# CodeDebugger — OpenEnv Registry Manifest
# Meta + Scalar OpenEnv Hackathon 2026

env:
  name: CodeDebugger-v1
  version: "1.0.0"
  description: >
    RL environment where an LLM agent sees buggy Python code and error messages,
    proposes fixes step by step, and gets rewarded based on test-case pass rates.
  
  author: CodeDebugger Team
  license: MIT
  
  interface:
    type: openenv
    action_space: text      # agent submits fixed Python code as a string
    observation_space: text  # dict with buggy_code, error_message, history
    reward_range: [0.0, 120.0]
    max_episode_steps: 5

  entry_point: codedebugger.env.codedebugger_env:CodeDebuggerEnv

  api:
    type: fastapi
    host: "0.0.0.0"
    port: 8000
    endpoints:
      reset: POST /reset
      step: POST /step
      render: GET /render
      metadata: GET /metadata
      problems: GET /problems

  reward:
    components:
      - name: test_score
        range: "0-50"
        description: Proportional score based on test cases passed, +10 bonus for 100%
      - name: fix_quality
        range: "0-20"
        description: Rewards minimal, targeted changes to the original code
      - name: format_score
        range: "0-15"
        description: Valid Python syntax, preserved function names, consistent style
      - name: speed_score
        range: "0-10"
        description: Rewards solving in fewer iterations (10/7/4 for iter 1/2/3)
      - name: safety_score
        range: "0-10"
        description: No forbidden imports or dangerous patterns detected
      - name: improvement_score
        range: "0-15"
        description: Rewards passing more tests than previous iteration
      - name: anti_hack_penalty
        range: "negative"
        description: Penalty for hardcoded returns, code gutting, function deletion
      - name: process_bonus
        range: "0-3"
        description: Bonus for fix addressing the root cause (keyword heuristic)

  anti_hacking:
    checks:
      - hardcoded_returns
      - function_deletion
      - trivial_pass
      - code_gutting
    penalty_factor: 0.1

  dataset:
    total_problems: 30
    difficulties: [easy, medium, hard]
    problems_per_difficulty: 10
    test_cases_per_problem: 4
    source: codedebugger.data.bug_dataset

  training:
    method: GRPO
    framework: trl
    optimizer: unsloth
    default_model: unsloth/Llama-3.2-1B-Instruct

  deployment:
    platform: huggingface_spaces
    docker: true
    streamlit_port: 7860