OpenAI Client Token Usage not being tracked

[gziz]

What happened?

The BaseOpenAIChatCompletionClient has a total_usage property that's supposed to track the token usage of the client.
However, it looks like the logic to do so is not implemented correctly.

Here's the function responsible of adding usage

def _add_usage(usage1: RequestUsage, usage2: RequestUsage) -> RequestUsage:
    return RequestUsage(
        prompt_tokens=usage1.prompt_tokens + usage2.prompt_tokens,
        completion_tokens=usage1.completion_tokens + usage2.completion_tokens,
    )

Here's how the function is being used

        _add_usage(self._total_usage, usage)

The function returns a RequestUsage object however, we are not even receiving that returned value.

AutoGen version

0.4

Which package was this bug in

Extensions

Model used

No response

Python version

No response

Operating system

No response

Any additional info you think would be helpful for fixing this bug

No response