Configure parallel tool call support Open AI client via Agent for Dotnet Package

[nejaco-MSFT]

What feature would you like to be added?

We would like to configure parallel tool call support via agent.

Why is this needed?

We are currently using Parallel tool calling in the C# version of the Autogen SDK Version 0.2.1. However, due to the nature of our Agent workflow we are noticing that Gpt4o is hallucinating heavily and making up tool calls.

This does not seem to be happening when a single tool was recommended at a time. We would like a flag to disable the parallel tool calling ability when calling into Open AI

https://platform.openai.com/docs/guides/function-calling/parallel-function-calling#parallel-function-calling-and-structured-outputs

[ekzhu]

As a side note, for Python API you can disable parallel tool call for OpenAI and Azure OpenAI models by passing parallel_tool_calls: false to the extra_create_args to the model client.