fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

litellm/llms/openai/completion/handler.py

@@ -49,6 +49,8 @@ class OpenAITextCompletion(BaseLLM):
         headers: Optional[dict] = None,
     ):
         try:
+            if headers:
+                optional_params = {**optional_params, "extra_headers": headers}
             if headers is None:
                 headers = self.validate_environment(api_key=api_key)
             if model is None or messages is None:

litellm/main.py

@@ -2135,9 +2135,6 @@ def completion(  # type: ignore # noqa: PLR0915
 
             headers = headers or litellm.headers
 
-            if extra_headers is not None:
-                optional_params["extra_headers"] = extra_headers
-
             ## LOAD CONFIG - if set
             config = litellm.OpenAITextCompletionConfig.get_config()
             for k, v in config.items():
@@ -2163,6 +2160,7 @@ def completion(  # type: ignore # noqa: PLR0915
             _response = openai_text_completions.completion(
                 model=model,
                 messages=messages,
+                headers=headers,
                 model_response=model_response,
                 print_verbose=print_verbose,
                 api_key=api_key,

tests/test_litellm/llms/openai/completion/test_completion_handler.py

@@ -0,0 +1,93 @@
+"""
+Tests that client headers are forwarded to the provider on the OpenAI
+text completion path.
+
+Regression tests for https://github.com/BerriAI/litellm/issues/27410
+"""
+
+import os
+import sys
+
+import pytest
+import respx
+from httpx import Response
+
+sys.path.insert(0, os.path.abspath("../../../../.."))
+
+import litellm
+from litellm import atext_completion, text_completion
+
+
+@pytest.fixture(autouse=True)
+def setup_env(monkeypatch):
+    monkeypatch.setenv("OPENAI_API_KEY", "sk-test-fake-key")
+
+
+@pytest.fixture
+def mock_completions_endpoint():
+    return respx.post("https://api.openai.com/v1/completions").mock(
+        return_value=Response(
+            200,
+            json={
+                "id": "cmpl-test123",
+                "object": "text_completion",
+                "created": 1677652288,
+                "model": "gpt-3.5-turbo-instruct",
+                "choices": [
+                    {
+                        "text": "hi",
+                        "index": 0,
+                        "logprobs": None,
+                        "finish_reason": "stop",
+                    }
+                ],
+                "usage": {
+                    "prompt_tokens": 1,
+                    "completion_tokens": 1,
+                    "total_tokens": 2,
+                },
+            },
+        )
+    )
+
+
+@respx.mock
+def test_completion_forwards_client_headers_to_provider(mock_completions_endpoint):
+    text_completion(
+        model="gpt-3.5-turbo-instruct",
+        prompt="hello",
+        max_tokens=5,
+        headers={"x-mycorp-llmcall-id": "abc-123"},
+    )
+
+    request_headers = mock_completions_endpoint.calls.last.request.headers
+    assert request_headers["x-mycorp-llmcall-id"] == "abc-123"
+
+
+@respx.mock
+def test_completion_forwards_extra_headers_to_provider(mock_completions_endpoint):
+    text_completion(
+        model="gpt-3.5-turbo-instruct",
+        prompt="hello",
+        max_tokens=5,
+        extra_headers={"x-mycorp-llmcall-id": "abc-123"},
+    )
+
+    request_headers = mock_completions_endpoint.calls.last.request.headers
+    assert request_headers["x-mycorp-llmcall-id"] == "abc-123"
+
+
+@respx.mock
+async def test_acompletion_forwards_client_headers_to_provider(
+    mock_completions_endpoint, monkeypatch
+):
+    monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
+    await atext_completion(
+        model="gpt-3.5-turbo-instruct",
+        prompt="hello",
+        max_tokens=5,
+        headers={"x-mycorp-llmcall-id": "abc-123"},
+    )
+
+    request_headers = mock_completions_endpoint.calls.last.request.headers
+    assert request_headers["x-mycorp-llmcall-id"] == "abc-123"