Error playing with tuple spaces, such as Blackjack

I tested a dqn using tf2rl toward openai gym env called Blackjack. There are some dimension erors about cpprb: Traceback (most recent call last):

  File "F:/zhihaogithub/rl2hrc/rl2hrc_dqn/run_dqn_blackjack.py", line 56, in <module>
    trainer()
  File "F:\zhihaogithub\rl2hrc\rl2hrc_dqn\tf2rl\experiments\trainer.py", line 134, in __call__
    next_obs=next_obs, rew=reward, done=done_flag)
  File "cpprb\PyReplayBuffer.pyx", line 857, in cpprb.PyReplayBuffer.ReplayBuffer.add
  File "<__array_function__ internals>", line 6, in reshape
  File "E:\anaconda\lib\site-packages\numpy\core\fromnumeric.py", line 301, in reshape
    return _wrapfunc(a, 'reshape', newshape, order=order)
  File "E:\anaconda\lib\site-packages\numpy\core\fromnumeric.py", line 61, in _wrapfunc
    return bound(*args, **kwds)
ValueError: cannot reshape array of size 3 into shape (45)