fix: annotations list and web_search_preview in Responses (#2520)

# What does this PR do?


These are a couple of fixes to get an example LangChain app working with
our OpenAI Responses API implementation.

The Responses API spec requires an annotations array in
`output[*].content[*].annotations` and we were not providing one. So,
this adds that as an empty list, even though we don't do anything to
populate it yet. This prevents an error from client libraries like
Langchain that expect this field to always exist, even if an empty list.

The other fix is `web_search_preview` is a valid name for the web search
tool in the Responses API, but we only responded to `web_search` or
`web_search_preview_2025_03_11`.


## Test Plan


The existing Responses unit tests were expanded to test these cases,
via:

```
pytest -sv tests/unit/providers/agents/meta_reference/test_openai_responses.py
```

The existing test_openai_responses.py integration tests still pass with
this change, tested as below with Fireworks:

```
uv run llama stack run llama_stack/templates/starter/run.yaml

LLAMA_STACK_CONFIG=http://localhost:8321 \
uv run pytest -sv tests/integration/agents/test_openai_responses.py \
  --text-model accounts/fireworks/models/llama4-scout-instruct-basic
```

Lastly, this example LangChain app now works with Llama stack (tested
with Ollama in the starter template in this case). This LangChain code
is using the example snippets for using Responses API at
https://python.langchain.com/docs/integrations/chat/openai/#responses-api

```python
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="http://localhost:8321/v1/openai/v1",
    api_key="fake",
    model="ollama/meta-llama/Llama-3.2-3B-Instruct",
)

tool = {"type": "web_search_preview"}
llm_with_tools = llm.bind_tools([tool])

response = llm_with_tools.invoke("What was a positive news story from today?")

print(response.content)
```

Signed-off-by: Ben Browning <bbrownin@redhat.com>

llama_stack/apis/agents/openai_responses.py

@@ -44,10 +44,55 @@ OpenAIResponseInputMessageContent = Annotated[
 register_schema(OpenAIResponseInputMessageContent, name="OpenAIResponseInputMessageContent")
 
 
+@json_schema_type
+class OpenAIResponseAnnotationFileCitation(BaseModel):
+    type: Literal["file_citation"] = "file_citation"
+    file_id: str
+    filename: str
+    index: int
+
+
+@json_schema_type
+class OpenAIResponseAnnotationCitation(BaseModel):
+    type: Literal["url_citation"] = "url_citation"
+    end_index: int
+    start_index: int
+    title: str
+    url: str
+
+
+@json_schema_type
+class OpenAIResponseAnnotationContainerFileCitation(BaseModel):
+    type: Literal["container_file_citation"] = "container_file_citation"
+    container_id: str
+    end_index: int
+    file_id: str
+    filename: str
+    start_index: int
+
+
+@json_schema_type
+class OpenAIResponseAnnotationFilePath(BaseModel):
+    type: Literal["file_path"] = "file_path"
+    file_id: str
+    index: int
+
+
+OpenAIResponseAnnotations = Annotated[
+    OpenAIResponseAnnotationFileCitation
+    | OpenAIResponseAnnotationCitation
+    | OpenAIResponseAnnotationContainerFileCitation
+    | OpenAIResponseAnnotationFilePath,
+    Field(discriminator="type"),
+]
+register_schema(OpenAIResponseAnnotations, name="OpenAIResponseAnnotations")
+
+
 @json_schema_type
 class OpenAIResponseOutputMessageContentOutputText(BaseModel):
     text: str
     type: Literal["output_text"] = "output_text"
+    annotations: list[OpenAIResponseAnnotations] = Field(default_factory=list)
 
 
 OpenAIResponseOutputMessageContent = Annotated[
@@ -384,9 +429,16 @@ OpenAIResponseInput = Annotated[
 register_schema(OpenAIResponseInput, name="OpenAIResponseInput")
 
 
+# Must match type Literals of OpenAIResponseInputToolWebSearch below
+WebSearchToolTypes = ["web_search", "web_search_preview", "web_search_preview_2025_03_11"]
+
+
 @json_schema_type
 class OpenAIResponseInputToolWebSearch(BaseModel):
-    type: Literal["web_search"] | Literal["web_search_preview_2025_03_11"] = "web_search"
+    # Must match values of WebSearchToolTypes above
+    type: Literal["web_search"] | Literal["web_search_preview"] | Literal["web_search_preview_2025_03_11"] = (
+        "web_search"
+    )
     # TODO: actually use search_context_size somewhere...
     search_context_size: str | None = Field(default="medium", pattern="^low|medium|high$")
     # TODO: add user_location

llama_stack/providers/inline/agents/meta_reference/openai_responses.py

@@ -42,6 +42,7 @@ from llama_stack.apis.agents.openai_responses import (
     OpenAIResponseOutputMessageWebSearchToolCall,
     OpenAIResponseText,
     OpenAIResponseTextFormat,
+    WebSearchToolTypes,
 )
 from llama_stack.apis.common.content_types import TextContentItem
 from llama_stack.apis.inference.inference import (
@@ -609,7 +610,7 @@ class OpenAIResponsesImpl:
             # TODO: Handle other tool types
             if input_tool.type == "function":
                 chat_tools.append(ChatCompletionToolParam(type="function", function=input_tool.model_dump()))
-            elif input_tool.type == "web_search":
+            elif input_tool.type in WebSearchToolTypes:
                 tool_name = "web_search"
                 tool = await self.tool_groups_api.get_tool(tool_name)
                 if not tool: