schema_version: 1 case_id: component-restart-during-incident-window ground_truth: root_cause: TiDB v8.5.2 known bug GitHub 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: targeted_panic_log_query_completed weight: 10 required: false description: Targeted panic log query is completed. match: all_of rules: - source: workflow_fact matcher: bool_true path: targeted_panic_log_query_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: - logs - 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: - logs - 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: - logs - 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: - logs - query_or_metric critical_evidence: weight: 30 checks: - id: restart_signal_present weight: 8 description: Direct restart evidence is present within the incident window. match: any_of rules: - source: artifact_json artifacts: - component_health matcher: json_list_nonempty path: component_health.restarts - source: artifact_json artifacts: - process_restart_metrics - kube_restart_metrics matcher: numeric_series_any_gt path: data.result threshold: 0 - source: logs matcher: keyword_any keywords: - "Welcome to TiDB." - id: panic_signal_present weight: 9 description: Direct panic evidence is present within the incident window. match: any_of rules: - source: logs matcher: keyword_any keywords: - "panic:" - "memory.(*Tracker).Consume" - "tracker accounting panic" - id: query_interruption_signal_present weight: 8 description: Direct query interruption evidence is present within the incident window. match: any_of rules: - source: logs matcher: keyword_any keywords: - "kill query" - "query execution was interrupted" - "query is killed" - "sqlkiller.go" 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 are resolvable whenever the patch contains metric refs. 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 are resolvable whenever the patch contains query refs. 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_known_bug_restart_chain mode: blended weight: 3 required: true description: Identifies the known-bug single-instance restart chain rather than a generic restart explanation. deterministic: match: all_of rules: - source: output_fact matcher: any_true paths: - diagnosis_single_instance_panic_restart_asserted - diagnosis_memory_tracker_panic_asserted semantic: id: 1 title: 主路径判断 description: | 判断回答是否将本次事件的主路径识别为 TiDB v8.5.2 已知 bug 导致的 single-instance restart chain，而不是 generic restart、missing index 或其它泛化解释。 - id: identify_kill_query_cleanup_chain mode: blended weight: 3 required: false description: Identifies KILL QUERY / query interruption as trigger and explains the cleanup chain toward panic or restart. deterministic: match: all_of rules: - source: output_fact matcher: bool_true path: diagnosis_kill_query_chain_asserted semantic: id: 2 title: 因果链完整性 description: | 判断回答是否说明 KILL QUERY / query interruption 是触发因素而不是主根因， 并进一步解释 rollback 或 idle transaction cleanup 到 panic/restart 的链路。 - id: reject_missing_index_root_cause mode: deterministic_only scoring_mode: penalty weight: 3 required: false description: Does not misdiagnose the case as a missing-index or full-scan primary root cause. deterministic: match: all_of rules: - source: output_fact matcher: bool_false path: missing_index_primary_root_cause_asserted - source: output_fact matcher: bool_false path: claims_panic_not_confirmable - id: mention_github_issue_id mode: deterministic_only weight: 3 required: false description: Explicitly cites issue 63956 as the known bug identifier. deterministic: match: all_of rules: - source: output_text matcher: keyword_any keywords: - "63956" - "GitHub #63956" - "issue #63956" - id: recommend_fixed_version_upgrade mode: blended weight: 3 required: false description: Recommends upgrading to a release containing the fix and explains the version relationship. deterministic: match: all_of rules: - source: output_fact matcher: bool_true path: mentions_v8_5_3_or_fixed_release semantic: id: 4 title: 修复建议对齐 description: | 判断回答是否给出了与 ground truth 一致的 remediation，例如升级到包含修复的版本， 而不是把建索引或泛化调参当成主修复方案。 critical: - id: identify_single_instance_panic_restart description: Identifies a TiDB panic event and/or single-instance restart rather than a cluster-wide slowdown. - id: identify_kill_query_chain description: Identifies KILL QUERY / query interruption as part of the root-cause chain. - id: reject_missing_index_root_cause description: Does not misdiagnose the case as a missing-index or full-scan primary root cause. - id: identify_known_bug_63956 description: Identifies TiDB v8.5.2 known bug GitHub - id: identify_kill_query_idle_txn_chain description: Explains the KILL QUERY plus idle transaction rollback cleanup trigger chain. - id: identify_version_without_fix description: States that v8.5.2 predates or does not include the fix. - id: recommend_fixed_version_upgrade description: Recommends upgrading to v8.5.3 or another version containing the fix.