fix(inference): AttributeError in streaming response cleanup (#4236)

This PR fixes issue #3185 
The code calls `await event_gen.aclose()` but OpenAI's `AsyncStream`
doesn't have an `aclose()` method - it has `close()` (which is async).
when clients cancel streaming requests, the server tries to clean up
with:

```python
await event_gen.aclose()  # ❌ AsyncStream doesn't have aclose()!
```

But `AsyncStream` has never had a public `aclose()` method. The error
message literally tells us:

```
AttributeError: 'AsyncStream' object has no attribute 'aclose'. Did you mean: 'close'?
                                                                            ^^^^^^^^
```

## Verification
* Reproduction script
[`reproduce_issue_3185.sh`](https://gist.github.com/r-bit-rry/dea4f8fbb81c446f5db50ea7abd6379b)
can be used to verify the fix.
*   Manual checks, validation against original OpenAI library code

src/llama_stack_api/inference.py

@@ -1020,11 +1020,11 @@ class InferenceProvider(Protocol):
     async def openai_completion(
         self,
         params: Annotated[OpenAICompletionRequestWithExtraBody, Body(...)],
-    ) -> OpenAICompletion:
+    ) -> OpenAICompletion | AsyncIterator[OpenAICompletion]:
         """Create completion.
 
         Generate an OpenAI-compatible completion for the given prompt using the specified model.
-        :returns: An OpenAICompletion.
+        :returns: An OpenAICompletion. When streaming, returns Server-Sent Events (SSE) with OpenAICompletion chunks.
         """
         ...
 
@@ -1036,7 +1036,7 @@ class InferenceProvider(Protocol):
         """Create chat completions.
 
         Generate an OpenAI-compatible chat completion for the given messages using the specified model.
-        :returns: An OpenAIChatCompletion.
+        :returns: An OpenAIChatCompletion. When streaming, returns Server-Sent Events (SSE) with OpenAIChatCompletionChunk objects.
         """
         ...