diff --git a/litellm/responses/file_search/emulated_handler.py b/litellm/responses/file_search/emulated_handler.py index 2ac1d3dea6..85a8f78998 100644 --- a/litellm/responses/file_search/emulated_handler.py +++ b/litellm/responses/file_search/emulated_handler.py @@ -339,9 +339,7 @@ def _synthesize_responses_api_response( output[0] = file_search_call item output[1] = message item (with citations) """ - import litellm - - return ResponsesAPIResponse( + synthesized = ResponsesAPIResponse( id=getattr(original_response, "id", f"resp_{uuid.uuid4().hex}"), object="response", created_at=getattr(original_response, "created_at", int(time.time())), @@ -351,6 +349,9 @@ def _synthesize_responses_api_response( usage=getattr(original_response, "usage", None), error=None, ) + if hasattr(original_response, "_hidden_params"): + synthesized._hidden_params = getattr(original_response, "_hidden_params") + return synthesized # --------------------------------------------------------------------------- @@ -513,7 +514,7 @@ async def aresponses_with_emulated_file_search( input=follow_up_input, model=model, tools=None, # no tools needed for the answer step - **{k: v for k, v in kwargs.items() if k not in ("tools",)}, + **kwargs, ), ) diff --git a/litellm/responses/main.py b/litellm/responses/main.py index 5438676c5f..761be5a2e1 100644 --- a/litellm/responses/main.py +++ b/litellm/responses/main.py @@ -742,6 +742,7 @@ def responses( "previous_response_id": previous_response_id, "reasoning": reasoning, "store": store, + "background": background, "stream": stream, "temperature": temperature, "text": text, @@ -749,6 +750,10 @@ def responses( "top_p": top_p, "truncation": truncation, "user": user, + "service_tier": service_tier, + "safety_identifier": safety_identifier, + "text_format": text_format, + "allowed_openai_params": allowed_openai_params, "extra_headers": extra_headers, "extra_query": extra_query, "extra_body": extra_body,