Merge branch 'meta-llama:main' into dell-distro

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/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

@@ -333,6 +333,7 @@ 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)