schema_version: 1 case_id: sql-tail-latency-spike-during-incident-window ground_truth: root_cause: A TiDB internal range-splitting path retained abnormal heap under a heavy lookup workload, driving GC pressure and tail-latency spikes; the workload was a trigger rather than the full root cause 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: gc_signal_present weight: 8 description: Evidence shows abnormal TiDB GC pressure during the incident window. match: any_of rules: - source: artifact_json artifacts: - metrics matcher: json_text_contains_any keywords: - go_gc - gc pause - GC pause - gc pressure - source: artifact_json artifacts: - summary_json matcher: json_text_contains_any keywords: - GC - heap - pause - id: heap_profile_signal_present weight: 9 description: Evidence includes heap-profile outliers and a dominant memory-retention stack. match: any_of rules: - source: artifact_json artifacts: - summary_json matcher: json_text_contains_any keywords: - heap - inuse_space - memory retention - dominant allocation - source: artifact_json artifacts: - queries matcher: json_text_contains_any keywords: - IndexLookUp - process_keys - large scan 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_gc_pressure_as_primary_driver mode: blended weight: 3 required: true description: Identifies GC pressure and frequent allocation activity as the primary driver of tail latency. deterministic: match: all_of rules: - source: output_text matcher: keyword_any keywords: - GC pressure - gc pause - frequent gc - frequent malloc - allocation pressure - GC 压力 - 频繁 GC - 频繁 malloc - source: output_text matcher: keyword_any keywords: - tail latency - P999 - latency spike - 尾延迟 semantic: id: 1 title: 主路径判断 description: | 判断回答是否把主路径识别为 GC pressure、frequent allocation / frequent GC 对尾延迟的直接放大作用，而不是 generic latency symptom。 - id: identify_heap_profile_dominant_stack mode: blended weight: 3 required: true description: Uses heap-profile stack evidence to localize the dominant problematic path. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - heap profile - dominant stack - stack trace - range splitting path - range split - split range - heap stack - pprof semantic: id: 2 title: heap profile 栈定位 description: | 判断回答是否基于 heap profile / dominant stack 证据，将问题定位到 range split 相关调用栈或同等粒度的具体内部路径，而不是只停留在 workload trigger。 - id: mention_github_issue_id mode: deterministic_only weight: 3 required: false description: Mentions the concrete GitHub issue id that matches the diagnosed path. deterministic: match: any_of rules: - source: output_text matcher: regex_any patterns: - "(github|issue)\\s*#?\\d+" - "issue\\s+id\\s*[:#]?\\s*\\d+" - "github issue\\s*[:#]?\\s*\\d+" - id: recommend_fixed_version_upgrade mode: blended weight: 4 required: false description: Recommends upgrading to a fixed version or build. deterministic: match: any_of rules: - source: output_text matcher: keyword_any keywords: - fixed release - upgrade - patched build - fixed version - 升级 - 修复版本 semantic: id: 3 title: 升级修复建议 description: | 判断回答是否建议升级到 fixed version、 patched build 或已修复 release。