config/metrics.yaml

# Metrics Configuration
metrics:
  # Scoring weights for composite score calculation
  weights:
    correctness_exact: 0.40
    exec_success: 0.25
    result_match_f1: 0.15
    dialect_ok: 0.10
    readability: 0.05
    latency: 0.05
  
  # Metric descriptions
  descriptions:
    correctness_exact: "Binary score (0/1) for exact result match"
    exec_success: "Binary score (0/1) for successful SQL execution"
    result_match_f1: "F1 score for partial result matching"
    latency: "Response time in milliseconds"
    readability: "Score based on SQL structure and formatting"
    dialect_ok: "Binary score (0/1) for successful SQL transpilation"
  
  # Thresholds and limits
  thresholds:
    max_latency_ms: 30000  # 30 seconds timeout
    min_score: 0.0
    max_score: 1.0
  
  # Display formatting
  formatting:
    composite_score: "{:.4f}"
    correctness_exact: "{:.2f}"
    exec_success: "{:.2f}"
    result_match_f1: "{:.4f}"
    latency_ms: "{:.1f}ms"
    dialect_ok: "{:.2f}"
    readability: "{:.2f}"

# Mock SQL Generation Patterns
mock_sql:
  patterns:
    count_queries:
      - "how many"
      - "count"
    average_queries:
      - "average"
      - "avg"
    total_queries:
      - "total"
      - "amount"
    passenger_queries:
      - "passenger"
  
  templates:
    count_trips: "SELECT COUNT(*) as total_trips FROM trips"
    count_generic: "SELECT COUNT(*) FROM trips"
    avg_fare: "SELECT AVG(fare_amount) as avg_fare FROM trips"
    avg_generic: "SELECT AVG(total_amount) FROM trips"
    total_amount: "SELECT SUM(total_amount) as total_collected FROM trips"
    passenger_count: "SELECT passenger_count, COUNT(*) as trip_count FROM trips GROUP BY passenger_count"
    default: "SELECT * FROM trips LIMIT 10"