Different behavior in streaming function calling

[stevenic]

Here’s someone who hacked together streaming+tools support but it’s a complete hack:

Has anyone managed to get a tool_call working when stream=True?

I got tool calls working on streaming calls to chatcompletion last weekend. It was a pain, as it’s not documented, and it’s unclear what’s happening when you dump the chunks to text. Plus there may be multiple tool/function calls in a single response now. It’s doable, though, and it does work. The relevant snippet is this: tool_calls = [] # build up the response structs from the streamed response, simultaneously sending message chunks to the browser for chunk in response: delta = chunk.cho…