schema_version: 1
case_id: latency-surge-with-tikv-cpu-imbalance
ground_truth:
  expected_diagnosis_skill_routes:
  - any_of:
    - tidb-query-tuning-autox
    - tidb-query-tuning
  root_cause: A high-QPS query on the talk_list table used IndexLookUp and generated heavy back-to-table seeks that saturated the unified read pool. Region leaders for the hot table were concentrated on one TiKV node, so the read amplification produced a node-local CPU spike and latency errors. Leader scattering and a better query/index path are the direct mitigations.
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: 10
      description: Primary symptom evidence is present in the collected evidence.
      match: any_of
      rules:
      - source: logs
        matcher: keyword_any
        keywords:
        - TiKV CPU
        - 100%
        - latency
        - HTTP 500
        - single node
      - source: artifact_json
        artifacts:
        - metrics
        - queries
        - summary_json
        - workspace_report
        matcher: json_text_contains_any
        keywords:
        - TiKV CPU
        - 100%
        - latency
        - HTTP 500
        - single node
    - id: root_cause_mechanism_evidence_present
      weight: 10
      description: Root-cause mechanism evidence is present in the collected evidence.
      match: any_of
      rules:
      - source: logs
        matcher: keyword_any
        keywords:
        - talk_list
        - IndexLookUp
        - back-to-table
        - seek
        - unified read pool
      - source: artifact_json
        artifacts:
        - metrics
        - queries
        - summary_json
        - workspace_report
        matcher: json_text_contains_any
        keywords:
        - talk_list
        - IndexLookUp
        - back-to-table
        - seek
        - unified read pool
    - id: scope_or_timeline_evidence_present
      weight: 10
      description: Placement evidence is present in the collected evidence.
      match: any_of
      rules:
      - source: logs
        matcher: keyword_any
        keywords:
        - region leader
        - store
        - leader-scatter
        - hot region
        - imbalance
      - source: artifact_json
        artifacts:
        - metrics
        - queries
        - summary_json
        - workspace_report
        matcher: json_text_contains_any
        keywords:
        - region leader
        - store
        - leader-scatter
        - hot region
        - imbalance
  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:
          - IndexLookUp
          - index lookup
        - source: output_text
          matcher: keyword_any
          keywords:
          - back-to-table
          - table lookup
          - seek
        - source: output_text
          matcher: keyword_any
          keywords:
          - unified read pool
          - read pool
      semantic:
        id: 1
        title: Primary failure mechanism
        description: The answer identifies query-driven lookup amplification and read-pool saturation.
    - 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:
          - region leader
          - leader
        - source: output_text
          matcher: keyword_any
          keywords:
          - single node
          - imbalance
          - concentrat
        - source: output_text
          matcher: keyword_any
          keywords:
          - CPU
          - latency
      semantic:
        id: 2
        title: Causal chain
        description: The answer connects leader concentration to node-local CPU saturation and application errors.
    - 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:
          - leader-scatter
          - scatter
          - distribute table
        - source: output_text
          matcher: keyword_any
          keywords:
          - index
          - query
          - IndexLookUp
        - source: output_text
          matcher: keyword_any
          keywords:
          - v8.5.7
          - CPU-aware
      semantic:
        id: 3
        title: Aligned remediation
        description: The answer recommends leader redistribution and query/index improvement, optionally noting CPU-aware scheduling in later releases.