LiveKit Community

I'm using inference gateway for the llm plugin on node js and am seeing this error in a lot of my sessions:
```400 provider: google model: google/gemini-2.5-flash, message: Error 400, Message: Please ensure that the number of function response parts is equal to the number of function call parts of the function call turn., Status: INVALID_ARGUMENT, Details: [].  Please ensure that the number of function response parts is equal to the number of function call parts of the function call turn```
I have the model set to gemini 3 flash, so what could be the issue here?

Thanks for reaching out, Tim. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.


I don't have the answer you're looking for.

You could also try asking your question:
• in one of the other Slack channels
or
• to <https://deepwiki.com/livekit/livekit_composite|https://deepwiki.com/livekit/livekit_composite> which is trained on all LiveKit source code

If you find the answer, please post it here to help others!


for inference LLM on gemini-3-flash, do I need to pass in
```thinkingConfig: {
            thinkingBudget: 0,
          },```
in the model options?