class TaskEnv(MultiTurnEnv):
    def env_response(self, model_output, state):
        action = parse_action(model_output)          # your task's syntax
        if not is_valid(action, state):
            return error_message(action), penalize(state)
        state = apply_action(state, action)          # your task's rules
        if not task_complete(state):
            state = environment_step(state)          # tool, API call, or opponent
        return render_state(state), state            # your task's display