{
  "eval_set_id": "basic_eval",
  "name": "Basic Agent Evaluation",
  "description": "Sample evaluation set for testing core agent functionality. Customize these cases based on your DESIGN_SPEC.md.",
  "eval_cases": [
    {
      "eval_id": "greeting",
      "conversation": [
        {
          "user_content": {
            "parts": [{"text": "Hello, what can you help me with?"}]
          }
        }
      ],
      "session_input": {
        "app_name": "app",
        "user_id": "eval_user",
        "state": {}
      }
    },
    {
      "eval_id": "weather_query",
      "conversation": [
        {
          "user_content": {
            "parts": [{"text": "What's the weather like in San Francisco?"}]
          }
        }
      ],
      "session_input": {
        "app_name": "app",
        "user_id": "eval_user",
        "state": {}
      }
    }
  ]
}