{ "audit": { "artifact_resolution": { "candidate_run_dirs": [ "evidences" ], "manifest_path_mismatch": false, "primary_failure_code": null, "resolution_mode": "workspace_evidence_root", "scanned_scopes": [ { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/data/workspaces/ws-eval-1784628774908-142a0c7d", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "status": "resolved" }, "case_id": "compaction-signals-on-db-tikv-9-in-saas01-during-latest-window", "contract": { "actual_cluster_id": "10989049060142230334", "cluster_scope_match": true, "expected_allowed_window_id": "saas01-db-tikv-9-bjt-2026-07-21-1100-5m", "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "time_window_match": true }, "critical_evidence_verdict": "partial", "evidence_collection_verdict": "pass", "evidence_routing_verdict": "pass", "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "execution_contract_verdict": "pass", "overall_verdict": "fail", "quality_verdict": "pass", "semantic_shadow": { "available": false, "status": "not_available" }, "source": "deterministic_judge", "strategy": "deterministic_trace_heavy_v1", "workflow_verdict": "pass" }, "case_run_id": "evalcase-eb1a19c81bb149f2ad312c3eda9a9419", "facts": { "artifact_observations": { "analysis_patch_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "artifacts": { "analysis_patch_path": "", "diagnosis_report_path": "evidences/workspace_evidence_report.json", "evidence_dir": "evidences", "logs_dir": "", "manifest_path": "", "manifest_path_mismatch": false, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "source_root": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419", "source_scope": "audit_dir", "summary_txt_path": "", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "compaction-signals-on-db-tikv-9-in-saas01-during-latest-window", "cluster": { "actual_cluster_id": "10989049060142230334", "allowed_cluster_ids": [ "10989049060142230334" ], "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "matched": true }, "contract": { "actual_cluster_id": "10989049060142230334", "cluster_scope_match": true, "expected_allowed_window_id": "saas01-db-tikv-9-bjt-2026-07-21-1100-5m", "expected_cluster_id": "10989049060142230334", "expected_parent_id": "", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "pending_compaction_metric_present", "l0_files_metric_present", "target_node_evidence_present", "metric_series_nonempty", "output_cluster_id_matches_reference", "output_tikv_node_matches_reference", "output_window_start_matches_reference", "output_window_end_matches_reference", "evidence_sufficient_matches_reference", "write_cf_pending_compaction_matches_reference", "lock_cf_pending_compaction_matches_reference", "write_cf_l0_files_matches_reference", "lock_cf_l0_files_matches_reference" ] }, "evidence": { "analysis_patch_path": "", "core_evidence_bundle_present": false, "decoded_plan_indexes_used": null, "events_attempted_implies_artifact_present": true, "events_channel_observed": true, "events_collection_attempted": false, "events_output_file_present": false, "hotspot_detected": false, "infra_clear": false, "kill_query_signal_present": false, "log_error_counts": {}, "logs_channel_observed": false, "logs_dir_present": false, "memory_tracker_panic_present": false, "metric_evidence": [ { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "tikv_engine_pending_compaction_bytes{instance=~\"db-tikv-9.*\"}", "start": 1784602800, "step": "15" }, "group": "tikv_pending_compaction_bytes_tikv9", "id": "tikv_pending_compaction_bytes_tikv9", "metric_group_id": "tikv_pending_compaction_bytes_tikv9", "name": "tikv_pending_compaction_bytes_tikv9", "promql": "tikv_engine_pending_compaction_bytes{instance=~\"db-tikv-9.*\"}", "ref": { "metric_group_id": "tikv_pending_compaction_bytes_tikv9", "type": "metric" }, "series_summaries": [ { "avg": 714910502.2380953, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 3446258045.0, "min": 0.0, "point_count": 21 }, { "avg": 245644265.9047619, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 3165561732.0, "min": 0.0, "point_count": 21 }, { "avg": 243480167.0, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 3196456340.0, "min": 0.0, "point_count": 21 }, { "avg": 554408061.2857143, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 3764236993.0, "min": 0.0, "point_count": 21 }, { "avg": 8881435.761904761, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 34343645.0, "min": 0.0, "point_count": 21 }, { "avg": 6011106.380952381, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 33085773.0, "min": 0.0, "point_count": 21 }, { "avg": 10512024.42857143, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 37422014.0, "min": 0.0, "point_count": 21 }, { "avg": 6819798.238095238, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 17807274.0, "min": 0.0, "point_count": 21 }, { "avg": 0.0, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 0.0, "min": 0.0, "point_count": 21 }, { "avg": 0.0, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 0.0, "min": 0.0, "point_count": 21 }, { "avg": 5570424.0, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 116978904.0, "min": 0.0, "point_count": 21 }, { "avg": 6344674.857142857, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 133238172.0, "min": 0.0, "point_count": 21 }, { "avg": 9800791705.761906, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 17669078025.0, "min": 49017281.0, "point_count": 21 }, { "avg": 8556731795.809524, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 15018016612.0, "min": 0.0, "point_count": 21 }, { "avg": 9311331039.0, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 15962356644.0, "min": 0.0, "point_count": 21 }, { "avg": 10186925472.761906, "labels": { "__name__": "tikv_engine_pending_compaction_bytes", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 18148388833.0, "min": 0.0, "point_count": 21 } ], "summary": { "avg": 2478647654.589286, "max": 18148388833.0, "min": 0.0, "point_count": 336, "series_count": 16 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "15" }, "unit": "" }, { "chart_data_ref": { "cluster_id": "10989049060142230334", "end": 1784603100, "kind": "promql_range", "promql": "tikv_engine_num_files_at_level{instance=~\"db-tikv-9.*\",level=\"0\"}", "start": 1784602800, "step": "15" }, "group": "tikv_l0_files_tikv9", "id": "tikv_l0_files_tikv9", "metric_group_id": "tikv_l0_files_tikv9", "name": "tikv_l0_files_tikv9", "promql": "tikv_engine_num_files_at_level{instance=~\"db-tikv-9.*\",level=\"0\"}", "ref": { "metric_group_id": "tikv_l0_files_tikv9", "type": "metric" }, "series_summaries": [ { "avg": 2.238095238095238, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 0.0, "point_count": 21 }, { "avg": 1.4761904761904763, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 0.0, "point_count": 21 }, { "avg": 1.7142857142857142, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 0.0, "point_count": 21 }, { "avg": 2.5238095238095237, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "default", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 1.0, "point_count": 21 }, { "avg": 1.0952380952380953, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 0.0, "point_count": 21 }, { "avg": 0.8095238095238095, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 4.0, "min": 0.0, "point_count": 21 }, { "avg": 1.2380952380952381, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 5.0, "min": 0.0, "point_count": 21 }, { "avg": 0.9047619047619048, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "lock", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 2.0, "min": 0.0, "point_count": 21 }, { "avg": 0.0, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 0.0, "min": 0.0, "point_count": 21 }, { "avg": 0.0, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 0.0, "min": 0.0, "point_count": 21 }, { "avg": 0.047619047619047616, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 1.0, "min": 0.0, "point_count": 21 }, { "avg": 0.047619047619047616, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "raft", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 1.0, "min": 0.0, "point_count": 21 }, { "avg": 3.857142857142857, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-9", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 8.0, "min": 0.0, "point_count": 21 }, { "avg": 4.428571428571429, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-90", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 9.0, "min": 1.0, "point_count": 21 }, { "avg": 4.333333333333333, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-91", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 8.0, "min": 0.0, "point_count": 21 }, { "avg": 4.428571428571429, "labels": { "__name__": "tikv_engine_num_files_at_level", "cf": "write", "cluster": "db", "cluster_id": "tidb10989049060142230334", "component": "tikv", "db": "kv", "instance": "db-tikv-92", "job": "tidb10989049060142230334-db-tikv", "kubernetes_namespace": "tidb10989049060142230334", "level": "0", "project": "1372813089454544954", "prometheus": "tidb10989049060142230334/o11y-vmagent", "seed_provider": "aws", "seed_region": "us-east-1", "shoot_infra": "aws", "shoot_name": "prod-1372813089454544954-eks-us-east-1-17f21136", "tenant": "1372813089209061633", "tidb_cluster": "tidb10989049060142230334-db", "tidb_cluster_id": "10989049060142230334" }, "max": 8.0, "min": 0.0, "point_count": 21 } ], "summary": { "avg": 1.8214285714285714, "max": 9.0, "min": 0.0, "point_count": 336, "series_count": 16 }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "15" }, "unit": "" } ], "panic_signal_artifact_present": false, "query_evidence": { "slow_query": [], "topsql": [] }, "query_or_metric_channel_observed": true, "slow_query_top_digest": "", "ticket_context_channel_observed": false, "topsql_collection_error_recorded": false }, "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "output": { "analyze_primary_culprit_asserted": false, "claims_panic_not_confirmable": false, "diagnosis_cpu_hotspot_asserted": false, "diagnosis_kill_query_chain_asserted": false, "diagnosis_memory_tracker_panic_asserted": false, "diagnosis_plan_stats_issue_asserted": false, "diagnosis_single_instance_panic_restart_asserted": false, "fake_alarm_primary_asserted": false, "focuses_on_missing_index": false, "mentions_cpu_saturation": false, "mentions_est_act_divergence": false, "mentions_idle_transaction": false, "mentions_intermediate_result_explosion": false, "mentions_kill_query": false, "mentions_memory_tracker_consume": false, "mentions_p99_latency_spike": false, "mentions_rollback_cleanup": false, "mentions_statistics_uninitialized": false, "mentions_v8_5_2": false, "mentions_v8_5_3_or_fixed_release": false, "mentions_without_fix": false, "missing_index_primary_root_cause_asserted": false, "puller_or_source_side_primary_root_cause_asserted": false, "query_only_primary_root_cause_asserted": false, "wide_scan_primary_root_cause_asserted": false }, "routing": { "analysis_event_items_present": false, "analysis_has_key_evidence": false, "analysis_has_supporting_evidence": false, "analysis_items_shape_valid": false, "analysis_log_items_present": false, "analysis_log_or_event_channel_resolvable": true, "analysis_metric_refs_required": false, "analysis_metric_refs_resolvable": true, "analysis_patch_present": false, "analysis_patch_valid_json": false, "analysis_query_refs_required": false, "analysis_query_refs_resolvable": true, "classification_contract_valid": false, "diagnosis_analyst_contract_present": false, "fault_classification_contract_valid": false, "primary_fault_class_component_restart_or_panic": false, "primary_fault_class_resource_control_or_capacity": false, "primary_fault_class_service_unavailability_or_worker_failure": false, "primary_fault_class_sql_plan_or_query": false, "primary_fault_class_storage_or_infra_io": false, "primary_fault_class_tidb_cpu_gc_or_memory": false, "primary_fault_class_tikv_read_hotspot": false, "primary_fault_class_unknown_insufficient_evidence": false, "selected_diagnosis_skills_present": false, "signal_tags_contract_valid": false }, "runtime_context_present": true, "window": { "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "expected_allowed_window_id": "saas01-db-tikv-9-bjt-2026-07-21-1100-5m", "expected_end_ts": 1784603100, "expected_start_ts": 1784602800, "matched_allowed_window": true }, "workflow": { "architecture_context_loaded": false, "collect_evidence_invoked": false, "diagnosis_run_initialized": true, "direct_conclusion_by_investigator": false, "evidence_collection_completed": true, "evidence_collection_started": false, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": false, "premise_verification_recorded": false, "summary_read_completed": false, "targeted_panic_log_query_completed": false } }, "id": "evaljudge-a16cae5c567a40b6b98fbd491213d35a", "invalid_subtype": null, "judged_at": "2026-07-21T10:13:58.346632+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": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "resolved", "selected": true, "source_kind": "audit_dir", "source_root": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true } ], "decision": "skipped_lower_priority", "selected": false, "source_kind": "workspace_dir", "source_root": "/data/workspaces/ws-eval-1784628774908-142a0c7d", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "selected_scope": "audit_dir", "selected_trace_candidate": { "actual_cluster_id": "10989049060142230334", "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "analysis_patch_path": "", "analysis_patch_present": false, "diagnosis_report_path": "evidences/workspace_evidence_report.json", "diagnosis_report_present": true, "evidence_dir": "evidences", "evidence_dir_present": true, "invalid_reasons": [], "logs_dir": "", "logs_dir_present": false, "manifest_path": "", "manifest_path_mismatch": false, "manifest_path_mismatch_fields": [], "manifest_present": false, "manifest_valid_json": true, "resolution_mode": "workspace_evidence_root", "run_dir": "evidences", "summary_json_path": "", "summary_json_present": false, "summary_txt_path": "", "summary_txt_present": false, "valid_bundle": true }, "status": "resolved" }, "contract": { "checks": [ { "description": "Actual diagnosis cluster scope matches the expected cluster id.", "id": "cluster_scope_match", "match": "all_of", "passed": true, "required": true, "rules": [ { "allowed": [], "matched": true, "matched_keys": [ "cluster_scope_match" ], "matcher": "bool_true", "path": "cluster_scope_match", "source": "trace_fact", "value": "" } ], "snippet": "matched trace facts: cluster_scope_match" } ], "status": "pass" }, "critical_evidence": { "checks": [ { "artifact_paths": [ "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json" ], "description": "Evidence includes TiKV pending compaction byte metrics.", "earned_score": 4, "id": "pending_compaction_metric_present", "match": "any_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "tikv_engine_pending_compaction_bytes", "matcher": "json_text_contains_any", "snippet": "paction_bytes_tikv9\", \"name\": \"tikv_pending_compaction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\":", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "tikv_engine_pending_compaction_bytes", "matcher": "json_text_contains_any", "snippet": "paction_bytes_tikv9\", \"name\": \"tikv_pending_compaction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\":", "source": "artifact_json" } ], "snippet": "paction_bytes_tikv9\", \"name\": \"tikv_pending_compaction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\":" }, { "artifact_paths": [ "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json" ], "description": "Evidence includes TiKV L0 SST file count metrics.", "earned_score": 4, "id": "l0_files_metric_present", "match": "any_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "tikv_engine_num_files_at_level", "matcher": "json_text_contains_any", "snippet": "ric_group_id\": \"tikv_l0_files_tikv9\", \"name\": \"tikv_l0_files_tikv9\", \"promql\": \"tikv_engine_num_files_at_level{instance=~\\\"db-tikv-9.*\\\",level=\\\"0\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\":", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "tikv_engine_num_files_at_level", "matcher": "json_text_contains_any", "snippet": "ric_group_id\": \"tikv_l0_files_tikv9\", \"name\": \"tikv_l0_files_tikv9\", \"promql\": \"tikv_engine_num_files_at_level{instance=~\\\"db-tikv-9.*\\\",level=\\\"0\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\":", "source": "artifact_json" } ], "snippet": "ric_group_id\": \"tikv_l0_files_tikv9\", \"name\": \"tikv_l0_files_tikv9\", \"promql\": \"tikv_engine_num_files_at_level{instance=~\\\"db-tikv-9.*\\\",level=\\\"0\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\":" }, { "artifact_paths": [ "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json" ], "description": "Evidence references the target TiKV node identity.", "earned_score": 4, "id": "target_node_evidence_present", "match": "any_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "db-tikv-9", "matcher": "json_text_contains_any", "snippet": "ction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\": 0.0, \"max\": 181483888", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "db-tikv-9", "matcher": "json_text_contains_any", "snippet": "ction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\": 0.0, \"max\": 181483888", "source": "artifact_json" } ], "snippet": "ction_bytes_tikv9\", \"promql\": \"tikv_engine_pending_compaction_bytes{instance=~\\\"db-tikv-9.*\\\"}\", \"unit\": \"\", \"summary\": {\"point_count\": 336, \"min\": 0.0, \"max\": 181483888" }, { "artifact_paths": [ "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json" ], "description": "Metric evidence includes at least one non-empty time-series payload instead of an all-empty metrics bundle.", "earned_score": 4, "id": "metric_series_nonempty", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": null, "matcher": "json_values_nonempty", "snippet": "[[1784602800, \"0\"], [1784602815, \"0\"], [1784602830, \"3172173767\"], [1784602845, \"3172173767\"], [1784602860, \"955111818\"], [1784602875, \"142641384\"], [1784602890, \"0\"], [1784602905, \"0\"], [1784602920, \"0\"], [1784602935, \"0\"], [1784602950, \"0", "source": "artifact_json" } ], "snippet": "[[1784602800, \"0\"], [1784602815, \"0\"], [1784602830, \"3172173767\"], [1784602845, \"3172173767\"], [1784602860, \"955111818\"], [1784602875, \"142641384\"], [1784602890, \"0\"], [1784602905, \"0\"], [1784602920, \"0\"], [1784602935, \"0\"], [1784602950, \"0" }, { "artifact_paths": [], "description": "Evidence must not use a broad instance regex that can pull db-tikv-90/91/92 into db-tikv-9 analysis.", "earned_score": 0, "id": "broad_instance_regex_absent", "match": "all_of", "max_score": 6, "passed": false, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": false, "matched_keyword": "instance=~\"db-tikv-9.*\"", "matcher": "json_values_not_contains_any", "snippet": "tikv_engine_pending_compaction_bytes{instance=~\"db-tikv-9.*\"}", "source": "artifact_json" } ], "snippet": null }, { "artifact_paths": [], "description": "Output JSON cluster_id matches the runtime reference.", "earned_score": 6, "id": "output_cluster_id_matches_reference", "match": "all_of", "max_score": 6, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"10989049060142230334\"", "source": "output_json" } ], "snippet": "\"10989049060142230334\"" }, { "artifact_paths": [], "description": "Output JSON tikv_node matches the runtime reference.", "earned_score": 6, "id": "output_tikv_node_matches_reference", "match": "all_of", "max_score": 6, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"db-tikv-9\"", "source": "output_json" } ], "snippet": "\"db-tikv-9\"" }, { "artifact_paths": [], "description": "Output JSON window.start matches the runtime reference.", "earned_score": 5, "id": "output_window_start_matches_reference", "match": "all_of", "max_score": 5, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:00:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:00:00Z\"" }, { "artifact_paths": [], "description": "Output JSON window.end matches the runtime reference.", "earned_score": 5, "id": "output_window_end_matches_reference", "match": "all_of", "max_score": 5, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:05:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:05:00Z\"" }, { "artifact_paths": [], "description": "Output JSON evidence_sufficient matches the runtime reference.", "earned_score": 4, "id": "evidence_sufficient_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "true", "source": "output_json" } ], "snippet": "true" }, { "artifact_paths": [], "description": "Output JSON write_cf pending compaction bytes match the runtime reference.", "earned_score": 8, "id": "write_cf_pending_compaction_matches_reference", "match": "all_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "17669078025", "source": "output_json" } ], "snippet": "17669078025" }, { "artifact_paths": [], "description": "Output JSON lock_cf pending compaction bytes match the runtime reference.", "earned_score": 8, "id": "lock_cf_pending_compaction_matches_reference", "match": "all_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "34343645", "source": "output_json" } ], "snippet": "34343645" }, { "artifact_paths": [], "description": "Output JSON write_cf L0 file count matches the runtime reference.", "earned_score": 8, "id": "write_cf_l0_files_matches_reference", "match": "all_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "8", "source": "output_json" } ], "snippet": "8" }, { "artifact_paths": [], "description": "Output JSON lock_cf L0 file count matches the runtime reference.", "earned_score": 8, "id": "lock_cf_l0_files_matches_reference", "match": "all_of", "max_score": 8, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "4", "source": "output_json" } ], "snippet": "4" } ], "max_score": 80, "raw_max_score": 80, "raw_score": 74, "score": 74, "status": "partial" }, "critical_evidence_verdict": "partial", "diagnosis": { "checks": [ { "description": "identify_known_bug_63956", "id": "identify_known_bug_63956", "passed": false, "snippet": null }, { "description": "identify_kill_query_idle_txn_chain", "id": "identify_kill_query_idle_txn_chain", "passed": false, "snippet": null }, { "description": "identify_version_without_fix", "id": "identify_version_without_fix", "passed": false, "snippet": null }, { "description": "recommend_fixed_version_upgrade", "id": "recommend_fixed_version_upgrade", "passed": false, "snippet": null } ], "hard_gate_passed": true, "max_score": 0, "raw_score": 0, "score": 0, "semantic_shadow": { "available": false, "checks": [], "packet_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-eb1a19c81bb149f2ad312c3eda9a9419/semantic_packet_v1.json", "reason": "semantic_packet_missing", "status": "not_available", "summary": { "disagreement_flags": [], "shadow_max_score": 0, "shadow_score": 0 } }, "status": "pass" }, "evidence_collection": { "checks": [ { "description": "Workspace diagnosis report is present and readable.", "earned_score": 2, "id": "required_report_present", "match": "all_of", "max_score": 2, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched collection facts: diagnosis_report_present" }, { "description": "Query or metric evidence is observed for this ad-hoc request.", "earned_score": 3, "id": "query_or_metric_channel_observed", "match": "all_of", "max_score": 3, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched collection facts: query_or_metric" }, { "description": "If an events collection query is attempted, an events output file is persisted even when the result set is empty.", "earned_score": 2, "id": "attempted_events_collection_persisted", "match": "all_of", "max_score": 2, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "events_attempted_implies_artifact_present" ], "matcher": "bool_true", "path": "events_attempted_implies_artifact_present", "paths": [], "source": "evidence_fact", "threshold": null } ], "snippet": "matched collection facts: events_attempted_implies_artifact_present" } ], "max_score": 5, "raw_max_score": 7, "raw_score": 7, "score": 5, "status": "pass" }, "evidence_collection_verdict": "pass", "evidence_routing": { "checks": [ { "description": "Analysis patch is only required to be valid when it exists.", "earned_score": 0, "id": "analysis_patch_valid_when_present", "match": "any_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "analysis_patch_present" ], "matcher": "bool_false", "path": "analysis_patch_present", "paths": [], "source": "routing_fact" }, { "matched": false, "matched_keys": [], "matcher": "bool_true", "path": "analysis_patch_valid_json", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" } ], "max_score": 0, "raw_max_score": 0, "raw_score": 0, "score": 0, "status": "pass" }, "evidence_routing_verdict": "pass", "execution_contract": { "artifact_facts": { "analysis_patch_present": false, "core_evidence_bundle_present": false, "diagnosis_report_present": true, "summary_artifact_present": false, "supplemental_loki_present": false }, "channel_facts": { "events": true, "logs": false, "query_or_metric": true, "ticket_context": false }, "checks": [ { "description": "The minimal ad-hoc workflow is present.", "id": "required_workflow_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "subset_observed", "path": "", "paths": [ "final_answer_emitted" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "id": "collect_evidence_not_used", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_not_used" ], "matcher": "subset_observed", "path": "", "paths": [ "collect_evidence_not_used" ], "source": "workflow_check", "threshold": null } ], "snippet": "matched execution contract facts: collect_evidence_not_used" }, { "description": "Workspace diagnosis report is present.", "id": "required_report_present", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched execution contract facts: diagnosis_report_present" }, { "description": "At least one query or metric evidence channel is observed.", "id": "query_or_metric_channel_observed", "match": "all_of", "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched execution contract facts: query_or_metric" } ], "status": "pass", "workflow_facts": { "collect_evidence_not_used": true, "final_answer_emitted": true } }, "execution_contract_verdict": "pass", "ground_truth_root_cause": "Correctly evaluating compaction pressure for this case requires exact single-node TiKV metric scope for db-tikv-9 rather than cluster-wide aggregation or over-broad regex matching.", "overall_verdict": "fail", "quality_verdict": "pass", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 69, "hard_gate_passed": false, "normalized_total_score": 93, "passing_hard_gate_score_floor": 70, "raw_total_score": 79, "total_max_score": 85 }, "strategy": "deterministic_trace_heavy_v1", "workflow": { "checks": [ { "description": "Final answer is emitted for the ad-hoc query.", "earned_score": 0, "id": "final_answer_emitted", "match": "all_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "final_answer_emitted" ], "matcher": "bool_true", "path": "final_answer_emitted", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: final_answer_emitted" }, { "description": "This ad-hoc case must not invoke collect_evidence.py.", "earned_score": 0, "id": "collect_evidence_not_used", "match": "all_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "collect_evidence_invoked" ], "matcher": "bool_false", "path": "collect_evidence_invoked", "paths": [], "source": "workflow_fact", "threshold": null } ], "snippet": "matched workflow facts: collect_evidence_invoked" } ], "max_score": 0, "raw_max_score": 0, "raw_score": 0, "score": 0, "status": "pass" }, "workflow_verdict": "pass" }, "passed_checks": 0, "primary_failure_code": "critical_evidence_partial", "score": 69, "total_checks": 0 }