schema_version: 1 case_id: service-degradation-during-incident-window ground_truth: root_cause: A dominant SQL join path drove the TiDB CPU hotspot on db-tidb-0, with stats-uninitialized plan misestimation, a TiFlash-to-TiKV plan shift, and intermediate result explosion amplifying the incident judge: semantic_strategy: undecided contract: checks: - id: time_window_match required: true description: Actual diagnosis time window matches one allowed case window. match: all_of rules: - source: trace_fact matcher: bool_true path: time_window_match - id: cluster_scope_match required: true description: Actual diagnosis cluster scope matches expected cluster id. match: all_of rules: - source: trace_fact matcher: bool_true path: cluster_scope_match workflow: checks: - id: architecture_context_loaded weight: 5 required: true description: Architecture context is loaded. match: all_of rules: - source: workflow_fact matcher: bool_true path: architecture_context_loaded - id: misdiagnosis_guardrails_loaded weight: 5 required: true description: Misdiagnosis guardrails are loaded. match: all_of rules: - source: workflow_fact matcher: bool_true path: misdiagnosis_guardrails_loaded - id: diagnosis_run_initialized weight: 5 required: true description: Diagnosis run is initialized. match: all_of rules: - source: workflow_fact matcher: bool_true path: diagnosis_run_initialized - id: evidence_collection_completed weight: 10 required: true description: Evidence collection completes. match: all_of rules: - source: workflow_fact matcher: bool_true path: evidence_collection_completed - id: summary_read_completed weight: 5 required: false description: Summary artifact is read when available. match: all_of rules: - source: workflow_fact matcher: bool_true path: summary_read_completed - id: final_answer_emitted weight: 0 required: false description: Final answer is emitted. match: all_of rules: - source: workflow_fact matcher: bool_true path: final_answer_emitted execution_contract: checks: - id: required_workflow_present required: true description: Required workflow milestones are present. match: all_of rules: - source: workflow_check matcher: subset_observed paths: - architecture_context_loaded - misdiagnosis_guardrails_loaded - diagnosis_run_initialized - evidence_collection_completed - id: required_artifacts_present required: true description: Required evidence artifacts are present. match: all_of rules: - source: artifact_fact matcher: subset_observed paths: - core_evidence_bundle_present - id: preferred_channels_all_observed required: false description: Preferred evidence channels are all observed. match: all_of rules: - source: channel_fact matcher: subset_observed paths: - query_or_metric evidence_collection: weight: 5 checks: - id: required_artifacts_present weight: 4 required: true description: Required evidence artifacts are present and readable. match: all_of rules: - source: artifact_fact matcher: subset_observed paths: - core_evidence_bundle_present - id: preferred_channels_all_observed weight: 6 required: false description: Preferred evidence channels are all observed. match: all_of rules: - source: channel_fact matcher: subset_observed paths: - query_or_metric critical_evidence: weight: 30 checks: - id: primary_symptom_evidence_present weight: 8 description: Primary symptom evidence is present for the incident window. match: all_of rules: - source: artifact_json artifacts: - gate_checks matcher: json_text_contains_any keywords: - HOTSPOT DETECTED - CPU saturation - id: primary_query_evidence_present weight: 9 description: Primary query evidence is present for the incident window. match: all_of rules: - source: artifact_json artifacts: - queries matcher: json_text_contains_any keywords: - TopSQL - digest - process_keys - cpu_time - id: root_cause_mechanism_evidence_present weight: 8 description: Root-cause mechanism evidence is present for the incident window. match: any_of rules: - source: artifact_json artifacts: - queries matcher: json_values_contains_any path: slow_queries keywords: - unInitialized - statistics unInitialized - stats:pseudo - pseudo[ - :pseudo[ - source: artifact_json artifacts: - queries matcher: json_values_contains_any path: topsql keywords: - unInitialized - statistics unInitialized - stats:pseudo - pseudo[ - :pseudo[ - source: artifact_json artifacts: - queries matcher: json_values_contains_any path: decoded_plan keywords: - unInitialized - statistics unInitialized - stats:pseudo - pseudo[ - :pseudo[ evidence_routing: weight: 5 checks: - id: analysis_patch_valid_json weight: 1 required: true description: Analysis patch is valid JSON whenever the patch exists. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_patch_present - source: routing_fact matcher: bool_true path: analysis_patch_valid_json - id: analysis_items_shape_valid weight: 2 required: true description: Analysis patch items are structurally valid whenever the patch exists. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_patch_present - source: routing_fact matcher: bool_true path: analysis_items_shape_valid - id: analysis_key_evidence_present weight: 2 required: true description: Analysis patch includes key evidence whenever the patch exists. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_patch_present - source: routing_fact matcher: bool_true path: analysis_has_key_evidence - id: metric_refs_resolvable weight: 1 required: true description: Metric refs resolve whenever the patch requires them. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_metric_refs_required - source: routing_fact matcher: bool_true path: analysis_metric_refs_resolvable - id: query_refs_resolvable weight: 1 required: true description: Query refs resolve whenever the patch requires them. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_query_refs_required - source: routing_fact matcher: bool_true path: analysis_query_refs_resolvable - id: supporting_evidence_present weight: 0 required: false description: Analysis patch includes supporting evidence whenever the patch exists. match: any_of rules: - source: routing_fact matcher: bool_false path: analysis_patch_present - source: routing_fact matcher: bool_true path: analysis_has_supporting_evidence - id: analysis_log_or_event_channel_resolvable weight: 0 required: false description: Routed log or event items stay resolvable against observed channels. match: all_of rules: - source: routing_fact matcher: bool_true path: analysis_log_or_event_channel_resolvable diagnosis: checks: - id: identify_specific_sql_hotspot_path mode: blended weight: 3 required: true description: Identifies the specific SQL path driving the single-instance TiDB CPU hotspot. deterministic: match: all_of rules: - source: output_fact matcher: bool_true path: diagnosis_cpu_hotspot_asserted - source: output_text matcher: keyword_any keywords: - TopSQL - slow query - dominant query - hot JOIN path - hot join path - sql digest - JOIN path semantic: id: 1 title: SQL 热点路径判断 description: | 判断回答是否把主路径识别为具体 SQL 或 join path 驱动的 single-instance TiDB CPU hotspot，而不是 generic infra explanation。 - id: identify_root_cause_mechanism mode: blended weight: 3 required: false description: Explains the root-cause mechanism rather than stopping at symptom-level diagnosis. deterministic: match: any_of rules: - source: output_fact matcher: bool_true path: diagnosis_plan_stats_issue_asserted - source: output_fact matcher: any_true paths: - mentions_statistics_uninitialized - mentions_est_act_divergence - mentions_intermediate_result_explosion semantic: id: 2 title: 根因机制解释 description: | 判断回答是否解释了 stats misestimation、uninitialized statistics 或 intermediate-result amplification 这类机制，而不是只停留在表面症状。 - id: identify_sql_plan_shift mode: blended weight: 3 required: false description: Identifies that the dominant SQL path experienced a plan shift as part of the root-cause chain. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - plan shift - plan changed - plan switched - execution plan changed - plan regression semantic: id: 3 title: 执行计划跳变 description: | 判断回答是否指出主 SQL 路径发生了执行计划跳变， 并将其纳入根因链路解释。 - id: identify_tiflash_to_tikv_execution_path_change mode: blended weight: 3 required: false description: Identifies that the execution path shifted from TiFlash to TiKV. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - TiFlash to TiKV - switched from TiFlash to TiKV - plan switched to TiKV - TiFlash - TiKV semantic: id: 4 title: TiFlash 到 TiKV 切换 description: | 判断回答是否指出执行路径从 TiFlash 切到 TiKV， 并将这条切换纳入根因链路解释。