`invalid_tool_calls` when using stream

### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### Example Code It is impossible to reproduce the bug with just a code example. ### Error Message and Stack Trace (if applicable) _No response_ ### Description Changes from [PR](https://github.com/langchain-ai/langchain/pull/31587) added a function [_advance](https://github.com/langchain-ai/langchain/blob/4656f727da238c1fe24f95698842b94d579844c2/libs/partners/openai/langchain_openai/chat_models/base.py#L3995) to chunk processing that changes the index variable. This creates a bug that corrupts arguments for custom functions that are called after a document search. The sequence of events to reproduce the bug: 1. Start a chat with the Responses API and the document search function 2. The model uses document search 3. The model calls the custom function and starts passing arguments: `{"type": "response.function_call_arguments.delta", "output_index": 1, "raw": {"delta": " battery", "item_id": "..., "output_index": 1, "sequence_number": 165, "type": "response.function_call_arguments.delta", "obfuscation": "..."} {"type": "response.function_call_arguments.delta", "output_index": 1, "raw": {"delta": " supply", "item_id": "....", "output_index": 1, "sequence_number": 166, "type": "response.function_call_arguments.delta", "obfuscation": "..."} {"type": "response.function_cal…