### Check for existing issues

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

### What happened?

When using the `langfuse_otel` callback with LiteLLM proxy and a model configured with a proxy alias (e.g. `groq-gpt-oss-120b` → `groq/openai/gpt-oss-120b`), **streaming requests** log the raw upstream model identifier (`openai/gpt-oss-120b`) in Langfuse instead of the configured proxy alias (`groq-gpt-oss-120b`).

Non-streaming requests work correctly and log the proxy alias.

Expected: Langfuse traces show the proxy alias (`groq-gpt-oss-120b`) for both streaming and non-streaming requests.

### Steps to Reproduce

1. Configure a model alias in config.yaml:

```yaml model_list: - model_name: groq-gpt-oss-120b litellm_params: model: groq/openai/gpt-oss-120b api_key: os.environ/GROQ_API_KEY

litellm_settings: callbacks: - langfuse_otel ```

2. Make a streaming request to the proxy:

``` import openai client = openai.OpenAI(base_url="http://localhost:4000", api_key="<master-key>") response = client.chat.completions.create( model="groq-gpt-oss-120b", messages=[{"role": "user", …