name: sql-debugger-env
version: "1.0.0"
description: >
  An RL environment for training AI agents to write, debug, and optimize
  SQL queries against a real SQLite database. Three task types cover
  real data analyst work: writing queries from specs, fixing broken SQL,
  and optimizing slow correlated subqueries.

tasks:
  - id: easy_01
    name: Filter high earners
    difficulty: easy
    type: write_query
    grader: true
    description: >
      Find all employees in the Engineering department with salary above 
      90000. Return name and salary ordered by salary descending.

  - id: easy_02
    name: Count by department
    difficulty: easy
    type: write_query
    grader: true
    description: >
      Count how many employees are in each department. Return department 
      name and count ordered by count descending.

  - id: medium_01
    name: Fix broken JOIN
    difficulty: medium
    type: fix_query
    grader: true
    description: >
      Fix the broken query that returns employees on active projects. 
      Bugs: missing ON keyword in JOIN, wrong table alias in WHERE clause.

  - id: medium_02
    name: Fix wrong GROUP BY
    difficulty: medium
    type: fix_query
    grader: true
    description: >
      Fix the query that computes average salary per department but 
      incorrectly groups by id instead of department.

  - id: hard_01
    name: Optimize correlated subquery
    difficulty: hard
    type: optimize_query
    grader: true
    description: >
      Replace correlated subqueries with window functions or CTEs to 
      find the top earner per department with total hours worked.

  - id: hard_02
    name: Eliminate N+1 problem
    difficulty: hard
    type: optimize_query
    grader: true
    description: >
      Rewrite the N+1 correlated subquery using LEFT JOIN and GROUP BY 
      to get department stats in a single efficient query.

action_space:
  type: object
  properties:
    action_type:
      type: string
      enum: [write_query, fix_query, optimize_query]
      description: The type of SQL action being taken
    sql:
      type: string
      description: A valid SQLite SELECT statement
    explanation:
      type: string
      description: Optional explanation of reasoning

observation_space:
  type: object
  properties:
    task_id:
      type: string
    task_type:
      type: string
    task_description:
      type: string
    schema_info:
      type: string
      description: DDL schema of all tables
    sample_data:
      type: string
      description: First 3 rows of each table
    last_sql:
      type: string
    last_result:
      type: string
    last_error:
      type: string
    step_count:
      type: integer
    done:
      type: boolean
    reward:
      type: number
      minimum: 0.05
      maximum: 0.95
      description: Strictly between 0 and 1, never exactly 0.0 or 1.0
    feedback:
      type: string

reward_range: [0.05, 0.95]
max_steps_per_episode: 8