fix: stop use_chat_completions_api flag from leaking into provider request body (#29447)

* fix: stop use_chat_completions_api flag from leaking into provider request body

use_chat_completions_api is a LiteLLM control flag that forces the
/responses -> /chat/completions bridge. It was missing from
all_litellm_params, so get_non_default_completion_params treated it as a
model-specific param and forwarded it to the upstream provider. A
model-level "use_chat_completions_api: true" in the proxy config therefore
reached the chat-completions path and was rejected by strict providers
(OpenAI/Anthropic) with HTTP 400 for an unknown body field.

Register it as a known internal param so it is stripped on every path
(completion, the responses bridge that calls litellm.completion, and
filter_out_litellm_params).

Adds a regression test driving litellm.completion() with a mocked OpenAI
client that asserts the flag never reaches the request body.

* test: clarify extra_body assertion in use_chat_completions_api leak test

Replace the misleading 'not in ... or {}' precedence idiom with an explicit
parenthesized guard that also handles extra_body being None.

(cherry picked from commit acbbfe9cae)

litellm/types/utils.py

@@ -3148,6 +3148,7 @@ all_litellm_params = (
         "allowed_openai_params",
         "litellm_session_id",
         "use_litellm_proxy",
+        "use_chat_completions_api",
         "prompt_label",
         "shared_session",
         "search_tool_name",

tests/test_litellm/llms/openai/test_use_chat_completions_api_no_leak.py

@@ -0,0 +1,74 @@
+"""
+Regression test for issue #28146.
+
+`use_chat_completions_api` is a LiteLLM-internal control flag (it forces the
+/responses -> /chat/completions bridge). When set as a model-level param in the
+proxy config, it must never be forwarded to the upstream provider's request
+body. OpenAI/Anthropic reject unknown body params with HTTP 400.
+"""
+
+import os
+import sys
+from unittest.mock import MagicMock
+
+sys.path.insert(0, os.path.abspath("../../../.."))
+
+import litellm
+from litellm.types.utils import all_litellm_params
+from litellm.utils import get_non_default_completion_params
+
+
+def test_use_chat_completions_api_is_a_known_litellm_param():
+    assert "use_chat_completions_api" in all_litellm_params
+
+
+def test_use_chat_completions_api_not_forwarded_as_provider_param():
+    forwarded = get_non_default_completion_params(
+        {"use_chat_completions_api": True, "temperature": 0.5}
+    )
+    assert "use_chat_completions_api" not in forwarded
+
+
+def test_completion_does_not_leak_flag_into_provider_request_body():
+    mock_response = MagicMock()
+    mock_response.model_dump.return_value = {
+        "id": "chatcmpl-1",
+        "object": "chat.completion",
+        "created": 1234567890,
+        "model": "gpt-4o-mini",
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": "hi"},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": {
+            "prompt_tokens": 1,
+            "completion_tokens": 1,
+            "total_tokens": 2,
+        },
+    }
+
+    mock_raw_response = MagicMock()
+    mock_raw_response.headers = {}
+    mock_raw_response.parse.return_value = mock_response
+
+    mock_client = MagicMock()
+    mock_client.chat.completions.with_raw_response.create.return_value = (
+        mock_raw_response
+    )
+
+    litellm.completion(
+        model="openai/gpt-4o-mini",
+        messages=[{"role": "user", "content": "hi"}],
+        use_chat_completions_api=True,
+        api_key="sk-test",
+        client=mock_client,
+    )
+
+    create_kwargs = (
+        mock_client.chat.completions.with_raw_response.create.call_args.kwargs
+    )
+    assert "use_chat_completions_api" not in create_kwargs
+    assert "use_chat_completions_api" not in (create_kwargs.get("extra_body") or {})