{ "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": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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-d13fad687c5f44b193d158c91bded21a", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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-1778485451230-a73e4c96", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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": "sql-tail-latency-spike-during-incident-window", "contract": { "actual_cluster_id": "10748116073341772391", "cluster_scope_match": true, "expected_allowed_window_id": "workspace_observed_window", "expected_cluster_id": "10748116073341772391", "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": 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": "fail", "quality_verdict": "fail", "semantic_shadow": { "available": true, "status": "ok" }, "source": "deterministic_judge", "strategy": "deterministic_trace_heavy_v1", "workflow_verdict": "pass" }, "case_run_id": "evalcase-d13fad687c5f44b193d158c91bded21a", "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-d13fad687c5f44b193d158c91bded21a", "source_scope": "audit_dir", "summary_txt_path": "evidences/evidence_summary_for_agent.txt", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "sql-tail-latency-spike-during-incident-window", "cluster": { "actual_cluster_id": "10748116073341772391", "expected_cluster_id": "10748116073341772391", "matched": true }, "contract": { "actual_cluster_id": "10748116073341772391", "cluster_scope_match": true, "expected_allowed_window_id": "workspace_observed_window", "expected_cluster_id": "10748116073341772391", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "gc_signal_present", "heap_profile_signal_present" ] }, "evidence": { "analysis_patch_path": "", "core_evidence_bundle_present": true, "decoded_plan_indexes_used": "\\N", "events_channel_observed": false, "hotspot_detected": true, "infra_clear": true, "kill_query_signal_present": false, "log_error_counts": { "pd": { "error": 3, "info": 0, "warn": 303 }, "tidb": { "error": 2295572, "info": 0, "warn": 5099207 }, "tikv": { "error": 2696, "info": 0, "warn": 4873 } }, "logs_channel_observed": true, "logs_dir_present": false, "memory_tracker_panic_present": false, "metric_evidence": [ { "instance": "all (8 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.03, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency Avg", "peak": 0.5, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-krx4fy", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.116, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 3.51, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-7sixuh", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.028, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 0.12, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-79yuza", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.026, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 0.118, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-n3jm51", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.02, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 0.105, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-7qc8pe", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.016, "metric_group_id": "tidb_p99_latency", "name": "TiDB P99 Latency", "peak": 0.102, "promql": "histogram_quantile(0.99, sum(rate(tidb_server_handle_query_duration_seconds_bucket[1m])) by (le, instance))", "unit": "seconds" }, { "component": "tidb", "instance": "all (db, 8 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 13.97, "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU Avg", "nodegroup": "db", "peak": 22.6, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "unit": "cores" }, { "component": "tidb", "instance": "db-2027220408993841152-tidb-krx4fy", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 27.0, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 31.0, "severity": "critical", "unit": "cores", "utilization": "87%" }, { "component": "tidb", "instance": "db-2027220408993841152-tidb-7sixuh", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 26.16, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 31.0, "severity": "critical", "unit": "cores", "utilization": "84%" }, { "component": "tidb", "instance": "db-2027220408993841152-tidb-n3jm51", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 25.76, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 31.0, "severity": "critical", "unit": "cores", "utilization": "83%" }, { "component": "tidb", "instance": "db-2027220408993841152-tidb-79yuza", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 25.49, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 31.0, "severity": "critical", "unit": "cores", "utilization": "82%" }, { "component": "tidb", "instance": "db-2027220408993841152-tidb-7qc8pe", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "metric_group_id": "tidb_cpu:db", "name": "TIDB CPU", "nodegroup": "db", "peak": 25.14, "promql": "rate(process_cpu_seconds_total{component=\"tidb\"}[1m])", "quota": 31.0, "severity": "critical", "unit": "cores", "utilization": "81%" }, { "instance": "all (8 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.536, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency Avg", "peak": 1.015, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "unit": "events/s" }, { "instance": "db-2027220408993841152-tidb-7sixuh", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.575, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 1.283, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "instance": "db-2027220408993841152-tidb-krx4fy", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.235, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 1.267, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "instance": "db-2027220408993841152-tidb-79yuza", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.561, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 1.25, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "instance": "db-2027220408993841152-tidb-jvlne6", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.7, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 0.983, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "instance": "db-2027220408993841152-tidb-7qc8pe", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.647, "metric_group_id": "tidb_gc_frequency", "name": "TiDB GC Frequency", "peak": 0.917, "promql": "rate(go_gc_duration_seconds_count{component=\"tidb\"}[1m])", "severity": "normal", "unit": "events/s" }, { "instance": "all (8 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.001, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate Avg", "peak": 0.017, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "unit": "seconds/second" }, { "instance": "db-2027220408993841152-tidb-krx4fy", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.005, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.083, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "instance": "db-2027220408993841152-tidb-79yuza", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.023, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "instance": "db-2027220408993841152-tidb-7sixuh", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.016, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "instance": "db-2027220408993841152-tidb-n3jm51", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.012, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "instance": "db-2027220408993841152-tidb-tn94el", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.0, "metric_group_id": "tidb_gc_duration_rate", "name": "TiDB GC Duration Rate", "peak": 0.001, "promql": "rate(go_gc_duration_seconds_sum{component=\"tidb\"}[1m])", "severity": "normal", "unit": "seconds/second" }, { "instance": "all (8 instances)", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.005, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99 Avg", "peak": 0.063, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-79yuza", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.004, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.117, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "warning", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-7sixuh", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.005, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.117, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "warning", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-krx4fy", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.022, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.117, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "warning", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-n3jm51", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.003, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.117, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "warning", "unit": "seconds" }, { "instance": "db-2027220408993841152-tidb-tn94el", "link": "https://clinic.pingcap.com/portal/#/clusters/10748116073341772391", "mean": 0.001, "metric_group_id": "tidb_gc_pause_p99", "name": "TiDB GC Pause P99", "peak": 0.017, "promql": "histogram_quantile(0.99, sum(rate(go_gc_pauses_seconds_bucket{component=\"tidb\"}[1m])) by (le, instance))", "severity": "normal", "unit": "seconds" } ], "panic_signal_artifact_present": false, "query_evidence": { "slow_query": [ { "avg_time": "1.26s", "digest": "908792e63b56548d90d46345e2077cecc168cbb3a2f42baf6ef5e0a159930a05", "exec_count": "4978", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=908792e63b56548d90d46345e2077cecc168cbb3a2f42baf6ef5e0a159930a05&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "7272117", "max_time": "19.39s", "source": "slow_query", "sql_preview": "delete from `c66_seamless_others` . `t_seamless_log_tiptop` where ( ( `id` between ? and ? ) and ( ( ( ? = ? ) and ( `created_time` >= ? ) ) and ( `created_time` < ? ) ) );" }, { "avg_time": "2.33s", "digest": "ed185a3821972c8c916764d48152867ed0d432f30fecd8886fdffd40e16f91a2", "exec_count": "1834", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=ed185a3821972c8c916764d48152867ed0d432f30fecd8886fdffd40e16f91a2&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "260832", "max_time": "20.43s", "source": "slow_query", "sql_preview": "select `id` , `login_name` , `wallet_type` , `accept_game` , `amount` , `currency` , `tenant` , `site_id` , `bet_site_id` , `branch_code` , `branch_name` , `term_type` , `cur_ip` , `active` , `revisio" }, { "avg_time": "3.84s", "digest": "a028483d134b7c42638ad3bf0bde6f27d231dc6b0be42e437e3f7e389f71ec92", "exec_count": "1299", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=a028483d134b7c42638ad3bf0bde6f27d231dc6b0be42e437e3f7e389f71ec92&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "78792", "max_time": "17.66s", "source": "slow_query", "sql_preview": "select `id` , `login_name` , `wallet_type` , `accept_game` , `amount` , `currency` , `tenant` , `site_id` , `bet_site_id` , `branch_code` , `branch_name` , `term_type` , `cur_ip` , `active` , `revisio" }, { "avg_time": "1.35s", "digest": "bdadb2f390740bf4e08e3672e17d2c881ff9fbc75f7e2037c247a2511a7b5baa", "exec_count": "1297", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=bdadb2f390740bf4e08e3672e17d2c881ff9fbc75f7e2037c247a2511a7b5baa&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "271008", "max_time": "17.96s", "source": "slow_query", "sql_preview": "update `t_seamless_wallet` set `amount` = ? , `updated_time` = ? , `sign` = ? , `revision` = `revision` + ? where `id` = ? and `revision` = ?;" }, { "avg_time": "2.58s", "digest": "e08ee53094e60d98b56340925e2d6c905c346d4d3e53d49668e97335d9aeeff7", "exec_count": "1138", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=e08ee53094e60d98b56340925e2d6c905c346d4d3e53d49668e97335d9aeeff7&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "129168", "max_time": "20.28s", "source": "slow_query", "sql_preview": "select `id` , `login_name` , `wallet_type` , `accept_game` , `amount` , `currency` , `tenant` , `site_id` , `bet_site_id` , `branch_code` , `branch_name` , `term_type` , `cur_ip` , `active` , `revisio" }, { "avg_time": "1.55s", "digest": "4adbd55820b559f6ac86509afb5db4dc77766433ff07e2b2ec82b3098215fa0c", "exec_count": "1107", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=4adbd55820b559f6ac86509afb5db4dc77766433ff07e2b2ec82b3098215fa0c&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "85070", "max_time": "15.91s", "source": "slow_query", "sql_preview": "select `id` , `bill_no` , `login_name` , `before_amount` , `after_amount` , `amount` , `provider_name` , `game_name` , `wallet_type` , `reference_id` , `ref_reference_id` , `ref_reference_id2` , `roll" }, { "avg_time": "1.21s", "digest": "66c2010b01cc62f26b50c14db3529f0df49021ea2b368649e6fa50ad5517d72f", "exec_count": "1046", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=66c2010b01cc62f26b50c14db3529f0df49021ea2b368649e6fa50ad5517d72f&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "144858", "max_time": "15.91s", "source": "slow_query", "sql_preview": "update `t_seamless_log_pg` set `async_status` = ? where `id` in ( ? );" }, { "avg_time": "2.02s", "digest": "9505cacb7c710ed17125fcc6cb3669e8ddca6c8cd8af6a31f6b3cd64604c3098", "exec_count": "1003", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=9505cacb7c710ed17125fcc6cb3669e8ddca6c8cd8af6a31f6b3cd64604c3098&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "155648", "max_time": "18.01s", "source": "slow_query", "sql_preview": "commit;" }, { "avg_time": "2.56s", "digest": "1f8958548fc0cc9efedf1875a1524834095ae832dbc6f8e2baeafbba316e3cf2", "exec_count": "659", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=1f8958548fc0cc9efedf1875a1524834095ae832dbc6f8e2baeafbba316e3cf2&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "8192", "max_time": "3.29s", "source": "slow_query", "sql_preview": "show session_states;" }, { "avg_time": "1.37s", "digest": "01cc27dd8a6d7fe9081ddbb2d073a3ee64085e9bee724935e4691fd1e9b36f84", "exec_count": "574", "link": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10748116073341772391&provider=alicloud®ion=ap-southeast-1&orgName=DigiPlus%27s%20Org&orgId=1372813089209289635&projectId=1372813089454736199&clusterName=prod-c66-seamless-others&deployType=premium&version=v8.5.4#/slow_query?digest=01cc27dd8a6d7fe9081ddbb2d073a3ee64085e9bee724935e4691fd1e9b36f84&from=1774951200&to=1774959060&show_internal=true&term=", "max_mem": "16384", "max_time": "17.73s", "source": "slow_query", "sql_preview": "select @@session.transaction_read_only;" } ], "topsql": [] }, "query_or_metric_channel_observed": true, "slow_query_top_digest": "908792e63b56548d90d46345e2077cecc168cbb3a2f42baf6ef5e0a159930a05", "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": true, "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": 1774959060, "actual_start_ts": 1774951200, "expected_allowed_window_id": "workspace_observed_window", "expected_end_ts": 1774959060, "expected_start_ts": 1774951200, "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-59aa931d36344cacabb383487f68b101", "invalid_subtype": null, "judged_at": "2026-05-11T07:49:39.931548+00:00", "judgment_verdict": "fail", "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": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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-d13fad687c5f44b193d158c91bded21a", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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-1778485451230-a73e4c96", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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": "10748116073341772391", "actual_end_ts": 1774959060, "actual_start_ts": 1774951200, "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-d13fad687c5f44b193d158c91bded21a/evidences/metrics.json", "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-d13fad687c5f44b193d158c91bded21a/evidences/evidence_summary_for_agent.json" ], "description": "Evidence shows abnormal TiDB GC pressure during the incident window.", "earned_score": 8, "id": "gc_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-d13fad687c5f44b193d158c91bded21a/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "go_gc", "matcher": "json_text_contains_any", "snippet": "instances)\", \"peak\": 1.015, \"mean\": 0.536, \"unit\": \"events/s\", \"promql\": \"rate(go_gc_duration_seconds_count{component=\\\"tidb\\\"}[1m])\", \"link\": \"https://clinic.pingc", "source": "artifact_json" }, { "artifact_path": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-d13fad687c5f44b193d158c91bded21a/evidences/evidence_summary_for_agent.json", "artifacts": [ "summary_json" ], "matched": true, "matched_keyword": "GC", "matcher": "json_text_contains_any", "snippet": "y_duration_seconds_bucket[1m])) by (le, instance))\", \"link\": \"https://clinic.pingcap.com/portal/#/clusters/10748116073341772391\"}, {\"name\": \"TiDB P99 Latency\", \"m", "source": "artifact_json" } ], "snippet": "instances)\", \"peak\": 1.015, \"mean\": 0.536, \"unit\": \"events/s\", \"promql\": \"rate(go_gc_duration_seconds_count{component=\\\"tidb\\\"}[1m])\", \"link\": \"https://clinic.pingc" }, { "artifact_paths": [ "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-d13fad687c5f44b193d158c91bded21a/evidences/queries.json" ], "description": "Evidence includes heap-profile outliers and a dominant memory-retention stack.", "earned_score": 9, "id": "heap_profile_signal_present", "match": "any_of", "max_score": 9, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [ "summary_json" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "/Users/huyibin/Documents/dev/investibook/backend/data/eval_audits/evalrun-3e8725979333434fa751c2dfb9a6b21f/evalcase-d13fad687c5f44b193d158c91bded21a/evidences/queries.json", "artifacts": [ "queries" ], "matched": true, "matched_keyword": "process_keys", "matcher": "json_text_contains_any", "snippet": "min:1ms, avg: 3.8ms, p80:8ms, p95:8ms, iters:24, tasks:5}, scan_detail: {total_process_keys: 5000, total_process_keys_size: 8470825, total_keys: 5005, get_snapshot_time: 3", "source": "artifact_json" } ], "snippet": "min:1ms, avg: 3.8ms, p80:8ms, p95:8ms, iters:24, tasks:5}, scan_detail: {total_process_keys: 5000, total_process_keys_size: 8470825, total_keys: 5005, get_snapshot_time: 3" }, { "artifact_paths": [], "description": "Evidence correlates the abnormal heap path with an upstream issue or fixed release.", "earned_score": 0, "id": "known_issue_correlation_context_present", "match": "any_of", "max_score": 8, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [ "summary_json" ], "matched": false, "matched_keyword": null, "matcher": "json_text_contains_any", "snippet": null, "source": "artifact_json" }, { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "keyword_any", "snippet": null, "source": "logs" } ], "snippet": null } ], "max_score": 30, "raw_max_score": 25, "raw_score": 17, "score": 20, "status": "partial" }, "critical_evidence_verdict": "partial", "diagnosis": { "checks": [ { "description": "Identifies GC pressure and frequent allocation activity as the primary driver of tail latency.", "deterministic": { "match": "all_of", "passed": true, "rules": [ { "keywords": [ "GC pressure", "gc pause", "frequent gc", "frequent malloc", "allocation pressure", "GC 压力", "频繁 GC", "频繁 malloc" ], "matched": true, "matched_keys": [ "gc pause" ], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" }, { "keywords": [ "tail latency", "P999", "latency spike", "尾延迟" ], "matched": true, "matched_keys": [ "P999", "尾延迟" ], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": true, "earned_score": 2.0, "id": "identify_gc_pressure_as_primary_driver", "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 tail-latency primarily to TiDB CPU saturation driven by a high-frequency DELETE with an inefficient access path and scan/lock amplification; it frames GC as a secondary \"warning-level fluctuation\" rather than the main amplification path (GC pressure / frequent allocation/GC) for tail latency." ], "semantic_status": "fail" }, { "description": "Uses heap-profile stack evidence to localize the dominant problematic path.", "deterministic": { "match": "any_of", "passed": false, "rules": [ { "keywords": [ "heap profile", "dominant stack", "stack trace", "range splitting path", "range split", "split range", "heap stack", "pprof" ], "matched": false, "matched_keys": [], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": false, "earned_score": 0.0, "id": "identify_heap_profile_dominant_stack", "max_score": 3, "mode": "blended", "passed": false, "penalty_applied": 0, "required": true, "scoring_mode": "positive", "semantic_check_id": 2, "semantic_confidence": 0.9, "semantic_notes": [ "Answer does not use heap profile / dominant stack evidence to localize the issue to an internal range-split-related retention stack (or equivalent internal path). It stays at workload/query-plan level (bad plan, wide scan, CPU saturation) and explicitly treats GC as non-primary, without tying to range split internals." ], "semantic_status": "fail" }, { "description": "Mentions the concrete GitHub issue id that matches the diagnosed path.", "deterministic": { "match": "any_of", "passed": false, "rules": [ { "keywords": [], "matched": false, "matched_keys": [], "matcher": "regex_any", "path": "", "paths": [], "patterns": [ "(github|issue)\\s*#?\\d+", "issue\\s+id\\s*[:#]?\\s*\\d+", "github issue\\s*[:#]?\\s*\\d+" ], "source": "output_text" } ] }, "deterministic_pass": false, "earned_score": 0.0, "id": "mention_github_issue_id", "max_score": 3, "mode": "deterministic_only", "passed": false, "penalty_applied": 0, "required": false, "scoring_mode": "positive", "semantic_check_id": null, "semantic_confidence": null, "semantic_notes": [], "semantic_status": null }, { "description": "Recommends upgrading to a fixed version or build.", "deterministic": { "match": "any_of", "passed": false, "rules": [ { "keywords": [ "fixed release", "upgrade", "patched build", "fixed version", "升级", "修复版本" ], "matched": false, "matched_keys": [], "matcher": "keyword_any", "path": "", "paths": [], "patterns": [], "source": "output_text" } ] }, "deterministic_pass": false, "earned_score": 0.0, "id": "recommend_fixed_version_upgrade", "max_score": 4, "mode": "blended", "passed": false, "penalty_applied": 0, "required": false, "scoring_mode": "positive", "semantic_check_id": 3, "semantic_confidence": 0.82, "semantic_notes": [ "Answer provides mitigation and query/index tuning suggestions but does not recommend upgrading to a fixed/patched release or a known fixed version." ], "semantic_status": "fail" } ], "hard_gate_passed": false, "max_score": 50, "raw_score": 2.0, "score": 8, "semantic_shadow": { "available": true, "bucket": "diagnosis.semantic", "checks": [ { "bucket": "diagnosis.semantic", "check_id": 1, "confidence": 0.86, "disagreement_flags": [], "evidence": { "critical_evidence_ids": [ "gc_signal_present" ], "routed_item_ids": [ "ce-1" ] }, "max_score": 3, "mode": "shadow", "notes": [ "Answer attributes tail-latency primarily to TiDB CPU saturation driven by a high-frequency DELETE with an inefficient access path and scan/lock amplification; it frames GC as a secondary \"warning-level fluctuation\" rather than the main amplification path (GC pressure / frequent allocation/GC) for tail latency." ], "score": 0, "status": "fail" }, { "bucket": "diagnosis.semantic", "check_id": 2, "confidence": 0.9, "disagreement_flags": [], "evidence": { "critical_evidence_ids": [ "heap_profile_signal_present" ], "routed_item_ids": [ "ce-2" ] }, "max_score": 3, "mode": "shadow", "notes": [ "Answer does not use heap profile / dominant stack evidence to localize the issue to an internal range-split-related retention stack (or equivalent internal path). It stays at workload/query-plan level (bad plan, wide scan, CPU saturation) and explicitly treats GC as non-primary, without tying to range split internals." ], "score": 0, "status": "fail" }, { "bucket": "diagnosis.semantic", "check_id": 3, "confidence": 0.82, "disagreement_flags": [], "evidence": { "critical_evidence_ids": [ "known_issue_correlation_context_present" ], "routed_item_ids": [] }, "max_score": 4, "mode": "shadow", "notes": [ "Answer provides mitigation and query/index tuning suggestions but does not recommend upgrading to a fixed/patched release or a known fixed version." ], "score": 0, "status": "fail" } ], "mode": "shadow", "packet_case_id": "sql-tail-latency-spike-during-incident-window", "packet_loaded": true, "packet_notes": [], "packet_status": "ok", "status": "ok", "summary": { "disagreement_flags": [], "shadow_max_score": 10, "shadow_score": 0 } }, "status": "fail" }, "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_metric_refs_required" ], "matcher": "bool_false", "path": "analysis_metric_refs_required", "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_metric_refs_required, 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_query_refs_required" ], "matcher": "bool_false", "path": "analysis_query_refs_required", "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_query_refs_required, 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": "A TiDB internal range-splitting path retained abnormal heap under a heavy lookup workload, driving GC pressure and tail-latency spikes; the workload was a trigger rather than the full root cause", "overall_verdict": "fail", "quality_verdict": "fail", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 48, "hard_gate_passed": false, "passing_hard_gate_score_floor": 70, "raw_total_score": 48 }, "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": 1, "primary_failure_code": "critical_evidence_partial", "score": 48, "total_checks": 4 }