Add check for model's max token length

[heyodai]

There's a Python library to get the token count. Returning a warning is better than an error.

Example:

(base) odai:magic-commit/ (24-add-readmemd-description-on-pypi✗) $ magic-commit                                                                                                                                                                                           [16:23:54]
error_code=context_length_exceeded error_message="This model's maximum context length is 4097 tokens. However, your messages resulted in 5925 tokens. Please reduce the length of the messages." error_param=messages error_type=invalid_request_error message='OpenAI API error received' stream_error=False
Traceback (most recent call last):
  File "/opt/homebrew/Caskroom/miniconda/base/bin/magic-commit", line 33, in <module>
    sys.exit(load_entry_point('magic-commit', 'console_scripts', 'magic-commit')())
  File "/Users/odai/magic-commit/magic_commit/__main__.py", line 54, in main
    results = run_magic_commit(directory=directory, api_key=key, model=model)
  File "/Users/odai/magic-commit/magic_commit/magic_commit.py", line 201, in run_magic_commit
    commit_message = generate_commit_message(diff, api_key, model)
  File "/Users/odai/magic-commit/magic_commit/magic_commit.py", line 150, in generate_commit_message
    response = openai.ChatCompletion.create(model=model, messages=messages)
  File "/opt/homebrew/Caskroom/miniconda/base/lib/python3.9/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/opt/homebrew/Caskroom/miniconda/base/lib/python3.9/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/opt/homebrew/Caskroom/miniconda/base/lib/python3.9/site-packages/openai/api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "/opt/homebrew/Caskroom/miniconda/base/lib/python3.9/site-packages/openai/api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "/opt/homebrew/Caskroom/miniconda/base/lib/python3.9/site-packages/openai/api_requestor.py", line 765, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 5925 tokens. Please reduce the length of the messages.