Add interleaved_reasoning option to openai compatible models (#54016)

Release Notes:

- Added interleaved_reasoning option to openai compatible models

---

This PR adds the interleaved_reasoning option for OpenAI-compatible
models, addressing the issue described in
https://github.com/ggml-org/llama.cpp/issues/20837.

In my testing, enabling interleaved_reasoning not only resolved the
tool-calling issues encountered by Qwen3.5 models in llama.cpp, but also
appeared to improve the model's coding capabilities. I have also
verified the outgoing requests using a proxy to ensure the parameter is
being sent correctly.It is also likely that this change will benefit
other models and providers as well.

Note: While I used AI to assist with the implementation, I have reviewed
and tested the changes. As I am relatively new to Rust and the Zed
codebase, I would appreciate any feedback or suggestions for
improvement. I am happy to make further adjustments if needed.

Thank you all for building such an amazing editor!

Co-authored-by: Oleksiy Syvokon <oleksiy@zed.dev>

docs/src/ai/llm-providers.md

@@ -607,6 +607,7 @@ By default, OpenAI-compatible models inherit the following capabilities:
 - `parallel_tool_calls`: false (does not support `parallel_tool_calls` parameter)
 - `prompt_cache_key`: false (does not support `prompt_cache_key` parameter)
 - `chat_completions`: true (calls the `/chat/completions` endpoint)
+- `interleaved_reasoning`: false (thinking tokens are sent inline in message text; set to true to send them as a dedicated `reasoning_content` field for models that expect it)
 
 If a provider exposes models that only work with the Responses API, set `chat_completions` to `false` for those entries. Zed uses the Responses endpoint for these models.