schema_version: 1 case_id: cpu-spike-during-incident-window ground_truth: root_cause: TiDB node count reduction increased per-node load; plan cache hit=0 and similar signals were not the differentiating primary root cause 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_minimum_observed required: true description: At least one preferred evidence channel is observed. match: all_of rules: - source: channel_fact matcher: count_gte paths: - query_or_metric threshold: 1 - 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_minimum_observed weight: 0 required: true description: At least the minimum number of preferred evidence channels are observed. match: all_of rules: - source: channel_fact matcher: count_gte paths: - query_or_metric threshold: 1 - 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 CPU hotspot evidence is present for the incident window. match: any_of rules: - source: artifact_json artifacts: - gate_checks matcher: json_text_contains_any keywords: - HOTSPOT - CPU - source: artifact_json artifacts: - metrics matcher: json_text_contains_any keywords: - process_cpu_seconds_total - tidb_cpu - cpu - id: capacity_comparison_context_present weight: 17 description: Evidence includes baseline-vs-incident capacity comparison context. match: any_of rules: - source: artifact_json artifacts: - cluster_meta matcher: json_path_unique_count_gte path: cluster.components.COMPONENT_TYPE_TIDB.tidbGroups.replicas threshold: 2 - source: artifact_json artifacts: - workspace_report matcher: json_path_unique_count_gte path: metadata.cluster.components.COMPONENT_TYPE_TIDB.tidbGroups.replicas threshold: 2 - source: artifact_json artifacts: - summary_json matcher: json_text_contains_any keywords: - per-node - node count - fewer nodes - same workload - baseline - comparison 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 references 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 references 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_capacity_shift_as_primary_driver mode: blended weight: 3 required: true description: Identifies a capacity or node-count shift as the primary driver of the CPU increase. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - node count reduction - fewer TiDB nodes - scale-in - capacity reduction - 节点数减少 - 实例数减少 - 节点数量下降 semantic: id: 1 title: 主路径判断 description: | 判断回答是否把主路径识别为容量变化或节点数下降导致的 per-node load increase， 而不是把 plan cache hit=0 当成主根因。 - id: reject_plan_cache_or_secondary_signals_as_primary_root_cause mode: blended scoring_mode: penalty weight: 3 required: false description: Avoids elevating plan cache hit=0 or similar secondary signals into the primary differentiating root cause. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - plan cache hit=0 is expected - plan cache miss is expected - plan cache is expected - plan cache is not the root cause - plan cache is not the differentiator - plan cache miss is not the root cause - plan cache miss is not the differentiator - plan cache 不是根因 - plan cache miss 不是根因 - source: output_text matcher: regex_any patterns: - "plan cache.{0,80}(not the root cause|not the differentiator|expected|normal)" - "(not the root cause|not the differentiator).{0,80}plan cache" - "plan cache.{0,80}(不是根因|不是差异因子|属于正常现象)" - "(不是根因|不是差异因子).{0,80}plan cache" - "(cache miss|plan cache miss).{0,80}(not the root cause|not the differentiator|expected|normal)" - "(不是根因|不是差异因子).{0,80}(cache miss|plan cache miss)" - "(secondary symptom|false lead).{0,80}(plan cache|cache miss)" semantic: id: 2 title: 误导线索排除 description: | 判断回答是否避免把 plan cache hit=0、plan cache miss 或类似次级现象抬升为 primary cause。 回答可以不显式提到 plan cache；只要主因稳定落在容量/节点数变化上，且没有把这些次级现象 当成主因，即可判为通过。若回答明确将其视为 false lead / secondary symptom，也应判为通过。 - id: recommend_capacity_adjustment_over_cache_tuning mode: blended weight: 3 required: false description: Recommends capacity adjustment rather than plan cache tuning. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - scale TiDB back - restore node count - capacity adjustment - 扩容 - 恢复节点数 - source: output_text matcher: regex_any patterns: - "(do not|don't|should not).{0,40}(fix|tune).{0,20}plan cache" - "不要.{0,20}(修|调).{0,20}plan cache" semantic: id: 3 title: 修复建议对齐 description: | 判断回答是否给出容量调整、workload redistribution 等对齐 remediation， 而不是优先建议做 plan cache tuning。