schema_version: 1 case_id: transaction-outcome-after-node-failure ground_truth: expected_diagnosis_skill_routes: - any_of: - transaction-oncall-handbook root_cause: The case is a transaction-semantics question, not a TiDB bug. Definite prewrite rejection can be retried or reported as failure, but an RPC or connection failure may lose the response after TiKV processed a request. If retries cannot determine the final commit state, TiDB can return an undetermined outcome. Clients must use idempotent operations or query business state instead of assuming every returned error means rollback. 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 - logs 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 - logs 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 - logs 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 - logs critical_evidence: weight: 30 checks: - id: primary_symptom_evidence_present weight: 10 description: Primary symptom evidence is present in the collected evidence. match: any_of rules: - source: logs matcher: keyword_any keywords: - region is missing - peer is not leader - Prewrite - RPC - node failure - source: artifact_json artifacts: - metrics - queries - summary_json - workspace_report matcher: json_text_contains_any keywords: - region is missing - peer is not leader - Prewrite - RPC - node failure - id: root_cause_mechanism_evidence_present weight: 10 description: Transaction-state evidence is present in the collected evidence. match: any_of rules: - source: logs matcher: keyword_any keywords: - Undetermined - response lost - commit state - retry - prewrite - source: artifact_json artifacts: - metrics - queries - summary_json - workspace_report matcher: json_text_contains_any keywords: - Undetermined - response lost - commit state - retry - prewrite - id: scope_or_timeline_evidence_present weight: 10 description: Client-contract evidence is present in the collected evidence. match: any_of rules: - source: logs matcher: keyword_any keywords: - idempotent - business query - application - error - rollback - source: artifact_json artifacts: - metrics - queries - summary_json - workspace_report matcher: json_text_contains_any keywords: - idempotent - business query - application - error - rollback evidence_routing: weight: 5 checks: - id: specialist_routing_contract weight: 3 required: true description: Diagnosis is authored by the analyst with a valid classification and the expected specialist route. match: all_of rules: - source: routing_fact matcher: bool_true path: diagnosis_analyst_dispatched - source: routing_fact matcher: bool_true path: classification_contract_valid - source: routing_fact matcher: bool_true path: expected_diagnosis_skill_routes_selected - 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_patch_present - 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_patch_present - source: routing_fact matcher: bool_true path: analysis_query_refs_resolvable diagnosis: checks: - id: identify_primary_failure_mechanism mode: blended weight: 3 required: true description: Primary failure mechanism is identified and supported. deterministic: match: all_of rules: - source: output_text matcher: keyword_any keywords: - RPC - connection - source: output_text matcher: keyword_any keywords: - response - lost - source: output_text matcher: keyword_any keywords: - Undetermined - unknown outcome semantic: id: 1 title: Primary failure mechanism description: The answer distinguishes an unknown response outcome from a confirmed transaction rollback. - id: explain_causal_chain mode: blended weight: 3 required: true description: Causal chain is identified and supported. deterministic: match: all_of rules: - source: output_text matcher: keyword_any keywords: - Prewrite - Commit - source: output_text matcher: keyword_any keywords: - processed - dropped - retry - source: output_text matcher: keyword_any keywords: - application - error semantic: id: 2 title: Causal chain description: The answer explains why transport failure can hide whether TiKV processed a phase. - id: recommend_aligned_remediation mode: blended weight: 3 required: true description: Aligned remediation is identified and supported. deterministic: match: all_of rules: - source: output_text matcher: keyword_any keywords: - idempotent - idempotency - source: output_text matcher: keyword_any keywords: - business query - check state - reconcile - source: output_text matcher: keyword_any keywords: - retry semantic: id: 3 title: Aligned remediation description: The answer recommends idempotent retry and business-state verification.