### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

When sending a request to gpt-oss-120b with websearch interception enabled, an error occurs where it attempts to route to the `openai` provider instead of `hosted_vllm`. Requests without web search work fine.

### Steps to Reproduce

1. Configure the model and web searching. ``` model_list: - model_name: gpt-oss-120b litellm_params: model: hosted_vllm/openai/gpt-oss-120b api_base: <url>

search_tools: - search_tool_name: brave-search litellm_params: search_provider: brave api_key: os.environ/BRAVE_API_KEY

litellm_settings: callbacks: - websearch_interception websearch_interception_params: enabled_providers: - hosted_vllm search_tool_name: brave-search ``` 2. Send a request. ``` curl -X POST --location '<url>/v1/chat/completions' \ --header 'Authorization: Bearer <key>' \ --header 'Content-Type: application/json' \ --data '{ "model": "gpt-oss-120b", "messages": [ { "role": "user", "content": "Find the latest LiteLLM issue about websearc…