update api

docs/_static/llama-stack-spec.html

@@ -7283,6 +7283,9 @@
                         "items": {
                             "$ref": "#/components/schemas/OpenAIResponseInputTool"
                         }
+                    },
+                    "max_infer_iters": {
+                        "type": "integer"
                     }
                 },
                 "additionalProperties": false,

docs/_static/llama-stack-spec.yaml

@@ -5149,6 +5149,8 @@ components:
           type: array
           items:
             $ref: '#/components/schemas/OpenAIResponseInputTool'
+        max_infer_iters:
+          type: integer
       additionalProperties: false
       required:
         - input

llama_stack/apis/agents/agents.py

@@ -604,6 +604,7 @@ class Agents(Protocol):
         stream: bool | None = False,
         temperature: float | None = None,
         tools: list[OpenAIResponseInputTool] | None = None,
+        max_infer_iters: int | None = 10,  # this is an extension to the OpenAI API
     ) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
         """Create a new OpenAI response.
 

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

@@ -325,9 +325,10 @@ class MetaReferenceAgentsImpl(Agents):
         stream: bool | None = False,
         temperature: float | None = None,
         tools: list[OpenAIResponseInputTool] | 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, tools
+            input, model, instructions, previous_response_id, store, stream, temperature, tools, max_infer_iters
         )
 
     async def list_openai_responses(