The current ChatCompletion API supports only `parallel_tool_calls=True`
or `parallel_tool_calls=NOT_GIVEN`
This PR is to support setting `parallel_tool_calls=False`, a common
requirement in controlling agent tool use patterns (e.g. ensuring one
tool call at the time, to facilitate desired tool calling sequence).

I followed the merged
[PR#333](https://github.com/openai/openai-agents-python/pull/333) for
consistency.