refactor(responses/): refactor to move responses_to_completion in separate folder

future work to support completion_to_responses bridge

allow calling codex mini via chat completions (and other endpoints)

enterprise/litellm_enterprise/enterprise_callbacks/session_handler.py

@@ -13,7 +13,7 @@ from litellm.types.llms.openai import (
 from litellm.types.utils import ChatCompletionMessageToolCall, Message, ModelResponse
 
 if TYPE_CHECKING:
-    from litellm.responses.litellm_completion_transformation.transformation import (
+    from litellm.responses.litellm_completion_transformation import (
         ChatCompletionSession,
     )
 else:
@@ -28,7 +28,7 @@ class _ENTERPRISE_ResponsesSessionHandler:
         """
         Return the chat completion message history for a previous response id
         """
-        from litellm.responses.litellm_completion_transformation.transformation import (
+        from litellm.responses.litellm_completion_transformation import (
             ChatCompletionSession,
             LiteLLMCompletionResponsesConfig,
         )

litellm/llms/gemini/realtime/transformation.py

@@ -13,7 +13,7 @@ from litellm.llms.base_llm.realtime.transformation import BaseRealtimeConfig
 from litellm.llms.vertex_ai.gemini.vertex_and_google_ai_studio_gemini import (
     VertexGeminiConfig,
 )
-from litellm.responses.litellm_completion_transformation.transformation import (
+from litellm.responses.litellm_completion_transformation import (
     LiteLLMCompletionResponsesConfig,
 )
 from litellm.types.llms.gemini import (

litellm/responses/litellm_completion_transformation/__init__.py

@@ -0,0 +1,13 @@
+from .responses_to_completion_bridge.handler import (
+    LiteLLMCompletionTransformationHandler,
+)
+from .responses_to_completion_bridge.transformation import (
+    ChatCompletionSession,
+    LiteLLMCompletionResponsesConfig,
+)
+
+__all__ = [
+    "LiteLLMCompletionTransformationHandler",
+    "ChatCompletionSession",
+    "LiteLLMCompletionResponsesConfig",
+]

litellm/responses/litellm_completion_transformation/responses_to_completion_bridge/handler.py

@@ -5,12 +5,6 @@ Handler for transforming responses api requests to litellm.completion requests
 from typing import Any, Coroutine, Optional, Union
 
 import litellm
-from litellm.responses.litellm_completion_transformation.streaming_iterator import (
-    LiteLLMCompletionStreamingIterator,
-)
-from litellm.responses.litellm_completion_transformation.transformation import (
-    LiteLLMCompletionResponsesConfig,
-)
 from litellm.responses.streaming_iterator import BaseResponsesAPIStreamingIterator
 from litellm.types.llms.openai import (
     ResponseInputParam,
@@ -19,9 +13,11 @@ from litellm.types.llms.openai import (
 )
 from litellm.types.utils import ModelResponse
 
+from .streaming_iterator import LiteLLMCompletionStreamingIterator
+from .transformation import LiteLLMCompletionResponsesConfig
+
 
 class LiteLLMCompletionTransformationHandler:
-
     def response_api_handler(
         self,
         model: str,
@@ -38,15 +34,13 @@ class LiteLLMCompletionTransformationHandler:
             Any, Any, Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]
         ],
     ]:
-        litellm_completion_request: dict = (
-            LiteLLMCompletionResponsesConfig.transform_responses_api_request_to_chat_completion_request(
-                model=model,
-                input=input,
-                responses_api_request=responses_api_request,
-                custom_llm_provider=custom_llm_provider,
-                stream=stream,
-                **kwargs,
-            )
+        litellm_completion_request: dict = LiteLLMCompletionResponsesConfig.transform_responses_api_request_to_chat_completion_request(
+            model=model,
+            input=input,
+            responses_api_request=responses_api_request,
+            custom_llm_provider=custom_llm_provider,
+            stream=stream,
+            **kwargs,
         )
 
         if _is_async:
@@ -65,12 +59,10 @@ class LiteLLMCompletionTransformationHandler:
         )
 
         if isinstance(litellm_completion_response, ModelResponse):
-            responses_api_response: ResponsesAPIResponse = (
-                LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
-                    chat_completion_response=litellm_completion_response,
-                    request_input=input,
-                    responses_api_request=responses_api_request,
-                )
+            responses_api_response: ResponsesAPIResponse = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+                chat_completion_response=litellm_completion_response,
+                request_input=input,
+                responses_api_request=responses_api_request,
             )
 
             return responses_api_response
@@ -89,7 +81,6 @@ class LiteLLMCompletionTransformationHandler:
         responses_api_request: ResponsesAPIOptionalRequestParams,
         **kwargs,
     ) -> Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]:
-
         previous_response_id: Optional[str] = responses_api_request.get(
             "previous_response_id"
         )
@@ -107,12 +98,10 @@ class LiteLLMCompletionTransformationHandler:
         )
 
         if isinstance(litellm_completion_response, ModelResponse):
-            responses_api_response: ResponsesAPIResponse = (
-                LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
-                    chat_completion_response=litellm_completion_response,
-                    request_input=request_input,
-                    responses_api_request=responses_api_request,
-                )
+            responses_api_response: ResponsesAPIResponse = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(
+                chat_completion_response=litellm_completion_response,
+                request_input=request_input,
+                responses_api_request=responses_api_request,
             )
 
             return responses_api_response

litellm/responses/litellm_completion_transformation/responses_to_completion_bridge/streaming_iterator.py

@@ -2,7 +2,7 @@ from typing import List, Optional, Union
 
 import litellm
 from litellm.main import stream_chunk_builder
-from litellm.responses.litellm_completion_transformation.transformation import (
+from litellm.responses.litellm_completion_transformation import (
     LiteLLMCompletionResponsesConfig,
 )
 from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator
@@ -144,7 +144,6 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
             Union[ModelResponse, TextCompletionResponse]
         ] = stream_chunk_builder(chunks=self.collected_chat_completion_chunks)
         if litellm_model_response and isinstance(litellm_model_response, ModelResponse):
-
             return ResponseCompletedEvent(
                 type=ResponsesAPIStreamEvents.RESPONSE_COMPLETED,
                 response=LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response(

litellm/responses/main.py

@@ -10,7 +10,7 @@ from litellm.constants import request_timeout
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig
 from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
-from litellm.responses.litellm_completion_transformation.handler import (
+from litellm.responses.litellm_completion_transformation import (
     LiteLLMCompletionTransformationHandler,
 )
 from litellm.responses.utils import ResponsesAPIRequestUtils
@@ -191,11 +191,11 @@ def responses(
         )
 
         # get provider config
-        responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
-            ProviderConfigManager.get_provider_responses_api_config(
-                model=model,
-                provider=litellm.LlmProviders(custom_llm_provider),
-            )
+        responses_api_provider_config: Optional[
+            BaseResponsesAPIConfig
+        ] = ProviderConfigManager.get_provider_responses_api_config(
+            model=model,
+            provider=litellm.LlmProviders(custom_llm_provider),
         )
 
         local_vars.update(kwargs)
@@ -385,11 +385,11 @@ def delete_responses(
             raise ValueError("custom_llm_provider is required but passed as None")
 
         # get provider config
-        responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
-            ProviderConfigManager.get_provider_responses_api_config(
-                model=None,
-                provider=litellm.LlmProviders(custom_llm_provider),
-            )
+        responses_api_provider_config: Optional[
+            BaseResponsesAPIConfig
+        ] = ProviderConfigManager.get_provider_responses_api_config(
+            model=None,
+            provider=litellm.LlmProviders(custom_llm_provider),
         )
 
         if responses_api_provider_config is None:
@@ -564,11 +564,11 @@ def get_responses(
             raise ValueError("custom_llm_provider is required but passed as None")
 
         # get provider config
-        responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
-            ProviderConfigManager.get_provider_responses_api_config(
-                model=None,
-                provider=litellm.LlmProviders(custom_llm_provider),
-            )
+        responses_api_provider_config: Optional[
+            BaseResponsesAPIConfig
+        ] = ProviderConfigManager.get_provider_responses_api_config(
+            model=None,
+            provider=litellm.LlmProviders(custom_llm_provider),
         )
 
         if responses_api_provider_config is None:
@@ -720,11 +720,11 @@ def list_input_items(
         if custom_llm_provider is None:
             raise ValueError("custom_llm_provider is required but passed as None")
 
-        responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
-            ProviderConfigManager.get_provider_responses_api_config(
-                model=None,
-                provider=litellm.LlmProviders(custom_llm_provider),
-            )
+        responses_api_provider_config: Optional[
+            BaseResponsesAPIConfig
+        ] = ProviderConfigManager.get_provider_responses_api_config(
+            model=None,
+            provider=litellm.LlmProviders(custom_llm_provider),
         )
 
         if responses_api_provider_config is None:

tests/llm_translation/test_openai.py

@@ -469,3 +469,15 @@ async def test_openai_pdf_url(model):
 
     assert "file_data" in request["raw_request_body"]["messages"][0]["content"][1]["file"]
 
+
+
+def test_openai_codex():
+    from litellm import completion
+
+    response = completion(
+        model="openai/codex-mini-latest",
+        messages=[{"role": "user", "content": "Hey!"}],
+    )
+    print("response: ", response)
+
+    assert response.choices[0].message.content is not None

tests/test_litellm/responses/litellm_completion_transformation/test_litellm_completion_responses.py

@@ -10,7 +10,7 @@ sys.path.insert(
     0, os.path.abspath("../../..")
 )  # Adds the parent directory to the system path
 
-from litellm.responses.litellm_completion_transformation.transformation import (
+from litellm.responses.litellm_completion_transformation import (
     LiteLLMCompletionResponsesConfig,
 )