Add gpt-4-turbo model; use for code changing (#416)
Without function calling, we need to use models that support
`json_object` as a response format.
At some point we should revisit function calling with the new client,
but it seems substantially more complicated than the old API. It also
appears to be deprecated in favor of "tool calling"":
> For function call sample, see [function
call](https://github.com/Azure/azure-sdk-for-java/tree/azure-ai-openai_1.0.0-beta.10/sdk/openai/azure-ai-openai/src/samples/java/com/azure/ai/openai/ChatCompletionsFunctionCall.java).
However, they are considered a legacy feature. Using tools is the
preferred way. For more details see sample [tool
calls](https://github.com/Azure/azure-sdk-for-java/blob/azure-ai-openai_1.0.0-beta.10/sdk/openai/azure-ai-openai/src/samples/java/com/azure/ai/openai/usage/GetChatCompletionsToolCallSample.java).
https://learn.microsoft.com/en-us/java/api/overview/azure/ai-openai-readme?view=azure-java-preview#chat-completions
