reasoning_gym:
  resources_servers:
    reasoning_gym:
      entrypoint: app.py
      domain: knowledge
      verified: true
      description: Claude Code agent harness for reasoning gym tasks
      value: Evaluate model capabilities in the Claude Code agent harness

reasoning_gym_claude_code_agent:
  responses_api_agents:
    claude_code_agent:
      entrypoint: app.py
      resources_server:
        type: resources_servers
        name: reasoning_gym
      concurrency: 32
      model: ${anthropic_model_name}
      anthropic_api_key: ${anthropic_api_key}
      anthropic_base_url: ${anthropic_base_url}
      max_turns: 30
      timeout: 300
      thinking: disabled
      system_prompt: |
        You are a precise reasoning assistant. You have access to Bash to run Python for calculations.
        For every problem: think step by step, use code to verify when helpful, and state your final answer clearly.
      datasets:
      - name: example
        type: example
        jsonl_fpath: resources_servers/reasoning_gym/data/example.jsonl
      - name: train
        type: train
        jsonl_fpath: resources_servers/reasoning_gym/data/Nemotron-RL-ReasoningGym-v1_train.jsonl
        huggingface_identifier:
          repo_id: nvidia/Nemotron-RL-ReasoningGym-v1
          artifact_fpath: data/train.jsonl
        license: Creative Commons Attribution 4.0 International