{ "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": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/Users/huyibin/Documents/dev/investibook/backend/data/workspaces/ws-eval-1778486319562-371b45dd", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true }, "status": "resolved" }, "case_id": "tail-latency-surge-during-incident-window", "contract": { "actual_cluster_id": "10805087899823024166", "cluster_scope_match": true, "expected_allowed_window_id": "workspace_observed_window", "expected_cluster_id": "10805087899823024166", "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": true, "diagnosis_report_present": true, "summary_artifact_present": true, "supplemental_loki_present": false }, "channel_facts": { "events": false, "logs": true, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "Required workflow milestones are present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "matcher": "subset_observed", "path": "", "paths": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: architecture_context_loaded, misdiagnosis_guardrails_loaded, diagnosis_run_initialized, evidence_collection_completed" }, { "description": "Required evidence artifacts are present.", "id": "required_artifacts_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "core_evidence_bundle_present" ], "matcher": "subset_observed", "path": "", "paths": [ "core_evidence_bundle_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: core_evidence_bundle_present" }, { "description": "At least one preferred evidence channel is observed.", "id": "preferred_channels_minimum_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" }, { "description": "Preferred evidence channels are all observed.", "id": "preferred_channels_all_observed", "match": "all_of", "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "subset_observed", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": null } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "architecture_context_loaded": true, "diagnosis_run_initialized": true, "evidence_collection_completed": true, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": true, "summary_read_completed": true } }, "execution_contract_verdict": "pass", "overall_verdict": "pass", "quality_verdict": "pass", "semantic_shadow": { "available": true, "status": "ok" }, "source": "deterministic_judge", "strategy": "deterministic_trace_heavy_v1", "workflow_verdict": "pass" }, "case_run_id": "evalcase-09408f2686be4b7988dcc839789f636a", "facts": { "artifact_observations": { "analysis_patch_present": false, "diagnosis_report_present": true, "summary_artifact_present": true, "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": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a", "source_scope": "audit_dir", "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "tail-latency-surge-during-incident-window", "cluster": { "actual_cluster_id": "10805087899823024166", "expected_cluster_id": "10805087899823024166", "matched": true }, "contract": { "actual_cluster_id": "10805087899823024166", "cluster_scope_match": true, "expected_allowed_window_id": "workspace_observed_window", "expected_cluster_id": "10805087899823024166", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "lock_contention_signal_present", "hotspot_instance_evidence_present", "primary_write_path_evidence_present" ] }, "evidence": { "analysis_patch_path": "", "core_evidence_bundle_present": true, "decoded_plan_indexes_used": "\\N", "events_channel_observed": false, "hotspot_detected": false, "infra_clear": true, "kill_query_signal_present": false, "log_error_counts": { "pd": { "error": 0, "info": 0, "warn": 130 }, "tidb": { "error": 8948, "info": 0, "warn": 4479 }, "tikv": { "error": 78, "info": 0, "warn": 95 } }, "logs_channel_observed": true, "logs_dir_present": false, "memory_tracker_panic_present": false, "metric_evidence": [ { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "all (2 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 3.15, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency Avg", "peak": 18.529, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-wts9s8", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 3.043, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 19.294, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-180hpg", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 3.257, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 17.764, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "component": "tidb", "instance": "all (db, 2 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 1.62, "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU Avg", "nodegroup": "db", "peak": 2.26, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "unit": "cores" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "component": "tidb", "instance": "db-2029059633078865920-tidb-wts9s8", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 2.3, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 7.0, "severity": "normal", "unit": "cores", "utilization": "33%" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "component": "tidb", "instance": "db-2029059633078865920-tidb-180hpg", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 2.23, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 7.0, "severity": "normal", "unit": "cores", "utilization": "32%" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "all (2 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.439, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency Avg", "peak": 0.525, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "unit": "events/s" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-180hpg", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.446, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 0.533, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-wts9s8", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.432, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 0.517, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "all (2 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate Avg", "peak": 0.0, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "unit": "seconds/second" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-180hpg", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.0, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-wts9s8", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.0, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "all (2 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.001, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99 Avg", "peak": 0.005, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-wts9s8", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.001, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.005, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "normal", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": "1773033240", "kind": "promql_range", "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "start": "1773029640", "step": "60s" }, "instance": "db-2029059633078865920-tidb-180hpg", "link": "https://clinic.pingcap.com/portal/#/clusters/10805087899823024166", "mean": 0.001, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.005, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "normal", "unit": "seconds" }, { "chart_data_ref": { "cluster_id": "10805087899823024166", "end": 1773033240, "kind": "promql_range", "promql": "sum(rate(tidb_tikvclient_backoff_seconds_sum{component=\"tidb\"}[1m])) by (type,instance)", "start": 1773029640, "step": "60" }, "group": "tidb_backoff_by_type", "id": "tidb_backoff_by_type", "metric_group_id": "tidb_backoff_by_type", "name": "tidb backoff duration by type", "promql": "sum(rate(tidb_tikvclient_backoff_seconds_sum{component=\"tidb\"}[1m])) by (type,instance)", "ref": { "metric_group_id": "tidb_backoff_by_type", "type": "metric" }, "series_summaries": [ { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "dataNotReady" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "isWitness" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "pdRPC" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0014978142076502653, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "regionMiss" }, "max": 0.0038666666666661814, "min": 0.0006999999999986055, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "regionRecoveryInProgress" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 1.092896174863389e-06, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "regionScheduling" }, "max": 3.333333333333336e-05, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "serverBusy" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "staleCommand" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "tikvDiskFull" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0015311475409836102, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "tikvLockFast" }, "max": 0.00290000000000011, "min": 0.00018333333333326134, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "tikvRPC" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-180hpg", "type": "txnLock" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "dataNotReady" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "isWitness" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "pdRPC" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.01617814207612017, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "regionMiss" }, "max": 0.021833333333336213, "min": 0.010899999998332532, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "regionRecoveryInProgress" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "regionScheduling" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "serverBusy" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "staleCommand" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "tikvDiskFull" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.00121311475409836, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "tikvLockFast" }, "max": 0.0023666666666665986, "min": 0.00015000000000000568, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "tikvRPC" }, "max": 0.0, "min": 0.0, "point_count": 61 }, { "avg": 0.0, "labels": { "instance": "db-2029059633078865920-tidb-wts9s8", "type": "txnLock" }, "max": 0.0, "min": 0.0, "point_count": 61 } ], "summary": { "avg": 0.000785435056731818, "max": 0.021833333333336213, "min": 0.0, "point_count": 1586, "series_count": 26 }, "time_window": { "end": 1773033240, "start": 1773029640, "step": "60" }, "unit": "seconds/second" } ], "panic_signal_artifact_present": false, "query_evidence": { "slow_query": [ { "avg_time": "7.81s", "digest": "d8f5b58e3cf9ae1cb7cd7d9d68991ee63399a5df1ca613ad58b6040f3541617c", "exec_count": "43388", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=d8f5b58e3cf9ae1cb7cd7d9d68991ee63399a5df1ca613ad58b6040f3541617c&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "446856", "max_time": "18.17s", "source": "slow_query", "sql_preview": "update `t_merchant_online` set `amount_by_day` = `amount_by_day` + ? , `total_amount` = `total_amount` + ? where `merchant_id` = ?;" }, { "avg_time": "11.92s", "digest": "1263c0b1abb18a08114a8f93a3159e61f8585a1f7db76495e9f4811d99c890cc", "exec_count": "37286", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=1263c0b1abb18a08114a8f93a3159e61f8585a1f7db76495e9f4811d99c890cc&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "375164", "max_time": "21.87s", "source": "slow_query", "sql_preview": "update `t_merchant_ol_pay_type` set `amount_by_day` = ? + `amount_by_day` , `last_deposit_date` = ? where `merchant_id` = ? and `pay_type` = ?;" }, { "avg_time": "0.94s", "digest": "e63a5a3721df7e879b7467bfe7e6feec4a48eb67e7a3d9f55d61e3671556f78c", "exec_count": "959", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=e63a5a3721df7e879b7467bfe7e6feec4a48eb67e7a3d9f55d61e3671556f78c&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "68631", "max_time": "1.93s", "source": "slow_query", "sql_preview": "select count ( ? ) from `t_product_tran` where ( `flag` = ? and `io_flag` = ? and ( `version_flag` is ? or `version_flag` = ? ) and `auto_flag` = ? and `bill_date` >= ? and `created_date` >= ? and `ch" }, { "avg_time": "0.46s", "digest": "31837fec6e728fe7c720032eee24c65f11119acc87dd902570c47ebe89892c60", "exec_count": "633", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=31837fec6e728fe7c720032eee24c65f11119acc87dd902570c47ebe89892c60&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "49292", "max_time": "1.72s", "source": "slow_query", "sql_preview": "select count ( ? ) from `t_product_tran` where ( `flag` = ? and `io_flag` = ? and `channel_code` = ? and `created_date` >= ? );" }, { "avg_time": "1.97s", "digest": "81480b587869e7ce1fe5e0392b720937bcbb420338542e73078af552fc2c471f", "exec_count": "120", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=81480b587869e7ce1fe5e0392b720937bcbb420338542e73078af552fc2c471f&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "55816", "max_time": "2.15s", "source": "slow_query", "sql_preview": "select `id` , `product_id` , `tran_source` , `flag` , `io_flag` , `merchant_id` , `channel_code` , `urgent` , `bill_flag` , `bill_no` , `bill_amount` , `bill_date` , `additional_amount` , `currency` ," }, { "avg_time": "1.41s", "digest": "a3da08f5565c28177fe62944f4fdda2eea34fabe04edf26c458f57d7b50160dd", "exec_count": "107", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=a3da08f5565c28177fe62944f4fdda2eea34fabe04edf26c458f57d7b50160dd&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "55856", "max_time": "1.90s", "source": "slow_query", "sql_preview": "select `id` , `product_id` , `tran_source` , `flag` , `io_flag` , `merchant_id` , `channel_code` , `urgent` , `bill_flag` , `bill_no` , `bill_amount` , `bill_date` , `additional_amount` , `currency` ," }, { "avg_time": "0.32s", "digest": "c84d6df4529b65884ecf596dbd73113f9af646a213814efd9908a6947e2bcd46", "exec_count": "86", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=c84d6df4529b65884ecf596dbd73113f9af646a213814efd9908a6947e2bcd46&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "60508", "max_time": "0.50s", "source": "slow_query", "sql_preview": "select `id` , `product_id` , `tran_source` , `flag` , `io_flag` , `merchant_id` , `channel_code` , `urgent` , `bill_flag` , `bill_no` , `bill_amount` , `bill_date` , `additional_amount` , `currency` ," }, { "avg_time": "2.94s", "digest": "c538d94fae384d939d9432a100938713ddd47d4c6cd519f9b96bdfc56a856e9f", "exec_count": "60", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=c538d94fae384d939d9432a100938713ddd47d4c6cd519f9b96bdfc56a856e9f&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "773616", "max_time": "3.20s", "source": "slow_query", "sql_preview": "select `id` from `t_order_ol` where `flag` = ? and `created_date` >= ? and `created_date` <= ? and `channel_code` in ( ... );" }, { "avg_time": "0.51s", "digest": "0a8a00476f15aaac340c34c819f0d5c1179aa2af7970a4230e8d8acc2255cae6", "exec_count": "3", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=0a8a00476f15aaac340c34c819f0d5c1179aa2af7970a4230e8d8acc2255cae6&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "8192", "max_time": "0.70s", "source": "slow_query", "sql_preview": "select `flag` , count ( ? ) as `quantity` from `t_product_tran` where `flag` in ( ... ) and `created_date` > date_add ( curdate ( ) , interval - ? day ) group by `flag`;" }, { "avg_time": "0.92s", "digest": "1f12f6e333d2a264e0da279518eed3312a8b3d8e558258b90233eff82db0eae8", "exec_count": "1", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10805087899823024166&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-capital&deployType=premium&version=v8.5.4#/slow_query?digest=1f12f6e333d2a264e0da279518eed3312a8b3d8e558258b90233eff82db0eae8&from=1773029640&to=1773033240&show_internal=true&term=", "max_mem": "399390", "max_time": "0.92s", "source": "slow_query", "sql_preview": "select `ifnull` ( sum ( `t` . `tran_amount` ) , ? ) as `transamount` , `ifnull` ( sum ( case when `t` . `io_flag` = ? then `t` . `tran_amount` end ) , ? ) as `depositamount` , `ifnull` ( sum ( case wh" } ], "topsql": [] }, "query_or_metric_channel_observed": true, "slow_query_top_digest": "d8f5b58e3cf9ae1cb7cd7d9d68991ee63399a5df1ca613ad58b6040f3541617c", "ticket_context_channel_observed": false, "topsql_collection_error_recorded": false }, "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": true, "diagnosis_report_present": true, "summary_artifact_present": true, "supplemental_loki_present": false }, "channel_facts": { "events": false, "logs": true, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "Required workflow milestones are present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "matcher": "subset_observed", "path": "", "paths": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: architecture_context_loaded, misdiagnosis_guardrails_loaded, diagnosis_run_initialized, evidence_collection_completed" }, { "description": "Required evidence artifacts are present.", "id": "required_artifacts_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "core_evidence_bundle_present" ], "matcher": "subset_observed", "path": "", "paths": [ "core_evidence_bundle_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: core_evidence_bundle_present" }, { "description": "At least one preferred evidence channel is observed.", "id": "preferred_channels_minimum_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" }, { "description": "Preferred evidence channels are all observed.", "id": "preferred_channels_all_observed", "match": "all_of", "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "subset_observed", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": null } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "architecture_context_loaded": true, "diagnosis_run_initialized": true, "evidence_collection_completed": true, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": true, "summary_read_completed": true } }, "output": { "analyze_primary_culprit_asserted": false, "claims_panic_not_confirmable": false, "diagnosis_cpu_hotspot_asserted": true, "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, "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 }, "window": { "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "expected_allowed_window_id": "workspace_observed_window", "expected_end_ts": 1773033240, "expected_start_ts": 1773029640, "matched_allowed_window": true }, "workflow": { "architecture_context_loaded": true, "diagnosis_run_initialized": true, "evidence_collection_completed": true, "evidence_collection_started": false, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": true, "summary_read_completed": true, "targeted_panic_log_query_completed": false } }, "id": "evaljudge-2a0061efcb12443eb4716598ee2d590d", "invalid_subtype": null, "judged_at": "2026-05-11T08:02:24.498870+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": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/Users/huyibin/Documents/dev/investibook/backend/data/workspaces/ws-eval-1778486319562-371b45dd", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10805087899823024166", "actual_end_ts": 1773033240, "actual_start_ts": 1773029640, "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": "evidences/evidence_summary_for_agent.json", "summary_json_present": true, "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "summary_txt_present": true, "valid_bundle": true }, "status": "resolved" }, "contract": { "checks": [ { "description": "Actual diagnosis time window matches one allowed case window.", "id": "time_window_match", "match": "all_of", "passed": true, "required": true, "rules": [ { "allowed": [], "matched": true, "matched_keys": [ "time_window_match" ], "matcher": "bool_true", "path": "time_window_match", "source": "trace_fact", "value": "" } ], "snippet": "matched trace facts: time_window_match" }, { "description": "Actual diagnosis cluster scope matches 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": [ "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json" ], "description": "Direct lock-contention evidence is present for the incident window.", "earned_score": 8, "id": "lock_contention_signal_present", "match": "any_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json", "artifacts": [ "queries" ], "matched": true, "matched_keyword": "lock_keys: {time:8.8s", "matcher": "json_text_contains_any", "snippet": "49792.svc.cluster.local:20160, }, region_num:1, write_keys:2, write_byte:3254}, lock_keys: {time:8.8s, region:192, keys:192, slowest_rpc: {total: 0.045s, region_id: 22587, store: db", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "metrics" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "summary_json" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" } ], "snippet": "49792.svc.cluster.local:20160, }, region_num:1, write_keys:2, write_byte:3254}, lock_keys: {time:8.8s, region:192, keys:192, slowest_rpc: {total: 0.045s, region_id: 22587, store: db" }, { "artifact_paths": [ "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json" ], "description": "Evidence isolates the hotspot to a single TiKV instance.", "earned_score": 8, "id": "hotspot_instance_evidence_present", "match": "any_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json", "artifacts": [ "queries" ], "matched": true, "matched_keyword": "store: db-a924bb0f-tikv-29grsn.db-cluster.tidb2028998946604449792.svc.cluster.local:20160", "matcher": "json_text_contains_any", "snippet": "_txn: {prewrite:2.85ms, slowest_prewrite_rpc: {total: 0.003s, region_id: 22587, store: db-a924bb0f-tikv-29grsn.db-cluster.tidb2028998946604449792.svc.cluster.local:20160, }, region_num:1, write_keys:2, write_byte:3254}, lock_keys: {time:8.8s, region", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "metrics" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "summary_json" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" } ], "snippet": "_txn: {prewrite:2.85ms, slowest_prewrite_rpc: {total: 0.003s, region_id: 22587, store: db-a924bb0f-tikv-29grsn.db-cluster.tidb2028998946604449792.svc.cluster.local:20160, }, region_num:1, write_keys:2, write_byte:3254}, lock_keys: {time:8.8s, region" }, { "artifact_paths": [ "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json" ], "description": "Query evidence points to the dominant write path rather than a generic infrastructure issue.", "earned_score": 9, "id": "primary_write_path_evidence_present", "match": "any_of", "max_score": 9, "passed": true, "required": true, "rules": [ { "artifact_path": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-09408f2686be4b7988dcc839789f636a/evidences/queries.json", "artifacts": [ "queries" ], "matched": true, "matched_keyword": "t_merchant_online", "matcher": "json_text_contains_any", "snippet": "9ae1cb7cd7d9d68991ee63399a5df1ca613ad58b6040f3541617c\", \"sql_preview\": \"update `t_merchant_online` set `amount_by_day` = `amount_by_day` + ? , `total_amount` = `total_amount` +", "source": "artifact_json" }, { "artifact_path": "", "artifacts": [ "summary_json" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" } ], "snippet": "9ae1cb7cd7d9d68991ee63399a5df1ca613ad58b6040f3541617c\", \"sql_preview\": \"update `t_merchant_online` set `amount_by_day` = `amount_by_day` + ? , `total_amount` = `total_amount` +" } ], "max_score": 30, "raw_max_score": 25, "raw_score": 25, "score": 30, "status": "pass" }, "critical_evidence_verdict": "pass", "diagnosis": { "checks": [ { "description": "Identifies lock contention on the primary write path as the main incident path.", "deterministic": { "match": "all_of", "passed": true, "rules": [ { "keywords": [ "lock contention", "pessimistic lock", "lock wait", "write contention", "concurrent write contention", "hotspot key serialization", "锁冲突", "锁竞争", "锁等待", "并发写争用", "热点键串行化" ], "matched": true, "matched_keys": [ "锁冲突", "锁竞争", "锁等待" ], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" }, { "keywords": [ "write path", "point update", "update workload", "写路径", "点更新" ], "matched": true, "matched_keys": [ "写路径", "点更新" ], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": true, "earned_score": 3.0, "id": "identify_lock_contention_as_primary_path", "max_score": 3, "mode": "blended", "passed": true, "penalty_applied": 0, "required": true, "scoring_mode": "positive", "semantic_check_id": 1, "semantic_confidence": 0.86, "semantic_notes": [ "Answer attributes the incident to a write-path hotspot with severe lock contention from high-concurrency point updates on the same key/row (merchant_id), and explicitly rules out generic CPU/IO/infra bottlenecks as the primary cause." ], "semantic_status": "pass" }, { "description": "Identifies that the pressure was concentrated on one TiKV instance rather than cluster-wide.", "deterministic": { "match": "any_of", "passed": false, "rules": [ { "keywords": [ "single TiKV instance", "hotspot TiKV", "one TiKV hotspot", "单个 TiKV 实例", "热点 TiKV" ], "matched": false, "matched_keys": [], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": false, "earned_score": 0.0, "id": "identify_single_tikv_hotspot", "max_score": 3, "mode": "blended", "passed": false, "penalty_applied": 0, "required": false, "scoring_mode": "positive", "semantic_check_id": 2, "semantic_confidence": 0.78, "semantic_notes": [ "Answer discusses lock contention and hot keys, but does not identify the hotspot as concentrated on a single TiKV instance; it even claims instance-level hotspot was not detected, which conflicts with the single-instance hotspot evidence requirement." ], "semantic_status": "fail" }, { "description": "Recommends mitigation targeted at the write-contention path.", "deterministic": { "match": "any_of", "passed": false, "rules": [ { "keywords": [ "batch update", "batch aggregation", "async aggregation", "periodic flush", "SHARD_ROW_ID_BITS", "reduce update frequency", "批量更新", "异步聚合", "降低更新频率" ], "matched": false, "matched_keys": [], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": false, "earned_score": 3.0, "id": "recommend_write_path_mitigation", "max_score": 3, "mode": "blended", "passed": true, "penalty_applied": 0, "required": false, "scoring_mode": "positive", "semantic_check_id": 4, "semantic_confidence": 0.84, "semantic_notes": [ "Recommendations align with write-contention mitigation: per-key serialization/merge, batching, backoff/jitter, sharded counters, async/event-stream aggregation, and reducing effective update frequency rather than increasing timeouts." ], "semantic_status": "pass" } ], "hard_gate_passed": true, "max_score": 50, "raw_score": 6.0, "score": 33, "semantic_shadow": { "available": true, "bucket": "diagnosis.semantic", "checks": [ { "bucket": "diagnosis.semantic", "check_id": 1, "confidence": 0.86, "disagreement_flags": [ "check_2_answer_denies_single_tikv_hotspot" ], "evidence": { "critical_evidence_ids": [ "primary_write_path_evidence_present", "lock_contention_signal_present" ], "routed_item_ids": [ "ce-3" ] }, "max_score": 3, "mode": "shadow", "notes": [ "Answer attributes the incident to a write-path hotspot with severe lock contention from high-concurrency point updates on the same key/row (merchant_id), and explicitly rules out generic CPU/IO/infra bottlenecks as the primary cause." ], "score": 3, "status": "pass" }, { "bucket": "diagnosis.semantic", "check_id": 2, "confidence": 0.78, "disagreement_flags": [ "check_2_answer_denies_single_tikv_hotspot" ], "evidence": { "critical_evidence_ids": [ "hotspot_instance_evidence_present" ], "routed_item_ids": [ "ce-2" ] }, "max_score": 3, "mode": "shadow", "notes": [ "Answer discusses lock contention and hot keys, but does not identify the hotspot as concentrated on a single TiKV instance; it even claims instance-level hotspot was not detected, which conflicts with the single-instance hotspot evidence requirement." ], "score": 0, "status": "fail" }, { "bucket": "diagnosis.semantic", "check_id": 4, "confidence": 0.84, "disagreement_flags": [ "check_2_answer_denies_single_tikv_hotspot" ], "evidence": { "critical_evidence_ids": [ "lock_contention_signal_present" ], "routed_item_ids": [ "ce-3" ] }, "max_score": 3, "mode": "shadow", "notes": [ "Recommendations align with write-contention mitigation: per-key serialization/merge, batching, backoff/jitter, sharded counters, async/event-stream aggregation, and reducing effective update frequency rather than increasing timeouts." ], "score": 3, "status": "pass" } ], "mode": "shadow", "packet_case_id": "tail-latency-surge-during-incident-window", "packet_loaded": true, "packet_notes": [], "packet_status": "ok", "status": "ok", "summary": { "disagreement_flags": [ "check_2_answer_denies_single_tikv_hotspot" ], "shadow_max_score": 9, "shadow_score": 6 } }, "status": "pass" }, "evidence_collection": { "checks": [ { "description": "Required evidence artifacts are present and readable.", "earned_score": 4, "id": "required_artifacts_present", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "core_evidence_bundle_present" ], "matcher": "subset_observed", "path": "", "paths": [ "core_evidence_bundle_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched collection facts: core_evidence_bundle_present" }, { "description": "At least the minimum number of preferred evidence channels are observed.", "earned_score": 0, "id": "preferred_channels_minimum_observed", "match": "all_of", "max_score": 0, "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": "Preferred evidence channels are all observed.", "earned_score": 6, "id": "preferred_channels_all_observed", "match": "all_of", "max_score": 6, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "subset_observed", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": null } ], "snippet": "matched collection facts: query_or_metric" } ], "max_score": 5, "raw_max_score": 10, "raw_score": 10, "score": 5, "status": "pass" }, "evidence_collection_verdict": "pass", "evidence_routing": { "checks": [ { "description": "Analysis patch is valid JSON whenever the patch exists.", "earned_score": 1, "id": "analysis_patch_valid_json", "match": "any_of", "max_score": 1, "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" }, { "description": "Analysis patch items are structurally valid whenever the patch exists.", "earned_score": 2, "id": "analysis_items_shape_valid", "match": "any_of", "max_score": 2, "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_items_shape_valid", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" }, { "description": "Analysis patch includes key evidence whenever the patch exists.", "earned_score": 2, "id": "analysis_key_evidence_present", "match": "any_of", "max_score": 2, "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_has_key_evidence", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" }, { "description": "Metric references resolve whenever the patch requires them.", "earned_score": 1, "id": "metric_refs_resolvable", "match": "any_of", "max_score": 1, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "analysis_patch_present" ], "matcher": "bool_false", "path": "analysis_patch_present", "paths": [], "source": "routing_fact" }, { "matched": true, "matched_keys": [ "analysis_metric_refs_resolvable" ], "matcher": "bool_true", "path": "analysis_metric_refs_resolvable", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present, analysis_metric_refs_resolvable" }, { "description": "Query references resolve whenever the patch requires them.", "earned_score": 1, "id": "query_refs_resolvable", "match": "any_of", "max_score": 1, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "analysis_patch_present" ], "matcher": "bool_false", "path": "analysis_patch_present", "paths": [], "source": "routing_fact" }, { "matched": true, "matched_keys": [ "analysis_query_refs_resolvable" ], "matcher": "bool_true", "path": "analysis_query_refs_resolvable", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present, analysis_query_refs_resolvable" }, { "description": "Analysis patch includes supporting evidence whenever the patch exists.", "earned_score": 0, "id": "supporting_evidence_present", "match": "any_of", "max_score": 0, "passed": true, "required": false, "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_has_supporting_evidence", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" }, { "description": "Routed log or event items stay resolvable against observed channels.", "earned_score": 0, "id": "analysis_log_or_event_channel_resolvable", "match": "all_of", "max_score": 0, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "analysis_log_or_event_channel_resolvable" ], "matcher": "bool_true", "path": "analysis_log_or_event_channel_resolvable", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_log_or_event_channel_resolvable" } ], "max_score": 5, "raw_max_score": 7, "raw_score": 7, "score": 5, "status": "pass" }, "evidence_routing_verdict": "pass", "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": true, "diagnosis_report_present": true, "summary_artifact_present": true, "supplemental_loki_present": false }, "channel_facts": { "events": false, "logs": true, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "Required workflow milestones are present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "matcher": "subset_observed", "path": "", "paths": [ "architecture_context_loaded", "misdiagnosis_guardrails_loaded", "diagnosis_run_initialized", "evidence_collection_completed" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: architecture_context_loaded, misdiagnosis_guardrails_loaded, diagnosis_run_initialized, evidence_collection_completed" }, { "description": "Required evidence artifacts are present.", "id": "required_artifacts_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "core_evidence_bundle_present" ], "matcher": "subset_observed", "path": "", "paths": [ "core_evidence_bundle_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: core_evidence_bundle_present" }, { "description": "At least one preferred evidence channel is observed.", "id": "preferred_channels_minimum_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" }, { "description": "Preferred evidence channels are all observed.", "id": "preferred_channels_all_observed", "match": "all_of", "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "subset_observed", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": null } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "architecture_context_loaded": true, "diagnosis_run_initialized": true, "evidence_collection_completed": true, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": true, "summary_read_completed": true } }, "execution_contract_verdict": "pass", "ground_truth_root_cause": "High-frequency point updates on t_merchant_online caused pessimistic lock contention and a single-TiKV hotspot during the incident window", "overall_verdict": "pass", "quality_verdict": "pass", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 83, "hard_gate_passed": true, "passing_hard_gate_score_floor": 70, "raw_total_score": 83 }, "strategy": "deterministic_trace_heavy_v1", "workflow": { "checks": [ { "description": "Architecture context is loaded.", "earned_score": 5, "id": "architecture_context_loaded", "match": "all_of", "max_score": 5, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "architecture_context_loaded" ], "matcher": "bool_true", "path": "architecture_context_loaded", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: architecture_context_loaded" }, { "description": "Misdiagnosis guardrails are loaded.", "earned_score": 5, "id": "misdiagnosis_guardrails_loaded", "match": "all_of", "max_score": 5, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "misdiagnosis_guardrails_loaded" ], "matcher": "bool_true", "path": "misdiagnosis_guardrails_loaded", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: misdiagnosis_guardrails_loaded" }, { "description": "Diagnosis run is initialized.", "earned_score": 5, "id": "diagnosis_run_initialized", "match": "all_of", "max_score": 5, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_run_initialized" ], "matcher": "bool_true", "path": "diagnosis_run_initialized", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: diagnosis_run_initialized" }, { "description": "Evidence collection completes.", "earned_score": 10, "id": "evidence_collection_completed", "match": "all_of", "max_score": 10, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "evidence_collection_completed" ], "matcher": "bool_true", "path": "evidence_collection_completed", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: evidence_collection_completed" }, { "description": "Summary artifact is read when available.", "earned_score": 5, "id": "summary_read_completed", "match": "all_of", "max_score": 5, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "summary_read_completed" ], "matcher": "bool_true", "path": "summary_read_completed", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: summary_read_completed" }, { "description": "Final answer is emitted.", "earned_score": 0, "id": "final_answer_emitted", "match": "all_of", "max_score": 0, "passed": true, "required": false, "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" } ], "max_score": 10, "raw_max_score": 25, "raw_score": 25, "score": 10, "status": "pass" }, "workflow_verdict": "pass" }, "passed_checks": 2, "primary_failure_code": null, "score": 83, "total_checks": 3 }