feat(responses): add output_text delta events to responses (#2265)

This adds initial streaming support to the Responses API. 

This PR makes sure that the _first_ inference call made to chat
completions streams out.

There's more to be done:
 - tool call output tokens need to stream out when possible
- we need to loop through multiple rounds of inference and they all need
to stream out.

## Test Plan

Added a test. Executed as:

```
FIREWORKS_API_KEY=... \
  pytest -s -v 'tests/verifications/openai_api/test_responses.py' \
  --provider=stack:fireworks --model meta-llama/Llama-4-Scout-17B-16E-Instruct
```

Then, started a llama stack fireworks distro and tested against it like
this:

```
OPENAI_API_KEY=blah \
   pytest -s -v 'tests/verifications/openai_api/test_responses.py' \
   --base-url http://localhost:8321/v1/openai/v1 \
  --model meta-llama/Llama-4-Scout-17B-16E-Instruct 
```

llama_stack/apis/agents/openai_responses.py

@@ -149,6 +149,16 @@ class OpenAIResponseObjectStreamResponseCreated(BaseModel):
     type: Literal["response.created"] = "response.created"
 
 
+@json_schema_type
+class OpenAIResponseObjectStreamResponseOutputTextDelta(BaseModel):
+    content_index: int
+    delta: str
+    item_id: str
+    output_index: int
+    sequence_number: int
+    type: Literal["response.output_text.delta"] = "response.output_text.delta"
+
+
 @json_schema_type
 class OpenAIResponseObjectStreamResponseCompleted(BaseModel):
     response: OpenAIResponseObject
@@ -156,7 +166,9 @@ class OpenAIResponseObjectStreamResponseCompleted(BaseModel):
 
 
 OpenAIResponseObjectStream = Annotated[
-    OpenAIResponseObjectStreamResponseCreated | OpenAIResponseObjectStreamResponseCompleted,
+    OpenAIResponseObjectStreamResponseCreated
+    | OpenAIResponseObjectStreamResponseOutputTextDelta
+    | OpenAIResponseObjectStreamResponseCompleted,
     Field(discriminator="type"),
 ]
 register_schema(OpenAIResponseObjectStream, name="OpenAIResponseObjectStream")