Merge branch 'main' into agent_session_unit_test

llama_stack/apis/agents/agents.py

@@ -706,6 +706,7 @@ class Agents(Protocol):
         temperature: float | None = None,
         text: OpenAIResponseText | None = None,
         tools: list[OpenAIResponseInputTool] | None = None,
+        include: list[str] | None = None,
         max_infer_iters: int | None = 10,  # this is an extension to the OpenAI API
     ) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
         """Create a new OpenAI response.
@@ -713,6 +714,7 @@ class Agents(Protocol):
         :param input: Input message(s) to create the response.
         :param model: The underlying LLM used for completions.
         :param previous_response_id: (Optional) if specified, the new response will be a continuation of the previous response. This can be used to easily fork-off new responses from existing responses.
+        :param include: (Optional) Additional fields to include in the response.
         :returns: An OpenAIResponseObject.
         """
         ...

llama_stack/apis/agents/openai_responses.py

@@ -170,6 +170,23 @@ class OpenAIResponseOutputMessageWebSearchToolCall(BaseModel):
     type: Literal["web_search_call"] = "web_search_call"
 
 
+class OpenAIResponseOutputMessageFileSearchToolCallResults(BaseModel):
+    """Search results returned by the file search operation.
+
+    :param attributes: (Optional) Key-value attributes associated with the file
+    :param file_id: Unique identifier of the file containing the result
+    :param filename: Name of the file containing the result
+    :param score: Relevance score for this search result (between 0 and 1)
+    :param text: Text content of the search result
+    """
+
+    attributes: dict[str, Any]
+    file_id: str
+    filename: str
+    score: float
+    text: str
+
+
 @json_schema_type
 class OpenAIResponseOutputMessageFileSearchToolCall(BaseModel):
     """File search tool call output message for OpenAI responses.
@@ -185,7 +202,7 @@ class OpenAIResponseOutputMessageFileSearchToolCall(BaseModel):
     queries: list[str]
     status: str
     type: Literal["file_search_call"] = "file_search_call"
-    results: list[dict[str, Any]] | None = None
+    results: list[OpenAIResponseOutputMessageFileSearchToolCallResults] | None = None
 
 
 @json_schema_type

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

@@ -327,10 +327,21 @@ class MetaReferenceAgentsImpl(Agents):
         temperature: float | None = None,
         text: OpenAIResponseText | None = None,
         tools: list[OpenAIResponseInputTool] | None = None,
+        include: list[str] | None = None,
         max_infer_iters: int | None = 10,
     ) -> OpenAIResponseObject:
         return await self.openai_responses_impl.create_openai_response(
-            input, model, instructions, previous_response_id, store, stream, temperature, text, tools, max_infer_iters
+            input,
+            model,
+            instructions,
+            previous_response_id,
+            store,
+            stream,
+            temperature,
+            text,
+            tools,
+            include,
+            max_infer_iters,
         )
 
     async def list_openai_responses(

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

@@ -38,6 +38,7 @@ from llama_stack.apis.agents.openai_responses import (
     OpenAIResponseOutputMessageContent,
     OpenAIResponseOutputMessageContentOutputText,
     OpenAIResponseOutputMessageFileSearchToolCall,
+    OpenAIResponseOutputMessageFileSearchToolCallResults,
     OpenAIResponseOutputMessageFunctionToolCall,
     OpenAIResponseOutputMessageMCPListTools,
     OpenAIResponseOutputMessageWebSearchToolCall,
@@ -333,6 +334,7 @@ class OpenAIResponsesImpl:
         temperature: float | None = None,
         text: OpenAIResponseText | None = None,
         tools: list[OpenAIResponseInputTool] | None = None,
+        include: list[str] | None = None,
         max_infer_iters: int | None = 10,
     ):
         stream = bool(stream)
@@ -826,12 +828,13 @@ class OpenAIResponsesImpl:
                         text = result.metadata["chunks"][i] if "chunks" in result.metadata else None
                         score = result.metadata["scores"][i] if "scores" in result.metadata else None
                         message.results.append(
-                            {
-                                "file_id": doc_id,
-                                "filename": doc_id,
-                                "text": text,
-                                "score": score,
-                            }
+                            OpenAIResponseOutputMessageFileSearchToolCallResults(
+                                file_id=doc_id,
+                                filename=doc_id,
+                                text=text,
+                                score=score,
+                                attributes={},
+                            )
                         )
                 if error_exc or (result.error_code and result.error_code > 0) or result.error_message:
                     message.status = "failed"