Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

When I use Gemini's OpenAI compatible endpoint to make streaming tool calls, the package raises the following error:
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/serviceme/llm_gateway/llm_adapters/base/decorators.py", line 68, in async_gen_wrapper
async for chunk in async_gen:
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/serviceme/llm_gateway/llm_adapters/openai/adapter.py", line 105, in _chat_completion_stream_async
async for chunk in stream:
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/.venv/lib/python3.11/site-packages/openai/lib/streaming/chat/_completions.py", line 195, in aiter
async for item in self._iterator:
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/.venv/lib/python3.11/site-packages/openai/lib/streaming/chat/_completions.py", line 241, in stream
events_to_fire = self._state.handle_chunk(sse_event)
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/.venv/lib/python3.11/site-packages/openai/lib/streaming/chat/_completions.py", line 348, in handle_chunk
return self._build_events(
File "/Users/shaun.yang/Desktop/medalsoft/serviceme-next-backend/.venv/lib/python3.11/site-packages/openai/lib/streaming/chat/_completions.py", line 536, in _build_events
tool_call = tool_calls[tool_call_delta.index]
TypeError: list indices must be integers or slices, not NoneType

To Reproduce

use the following code to reproduce:

from openai import AsyncClient
async def main():
    client = AsyncClient(
        api_key='<my-apikey>',
        base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
    )
    tools = [
      {
        "type": "function",
        "function": {
            "strict": True,
          "name": "get_weather",
          "description": "Get the weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. Chicago, IL",
              },
              "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
          },
        }
      }
    ]

    messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
    async with client.chat.completions.stream(
      model="gemini-3-flash-preview",
      messages=messages,
      tools=tools,
      tool_choice="auto",
    ) as stream:
        async for event in stream:
            print(event)

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

Code snippets

OS

macOS

Python version

Python 3.11.13

Library version

openai v2.14.0