Add Streaming of Function Call Arguments to Chat Completions

[devtalker]

Summary

This PR implements real-time streaming of function call arguments as requested in #834. Previously, function call arguments were only emitted after the entire function call was complete, causing poor user experience for large parameter generation.

Changes

• Enhanced ChatCmplStreamHandler: Added real-time streaming of function call arguments during generation
• New streaming logic: Function call arguments now stream incrementally as they are generated, similar to text content
• Backward compatibility: Maintains existing behavior for completed function calls
• Comprehensive testing: Added tests for both OpenAI and LiteLLM models
• Example implementation: Created demonstration code showing the new streaming capability

Closes #834

[devtalker]

Hey @seratch @rm-openai! 👋

Would you mind taking a look at this PR? I've implemented real-time streaming for function call arguments (fixes #834). Basically, instead of waiting for the entire function call to complete, users now see the arguments being built up incrementally as the LLM generates them. This should make the experience much smoother for things like code generation and API building.

Let me know what you think! 🚀

[seratch]

Thanks for your pull request. Left a few comments.

[devtalker]

@rm-openai @seratch hi there, just wanted to gently check in and see if you had a chance to review the PR.

[rm-openai]

Hey @devtalker this looks generally pretty good! However I did some digging and turns out this comment that I wrote is inaccurate in practice:

 # Because we don't know the name of the function until the end of the stream, we'll save everything ...

The function name is actually correct the very first time, and doesn't change. AFAICT this applies to all LLM providers.

So you should be able to simplify the code a decent amount!

[devtalker]

@rm-openai Thanks for the feedback! I've simplified the function call name logic based on your observation that function names are correct from the first chunk. Please review the changes when you have a chance

[devtalker]

Hey @rm-openai! 👋 Could you take a quick look? We need this feature ASAP for better UX 🚀