 60, \"min\": 0.00123216945" }, { "artifact_paths": [ "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": null, "matcher": "json_values_nonempty", "snippet": "[[1784602800, \"0.013550077787381203\"], [1784602860, \"0.013060386660222308\"], [1784602920, \"0.013382747509531487\"], [1784602980, \"0.013417140096618402\"], [1784603040, \"0.013470760563380386\"], [1784603100, \"0.013237619047619133\"]]", "source": "artifact_json" } ], "snippet": "[[1784602800, \"0.013550077787381203\"], [1784602860, \"0.013060386660222308\"], [1784602920, \"0.013382747509531487\"], [1784602980, \"0.013417140096618402\"], [1784603040, \"0.013470760563380386\"], [1784603100, \"0.013237619047619133\"]]" }, { "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": "\"10748116073341772391\"", "source": "output_json" } ], "snippet": "\"10748116073341772391\"" }, { "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": 0, "id": "evidence_sufficient_matches_reference", "match": "all_of", "max_score": 4, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": null, "source": "output_json" } ], "snippet": null }, { "artifact_paths": [], "description": "Output JSON cluster_avg_tikv_grpc_request_handle_p99_s matches the runtime reference.", "earned_score": 0, "id": "cluster_avg_tikv_grpc_matches_reference", "match": "all_of", "max_score": 4, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": null, "source": "output_json" } ], "snippet": null }, { "artifact_paths": [], "description": "Output JSON cluster_avg_pd_tso_request_handle_p99_s matches the runtime reference.", "earned_score": 0, "id": "cluster_avg_pd_tso_matches_reference", "match": "all_of", "max_score": 4, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": null, "source": "output_json" } ], "snippet": null }, { "artifact_paths": [], "description": "Output JSON ranked TiDB nodes and their P99 breakdown match the runtime reference ordering and values.", "earned_score": 0, "id": "top_nodes_match_runtime_reference", "match": "all_of", "max_score": 10, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "json_array_matches_reference", "snippet": null, "source": "output_json" } ], "snippet": null } ], "max_score": 80, "raw_max_score": 50, "raw_score": 22, "score": 35, "status": "partial" }, "critical_evidence_verdict": "partial", "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": 50, "raw_score": 0, "score": 0, "semantic_shadow": { "available": false, "checks": [], "packet_path": "/data/eval_audits/evalrun-dca9124193b04b2c873027cd9fb2ca6f/evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01/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": 5, "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": "fail", "quality_verdict": "pass", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 40, "hard_gate_passed": false, "passing_hard_gate_score_floor": 70, "raw_total_score": 40 }, "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": 10, "raw_max_score": 0, "raw_score": 0, "score": 0, "status": "pass" }, "workflow_verdict": "pass" }, "passed_checks": 0, "primary_failure_code": "critical_evidence_partial", "score": 40, "total_checks": 0 }