{ "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": "10518506906906971664", "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-a4e7b424827349fabb737e1ee940fccf", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10518506906906971664", "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-1784628476449-a1d374b1", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10518506906906971664", "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": "10518506906906971664", "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": "topsql-links-for-hottest-two-tikv-nodes-during-incident-window", "contract": { "actual_cluster_id": "10518506906906971664", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10518506906906971664", "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-a4e7b424827349fabb737e1ee940fccf", "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-a4e7b424827349fabb737e1ee940fccf", "source_scope": "audit_dir", "summary_txt_path": "", "telemetry_path": ".opencode/telemetry.log" }, "case_id": "topsql-links-for-hottest-two-tikv-nodes-during-incident-window", "cluster": { "actual_cluster_id": "10518506906906971664", "allowed_cluster_ids": [ "10518506906906971664" ], "expected_cluster_id": "10518506906906971664", "expected_parent_id": "", "matched": true }, "contract": { "actual_cluster_id": "10518506906906971664", "cluster_scope_match": true, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_cluster_id": "10518506906906971664", "expected_parent_id": "", "time_window_match": true }, "critical_evidence": { "configured": true, "matched_check_ids": [ "raw_disk_read_metric_present", "cluster_scoped_mapping_evidence_present", "output_cluster_id_matches_reference", "output_window_start_matches_reference", "output_window_end_matches_reference", "mapping_strategy_matches_reference", "evidence_sufficient_matches_reference", "topsql_links_present", "topsql_links_have_two_unique_tikv_nodes" ] }, "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": "10518506906906971664", "end": 1784603100, "kind": "promql_range", "promql": "client-side join: sum by (instance) (rate(node_disk_reads_completed_total{instance=~\".*\",device!~\"dm.*\"}[60s])) -> kube_pod_info namespace=tidb10518506906906971664", "start": 1784602800, "step": "60" }, "group": "tikv_read_iops_for_topsql_links", "id": "tikv_read_iops_for_topsql_links", "metric_group_id": "tikv_read_iops_for_topsql_links", "name": "tikv_read_iops_for_topsql_links", "promql": "client-side join: sum by (instance) (rate(node_disk_reads_completed_total{instance=~\".*\",device!~\"dm.*\"}[60s])) -> kube_pod_info namespace=tidb10518506906906971664", "ref": { "metric_group_id": "tikv_read_iops_for_topsql_links", "type": "metric" }, "series_summaries": [ { "avg": 5073.758333333334, "labels": { "instance": "ip-172-26-1-42.ec2.internal", "pod": "db-tikv-25" }, "max": 6462.75, "min": 2094.0, "point_count": 6 }, { "avg": 5537.61111111111, "labels": { "instance": "ip-172-26-10-204.ec2.internal", "pod": "db-tikv-33" }, "max": 7756.066666666667, "min": 2323.8333333333335, "point_count": 6 }, { "avg": 7615.066666666667, "labels": { "instance": "ip-172-26-11-99.ec2.internal", "pod": "db-tikv-52" }, "max": 10683.7, "min": 3025.633333333333, "point_count": 6 }, { "avg": 6976.73611111111, "labels": { "instance": "ip-172-26-129-172.ec2.internal", "pod": "db-tikv-18" }, "max": 9303.283333333333, "min": 2822.7166666666667, "point_count": 6 }, { "avg": 5518.391666666666, "labels": { "instance": "ip-172-26-129-220.ec2.internal", "pod": "db-tikv-8" }, "max": 6729.55, "min": 2358.8, "point_count": 6 }, { "avg": 5395.597222222223, "labels": { "instance": "ip-172-26-129-38.ec2.internal", "pod": "db-tikv-2" }, "max": 7141.383333333333, "min": 2341.3, "point_count": 6 }, { "avg": 6125.480555555555, "labels": { "instance": "ip-172-26-130-16.ec2.internal", "pod": "db-tikv-32" }, "max": 7916.2, "min": 2578.116666666667, "point_count": 6 }, { "avg": 5496.433333333333, "labels": { "instance": "ip-172-26-132-70.ec2.internal", "pod": "db-tikv-3" }, "max": 6607.716666666666, "min": 2247.233333333333, "point_count": 6 }, { "avg": 5513.4944444444445, "labels": { "instance": "ip-172-26-133-35.ec2.internal", "pod": "db-tikv-17" }, "max": 7467.116666666667, "min": 2356.016666666667, "point_count": 6 }, { "avg": 5909.783333333333, "labels": { "instance": "ip-172-26-134-135.ec2.internal", "pod": "db-tikv-27" }, "max": 7623.0, "min": 2370.233333333333, "point_count": 6 }, { "avg": 6842.394444444445, "labels": { "instance": "ip-172-26-134-44.ec2.internal", "pod": "db-tikv-44" }, "max": 8388.883333333333, "min": 2608.75, "point_count": 6 }, { "avg": 5950.202777777778, "labels": { "instance": "ip-172-26-135-197.ec2.internal", "pod": "db-tikv-23" }, "max": 7678.866666666667, "min": 2439.75, "point_count": 6 }, { "avg": 8288.705555555556, "labels": { "instance": "ip-172-26-14-182.ec2.internal", "pod": "db-tikv-48" }, "max": 10135.366666666667, "min": 3035.25, "point_count": 6 }, { "avg": 5711.358333333334, "labels": { "instance": "ip-172-26-145-60.ec2.internal", "pod": "db-tikv-47" }, "max": 7413.133333333333, "min": 2149.366666666667, "point_count": 6 }, { "avg": 6458.433333333333, "labels": { "instance": "ip-172-26-147-197.ec2.internal", "pod": "db-tikv-11" }, "max": 7724.05, "min": 3234.516666666667, "point_count": 6 }, { "avg": 5724.2, "labels": { "instance": "ip-172-26-147-201.ec2.internal", "pod": "db-tikv-24" }, "max": 6784.083333333333, "min": 2318.4666666666667, "point_count": 6 }, { "avg": 6288.558333333333, "labels": { "instance": "ip-172-26-148-232.ec2.internal", "pod": "db-tikv-39" }, "max": 8893.55, "min": 2125.733333333333, "point_count": 6 }, { "avg": 5983.938888888889, "labels": { "instance": "ip-172-26-152-177.ec2.internal", "pod": "db-tikv-34" }, "max": 7883.2, "min": 2486.766666666667, "point_count": 6 }, { "avg": 5829.216666666667, "labels": { "instance": "ip-172-26-154-159.ec2.internal", "pod": "db-tikv-14" }, "max": 8306.1, "min": 2404.616666666667, "point_count": 6 }, { "avg": 5258.3388888888885, "labels": { "instance": "ip-172-26-157-19.ec2.internal", "pod": "db-tikv-90" }, "max": 6615.783333333333, "min": 2027.4666666666667, "point_count": 6 }, { "avg": 5888.2138888888885, "labels": { "instance": "ip-172-26-158-162.ec2.internal", "pod": "db-tikv-36" }, "max": 7340.716666666666, "min": 2241.9, "point_count": 6 }, { "avg": 5637.441666666667, "labels": { "instance": "ip-172-26-159-232.ec2.internal", "pod": "db-tikv-51" }, "max": 6568.766666666666, "min": 2299.7166666666667, "point_count": 6 }, { "avg": 7059.877777777777, "labels": { "instance": "ip-172-26-159-67.ec2.internal", "pod": "db-tikv-49" }, "max": 8723.3, "min": 2794.4166666666665, "point_count": 6 }, { "avg": 5423.305555555556, "labels": { "instance": "ip-172-26-19-36.ec2.internal", "pod": "db-tikv-15" }, "max": 7081.883333333333, "min": 2930.6, "point_count": 6 }, { "avg": 6448.125, "labels": { "instance": "ip-172-26-20-145.ec2.internal", "pod": "db-tikv-30" }, "max": 8119.2, "min": 2392.766666666667, "point_count": 6 }, { "avg": 5609.733333333334, "labels": { "instance": "ip-172-26-21-48.ec2.internal", "pod": "db-tikv-7" }, "max": 6625.55, "min": 2561.3, "point_count": 6 }, { "avg": 5809.747222222223, "labels": { "instance": "ip-172-26-22-37.ec2.internal", "pod": "db-tikv-42" }, "max": 7424.283333333334, "min": 2493.6833333333334, "point_count": 6 }, { "avg": 5504.836111111111, "labels": { "instance": "ip-172-26-23-203.ec2.internal", "pod": "db-tikv-9" }, "max": 7126.549999999999, "min": 2119.6833333333334, "point_count": 6 }, { "avg": 6730.555555555556, "labels": { "instance": "ip-172-26-24-244.ec2.internal", "pod": "db-tikv-38" }, "max": 8851.433333333332, "min": 2527.3333333333335, "point_count": 6 }, { "avg": 5960.877777777777, "labels": { "instance": "ip-172-26-25-229.ec2.internal", "pod": "db-tikv-21" }, "max": 7590.383333333333, "min": 2835.85, "point_count": 6 }, { "avg": 5291.952777777778, "labels": { "instance": "ip-172-26-26-50.ec2.internal", "pod": "db-tikv-40" }, "max": 6438.916666666666, "min": 2433.8333333333335, "point_count": 6 }, { "avg": 5447.530555555556, "labels": { "instance": "ip-172-26-29-36.ec2.internal", "pod": "db-tikv-45" }, "max": 6842.833333333333, "min": 2660.733333333333, "point_count": 6 }, { "avg": 5530.349999999999, "labels": { "instance": "ip-172-26-30-5.ec2.internal", "pod": "db-tikv-28" }, "max": 6831.3, "min": 2662.2, "point_count": 6 }, { "avg": 5281.863888888889, "labels": { "instance": "ip-172-26-6-168.ec2.internal", "pod": "db-tikv-0" }, "max": 6759.916666666667, "min": 2231.4, "point_count": 6 }, { "avg": 5679.063888888889, "labels": { "instance": "ip-172-26-6-57.ec2.internal", "pod": "db-tikv-5" }, "max": 7382.366666666667, "min": 2256.55, "point_count": 6 }, { "avg": 7425.236111111112, "labels": { "instance": "ip-172-26-65-24.ec2.internal", "pod": "db-tikv-26" }, "max": 9419.616666666667, "min": 3238.516666666667, "point_count": 6 }, { "avg": 4833.133333333333, "labels": { "instance": "ip-172-26-67-218.ec2.internal", "pod": "db-tikv-41" }, "max": 5935.6, "min": 2432.2, "point_count": 6 }, { "avg": 4472.491666666667, "labels": { "instance": "ip-172-26-67-42.ec2.internal", "pod": "db-tikv-53" }, "max": 5643.533333333334, "min": 1851.4333333333334, "point_count": 6 }, { "avg": 4790.147222222223, "labels": { "instance": "ip-172-26-70-63.ec2.internal", "pod": "db-tikv-46" }, "max": 6686.05, "min": 1872.85, "point_count": 6 }, { "avg": 5144.044444444445, "labels": { "instance": "ip-172-26-71-125.ec2.internal", "pod": "db-tikv-31" }, "max": 6776.3, "min": 1824.7333333333333, "point_count": 6 }, { "avg": 6246.275000000001, "labels": { "instance": "ip-172-26-71-33.ec2.internal", "pod": "db-tikv-37" }, "max": 8065.783333333334, "min": 2518.616666666667, "point_count": 6 }, { "avg": 5171.783333333334, "labels": { "instance": "ip-172-26-72-246.ec2.internal", "pod": "db-tikv-35" }, "max": 6347.533333333334, "min": 2573.516666666667, "point_count": 6 }, { "avg": 4828.427777777778, "labels": { "instance": "ip-172-26-73-201.ec2.internal", "pod": "db-tikv-6" }, "max": 6468.45, "min": 2184.5, "point_count": 6 }, { "avg": 4753.76388888889, "labels": { "instance": "ip-172-26-74-14.ec2.internal", "pod": "db-tikv-16" }, "max": 6158.25, "min": 2365.55, "point_count": 6 }, { "avg": 5059.102777777778, "labels": { "instance": "ip-172-26-74-217.ec2.internal", "pod": "db-tikv-4" }, "max": 6932.85, "min": 2167.0666666666666, "point_count": 6 }, { "avg": 5150.075, "labels": { "instance": "ip-172-26-77-125.ec2.internal", "pod": "db-tikv-50" }, "max": 6099.516666666666, "min": 2324.2, "point_count": 6 }, { "avg": 5892.938888888889, "labels": { "instance": "ip-172-26-77-38.ec2.internal", "pod": "db-tikv-10" }, "max": 7283.266666666666, "min": 2019.95, "point_count": 6 }, { "avg": 5395.052777777778, "labels": { "instance": "ip-172-26-78-179.ec2.internal", "pod": "db-tikv-22" }, "max": 7160.966666666666, "min": 2160.5333333333333, "point_count": 6 }, { "avg": 7857.455555555555, "labels": { "instance": "ip-172-26-8-44.ec2.internal", "pod": "db-tikv-20" }, "max": 10664.55, "min": 2782.4333333333334, "point_count": 6 }, { "avg": 5310.3388888888885, "labels": { "instance": "ip-172-26-8-68.ec2.internal", "pod": "db-tikv-13" }, "max": 7278.05, "min": 2160.9, "point_count": 6 } ], "summary": { "avg": 5726.584307992202, "max": 10683.7, "min": 1758.85, "point_count": 342, "series_count": 57, "top_series": [ { "avg": 8288.705555555556, "labels": { "instance": "ip-172-26-14-182.ec2.internal", "pod": "db-tikv-48" }, "max": 10135.366666666667, "min": 3035.25, "point_count": 6 }, { "avg": 7857.455555555555, "labels": { "instance": "ip-172-26-8-44.ec2.internal", "pod": "db-tikv-20" }, "max": 10664.55, "min": 2782.4333333333334, "point_count": 6 } ], "topsql_links": [ { "avg_read_iops": 8288.705555555556, "metric_labels": { "instance": "ip-172-26-14-182.ec2.internal", "pod": "db-tikv-48" }, "tikv_instance": "db-tikv-48.db-tikv-peer.tidb10518506906906971664.svc:20160", "tikv_node": "db-tikv-48", "url": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10518506906906971664&provider=aws®ion=us-east-1&orgName=Buffet%27s%20Org&orgId=1372813089209061633&projectId=1372813089454544954&clusterName=prod-us-saas-gosaas-region-tidb-v85-02&deployType=dedicated&version=v8.5.4#/topsql?from=1784602800&to=1784603100&instance=db-tikv-48.db-tikv-peer.tidb10518506906906971664.svc%3A20160" }, { "avg_read_iops": 7857.455555555555, "metric_labels": { "instance": "ip-172-26-8-44.ec2.internal", "pod": "db-tikv-20" }, "tikv_instance": "db-tikv-20.db-tikv-peer.tidb10518506906906971664.svc:20160", "tikv_node": "db-tikv-20", "url": "https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10518506906906971664&provider=aws®ion=us-east-1&orgName=Buffet%27s%20Org&orgId=1372813089209061633&projectId=1372813089454544954&clusterName=prod-us-saas-gosaas-region-tidb-v85-02&deployType=dedicated&version=v8.5.4#/topsql?from=1784602800&to=1784603100&instance=db-tikv-20.db-tikv-peer.tidb10518506906906971664.svc%3A20160" } ] }, "time_window": { "end": 1784603100, "start": 1784602800, "step": "60" }, "unit": "ops/s" } ], "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": true, "diagnosis_kill_query_chain_asserted": false, "diagnosis_memory_tracker_panic_asserted": false, "diagnosis_plan_stats_issue_asserted": false, "diagnosis_single_instance_panic_restart_asserted": false, "fake_alarm_primary_asserted": false, "focuses_on_missing_index": false, "mentions_cpu_saturation": false, "mentions_est_act_divergence": false, "mentions_idle_transaction": false, "mentions_intermediate_result_explosion": false, "mentions_kill_query": false, "mentions_memory_tracker_consume": false, "mentions_p99_latency_spike": false, "mentions_rollback_cleanup": false, "mentions_statistics_uninitialized": false, "mentions_v8_5_2": false, "mentions_v8_5_3_or_fixed_release": false, "mentions_without_fix": false, "missing_index_primary_root_cause_asserted": false, "puller_or_source_side_primary_root_cause_asserted": false, "query_only_primary_root_cause_asserted": false, "wide_scan_primary_root_cause_asserted": false }, "routing": { "analysis_event_items_present": false, "analysis_has_key_evidence": false, "analysis_has_supporting_evidence": false, "analysis_items_shape_valid": false, "analysis_log_items_present": false, "analysis_log_or_event_channel_resolvable": true, "analysis_metric_refs_required": false, "analysis_metric_refs_resolvable": true, "analysis_patch_present": false, "analysis_patch_valid_json": false, "analysis_query_refs_required": false, "analysis_query_refs_resolvable": true, "classification_contract_valid": false, "diagnosis_analyst_contract_present": false, "fault_classification_contract_valid": false, "primary_fault_class_component_restart_or_panic": false, "primary_fault_class_resource_control_or_capacity": false, "primary_fault_class_service_unavailability_or_worker_failure": false, "primary_fault_class_sql_plan_or_query": false, "primary_fault_class_storage_or_infra_io": false, "primary_fault_class_tidb_cpu_gc_or_memory": false, "primary_fault_class_tikv_read_hotspot": false, "primary_fault_class_unknown_insufficient_evidence": false, "selected_diagnosis_skills_present": false, "signal_tags_contract_valid": false }, "runtime_context_present": true, "window": { "actual_end_ts": 1784603100, "actual_start_ts": 1784602800, "expected_allowed_window_id": "bjt-2026-07-21-1100-5m", "expected_end_ts": 1784603100, "expected_start_ts": 1784602800, "matched_allowed_window": true }, "workflow": { "architecture_context_loaded": false, "collect_evidence_invoked": false, "diagnosis_run_initialized": true, "direct_conclusion_by_investigator": false, "evidence_collection_completed": true, "evidence_collection_started": false, "final_answer_emitted": true, "misdiagnosis_guardrails_loaded": false, "premise_verification_recorded": false, "summary_read_completed": false, "targeted_panic_log_query_completed": false } }, "id": "evaljudge-9b1a5ee58e0842c5bc590588e25fd718", "invalid_subtype": null, "judged_at": "2026-07-21T10:08:19.735029+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": "10518506906906971664", "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-a4e7b424827349fabb737e1ee940fccf", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 }, { "candidate_count": 1, "candidates": [ { "actual_cluster_id": "10518506906906971664", "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-1784628476449-a1d374b1", "telemetry_path": ".opencode/telemetry.log", "valid_candidate_count": 1 } ], "selected_candidate": { "actual_cluster_id": "10518506906906971664", "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": "10518506906906971664", "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 time window matches the runtime-resolved 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 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-a4e7b424827349fabb737e1ee940fccf/evidences/metrics.json", "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/workspace_evidence_report.json" ], "description": "Evidence includes node-level disk read metric collection.", "earned_score": 4, "id": "raw_disk_read_metric_present", "match": "any_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "node_disk_reads_completed_total", "matcher": "json_text_contains_any", "snippet": "ad_iops_for_topsql_links\", \"promql\": \"client-side join: sum by (instance) (rate(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb105185", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "node_disk_reads_completed_total", "matcher": "json_text_contains_any", "snippet": "ad_iops_for_topsql_links\", \"promql\": \"client-side join: sum by (instance) (rate(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb105185", "source": "artifact_json" } ], "snippet": "ad_iops_for_topsql_links\", \"promql\": \"client-side join: sum by (instance) (rate(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb105185" }, { "artifact_paths": [ "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/metrics.json", "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/workspace_evidence_report.json" ], "description": "Evidence shows a cluster-scoped mapping or node-filter strategy for TiKV disk reads.", "earned_score": 6, "id": "cluster_scoped_mapping_evidence_present", "match": "any_of", "max_score": 6, "passed": true, "required": true, "rules": [ { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/metrics.json", "artifacts": [ "metrics" ], "matched": true, "matched_keyword": "kube_pod_info", "matcher": "json_text_contains_any", "snippet": "te(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb10518506906906971664\", \"unit\": \"ops/s\", \"summary\": {\"point_count\"", "source": "artifact_json" }, { "artifact_path": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-a4e7b424827349fabb737e1ee940fccf/evidences/workspace_evidence_report.json", "artifacts": [ "workspace_report" ], "matched": true, "matched_keyword": "kube_pod_info", "matcher": "json_text_contains_any", "snippet": "te(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb10518506906906971664\", \"unit\": \"ops/s\", \"summary\": {\"point_count\"", "source": "artifact_json" } ], "snippet": "te(node_disk_reads_completed_total{instance=~\\\".*\\\",device!~\\\"dm.*\\\"}[60s])) -> kube_pod_info namespace=tidb10518506906906971664\", \"unit\": \"ops/s\", \"summary\": {\"point_count\"" }, { "artifact_paths": [], "description": "Output JSON cluster_id matches the runtime reference.", "earned_score": 4, "id": "output_cluster_id_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"10518506906906971664\"", "source": "output_json" } ], "snippet": "\"10518506906906971664\"" }, { "artifact_paths": [], "description": "Output JSON window.start matches the runtime reference.", "earned_score": 4, "id": "output_window_start_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:00:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:00:00Z\"" }, { "artifact_paths": [], "description": "Output JSON window.end matches the runtime reference.", "earned_score": 4, "id": "output_window_end_matches_reference", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_equals_reference", "snippet": "\"2026-07-21T03:05:00Z\"", "source": "output_json" } ], "snippet": "\"2026-07-21T03:05:00Z\"" }, { "artifact_paths": [], "description": "Output JSON mapping_strategy matches the runtime reference.", "earned_score": 4, "id": "mapping_strategy_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": "\"node_filter\"", "source": "output_json" } ], "snippet": "\"node_filter\"" }, { "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": [ "output_json" ], "description": "Output JSON contains a non-empty TopSQL link list.", "earned_score": 3, "id": "topsql_links_present", "match": "all_of", "max_score": 3, "passed": true, "required": true, "rules": [ { "artifact_path": "output_json", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_list_nonempty", "snippet": "{\"tikv_node\": \"db-tikv-48\", \"url\": \"https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10518506906906971664&provider=aws®ion=us-east-1&orgName=Buffet%27s%20Org&orgId=1372813089209061633&projectId=1372813089454544954&clu", "source": "output_json" } ], "snippet": "{\"tikv_node\": \"db-tikv-48\", \"url\": \"https://clinic.pingcap.com/portal/dashboard/cloud/ngm.html?clusterId=10518506906906971664&provider=aws®ion=us-east-1&orgName=Buffet%27s%20Org&orgId=1372813089209061633&projectId=1372813089454544954&clu" }, { "artifact_paths": [ "output_json" ], "description": "Output JSON contains two unique TiKV node names.", "earned_score": 4, "id": "topsql_links_have_two_unique_tikv_nodes", "match": "all_of", "max_score": 4, "passed": true, "required": true, "rules": [ { "artifact_path": "output_json", "artifacts": [], "matched": true, "matched_keyword": null, "matcher": "json_path_unique_count_gte", "snippet": "unique_count=2 values=['db-tikv-20', 'db-tikv-48']", "source": "output_json" } ], "snippet": "unique_count=2 values=['db-tikv-20', 'db-tikv-48']" }, { "artifact_paths": [], "description": "Output JSON node ordering matches the runtime reference.", "earned_score": 0, "id": "topsql_link_nodes_match_runtime_reference", "match": "all_of", "max_score": 7, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "json_array_matches_reference", "snippet": null, "source": "output_json" } ], "snippet": null }, { "artifact_paths": [], "description": "Output JSON TopSQL URLs match the runtime reference semantics for cluster, window, and instance.", "earned_score": 0, "id": "topsql_urls_match_runtime_reference", "match": "all_of", "max_score": 10, "passed": false, "required": true, "rules": [ { "artifact_path": "", "artifacts": [], "matched": false, "matched_keyword": null, "matcher": "topsql_url_semantically_matches_reference", "snippet": null, "source": "output_json" } ], "snippet": null } ], "max_score": 80, "raw_max_score": 54, "raw_score": 37, "score": 55, "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-a4e7b424827349fabb737e1ee940fccf/semantic_packet_v1.json", "reason": "semantic_packet_missing", "status": "not_available", "summary": { "disagreement_flags": [], "shadow_max_score": 0, "shadow_score": 0 } }, "status": "pass" }, "evidence_collection": { "checks": [ { "description": "Workspace diagnosis report is present and readable.", "earned_score": 2, "id": "required_report_present", "match": "all_of", "max_score": 2, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "diagnosis_report_present" ], "matcher": "subset_observed", "path": "", "paths": [ "diagnosis_report_present" ], "source": "artifact_fact", "threshold": null } ], "snippet": "matched collection facts: diagnosis_report_present" }, { "description": "Query or metric evidence is observed for this ad-hoc request.", "earned_score": 2, "id": "query_or_metric_channel_observed", "match": "all_of", "max_score": 2, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "query_or_metric" ], "matcher": "count_gte", "path": "", "paths": [ "query_or_metric" ], "source": "channel_fact", "threshold": 1.0 } ], "snippet": "matched collection facts: query_or_metric" }, { "description": "If an events collection query is attempted, an events output file is persisted even when the result set is empty.", "earned_score": 2, "id": "attempted_events_collection_persisted", "match": "all_of", "max_score": 2, "passed": true, "required": false, "rules": [ { "matched": true, "matched_keys": [ "events_attempted_implies_artifact_present" ], "matcher": "bool_true", "path": "events_attempted_implies_artifact_present", "paths": [], "source": "evidence_fact", "threshold": null } ], "snippet": "matched collection facts: events_attempted_implies_artifact_present" } ], "max_score": 5, "raw_max_score": 6, "raw_score": 6, "score": 5, "status": "pass" }, "evidence_collection_verdict": "pass", "evidence_routing": { "checks": [ { "description": "Analysis patch is only required to be valid when it exists.", "earned_score": 0, "id": "analysis_patch_valid_when_present", "match": "any_of", "max_score": 0, "passed": true, "required": true, "rules": [ { "matched": true, "matched_keys": [ "analysis_patch_present" ], "matcher": "bool_false", "path": "analysis_patch_present", "paths": [], "source": "routing_fact" }, { "matched": false, "matched_keys": [], "matcher": "bool_true", "path": "analysis_patch_valid_json", "paths": [], "source": "routing_fact" } ], "snippet": "matched routing facts: analysis_patch_present" } ], "max_score": 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": "Correct TopSQL links require first identifying the hottest TiKV nodes within the target cluster and window, then generating per-instance TopSQL URLs for those exact TiKV instances.", "overall_verdict": "fail", "quality_verdict": "pass", "scoring": { "failing_hard_gate_score_cap": 69, "final_score": 69, "hard_gate_passed": false, "normalized_total_score": 71, "passing_hard_gate_score_floor": 70, "raw_total_score": 60, "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 }