fix!: Enhance response API support to not fail with tool calling (#3385)

# What does this PR do?
Introduces two main fixes to enhance the stability of Responses API when
dealing with tool calling responses and structured outputs.

### Changes Made

1. It added OpenAIResponseOutputMessageMCPCall and ListTools to
OpenAIResponseInput but
https://github.com/llamastack/llama-stack/pull/3810 got merge that did
the same in a different way. Still this PR does it in a way that keep
the sync between OpenAIResponsesOutput and the allowed objects in
OpenAIResponseInput.

2. Add protection in case self.ctx.response_format does not have type
attribute

BREAKING CHANGE: OpenAIResponseInput now uses OpenAIResponseOutput union
type.
This is semantically equivalent - all previously accepted types are
still supported
via the OpenAIResponseOutput union. This improves type consistency and
maintainability.

llama_stack/apis/agents/openai_responses.py

@@ -1254,14 +1254,9 @@ class OpenAIResponseInputFunctionToolCallOutput(BaseModel):
 
 OpenAIResponseInput = Annotated[
     # Responses API allows output messages to be passed in as input
-    OpenAIResponseOutputMessageWebSearchToolCall
-    | OpenAIResponseOutputMessageFileSearchToolCall
-    | OpenAIResponseOutputMessageFunctionToolCall
+    OpenAIResponseOutput
     | OpenAIResponseInputFunctionToolCallOutput
-    | OpenAIResponseMCPApprovalRequest
     | OpenAIResponseMCPApprovalResponse
-    | OpenAIResponseOutputMessageMCPCall
-    | OpenAIResponseOutputMessageMCPListTools
     | OpenAIResponseMessage,
     Field(union_mode="left_to_right"),
 ]

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

@@ -217,7 +217,9 @@ class StreamingResponseOrchestrator:
             while True:
                 # Text is the default response format for chat completion so don't need to pass it
                 # (some providers don't support non-empty response_format when tools are present)
-                response_format = None if self.ctx.response_format.type == "text" else self.ctx.response_format
+                response_format = (
+                    None if getattr(self.ctx.response_format, "type", None) == "text" else self.ctx.response_format
+                )
                 logger.debug(f"calling openai_chat_completion with tools: {self.ctx.chat_tools}")
 
                 params = OpenAIChatCompletionRequestWithExtraBody(