fix(ovhcloud): remove dead transform_response override

The parent OpenAIGPTConfig already handles reasoning->reasoning_content
for non-streaming via _extract_reasoning_content. The override was dead
code giving false confidence. Streaming fix in chunk_parser is the only
change needed for chat completions.

Addresses Agent Shin review feedback on #26595

litellm/llms/ovhcloud/chat/transformation.py

@@ -5,15 +5,15 @@ Our unified API follows the OpenAI standard.
 More information on our website: https://endpoints.ai.cloud.ovh.net
 """
 
-from typing import Any, Optional, Union, List
+from typing import Optional, Union, List
 
 import httpx
-from litellm.utils import ModelResponse, ModelResponseStream
+from litellm.utils import ModelResponseStream
 from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
 from litellm.llms.ovhcloud.utils import OVHCloudException
 from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
-from litellm.llms.base_llm.chat.transformation import LiteLLMLoggingObj
+
 from litellm.types.llms.openai import AllMessageValues
 
 
@@ -75,48 +75,7 @@ class OVHCloudChatConfig(OpenAIGPTConfig):
         response.update(extra_body)
         return response
 
-    def transform_response(
-        self,
-        model: str,
-        raw_response: httpx.Response,
-        model_response: ModelResponse,
-        logging_obj: LiteLLMLoggingObj,
-        request_data: dict,
-        messages: List[AllMessageValues],
-        optional_params: dict,
-        litellm_params: dict,
-        encoding: Any,
-        api_key: Optional[str] = None,
-        json_mode: Optional[bool] = None,
-    ) -> ModelResponse:
-        # Call parent to do standard OpenAI response parsing
-        model_response = super().transform_response(
-            model=model,
-            raw_response=raw_response,
-            model_response=model_response,
-            logging_obj=logging_obj,
-            request_data=request_data,
-            messages=messages,
-            optional_params=optional_params,
-            litellm_params=litellm_params,
-            encoding=encoding,
-            api_key=api_key,
-            json_mode=json_mode,
-        )
 
-        # OVHCloud field migration (deadline: 2026-05-11):
-        # `reasoning_content` is replaced by `reasoning` in non-streaming responses.
-        # Normalise to `reasoning_content` so downstream consumers
-        # see a consistent key during the transition window.
-        for choice in model_response.choices:
-            message = getattr(choice, "message", None)
-            if message is not None:
-                reasoning_new = getattr(message, "reasoning", None)
-                reasoning_legacy = getattr(message, "reasoning_content", None)
-                if reasoning_new is not None and reasoning_legacy is None:
-                    message.reasoning_content = reasoning_new
-
-        return model_response
 
 
 class OVHCloudChatCompletionStreamingHandler(BaseModelResponseIterator):

tests/test_litellm/llms/ovhcloud/test_ovhcloud_chat_transformation.py

@@ -4,7 +4,7 @@ Unit tests for OVHCloud AI Endpoints chat integration.
 
 import os
 import sys
-import litellm
+
 import pytest
 
 from litellm.llms.ovhcloud.utils import OVHCloudException
@@ -367,49 +367,3 @@ class TestOVHCloudReasoningFieldMigration:
         assert result.choices[0]["delta"]["reasoning_content"] == "legacy field"
 
 
-    def test_non_streaming_new_reasoning_field(self):
-            """Non-streaming: new `reasoning` field should be mapped to `reasoning_content`."""
-            from unittest.mock import MagicMock, patch
-            import json
-
-            config = OVHCloudChatConfig()
-
-            raw_response = MagicMock()
-            raw_response.status_code = 200
-            raw_response.headers = {"Content-Type": "application/json"}
-            raw_response.text = json.dumps({
-                "id": "test-id",
-                "object": "chat.completion",
-                "created": 1234567890,
-                "model": "test-model",
-                "choices": [
-                    {
-                        "index": 0,
-                        "message": {
-                            "role": "assistant",
-                            "content": "Hello!",
-                            "reasoning": "Let me think...",
-                        },
-                        "finish_reason": "stop",
-                    }
-                ],
-                "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15},
-            })
-            raw_response.json.return_value = json.loads(raw_response.text)
-
-            model_response = litellm.ModelResponse()
-
-            result = config.transform_response(
-                model="ovhcloud/test-model",
-                raw_response=raw_response,
-                model_response=model_response,
-                logging_obj=MagicMock(),
-                request_data={},
-                messages=[],
-                optional_params={},
-                litellm_params={},
-                encoding=None,
-                api_key="test-key",
-            )
-
-            assert result.choices[0].message.reasoning_content == "Let me think..."