env/tasks.py

def load_task(task_id: str):
    # Grader Logic: ensures scores are strictly between 0 and 1
    tasks = {
        "easy_refund": {
            "text": "User #101: Requesting refund for order 404.",
            "target": "refund",
            "reward_weight": 0.82  # Strictly (0, 1)
        },
        "medium_db": {
            "text": "System Alert: DB_CONNECTION_TIMEOUT in cluster-A.",
            "target": "database",
            "reward_weight": 0.74  # Strictly (0, 1)
        },
        "hard_security": {
            "text": "Critical: Multi-factor bypass detected on admin login.",
            "target": "security",
            "reward_weight": 0.68  # Strictly (0, 1)
        }
    }
    return [tasks.get(task_id, tasks["easy_refund"])]