diff --git a/litellm/main.py b/litellm/main.py index 011617670b4..c2e7a8283e9 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -678,7 +678,10 @@ async def acompletion( if custom_llm_provider is None: _supplemental: Final = cast( # cast-ok: kwargs values are request-scoped objects "dict[str, object]", - {k: kwargs[k] for k in OPTIONAL_KWARGS_KEYS | {"provider_specific_header"} if k in kwargs}, + { + **{k: kwargs[k] for k in OPTIONAL_KWARGS_KEYS | {"provider_specific_header"} if k in kwargs}, + "extra_headers": extra_headers, + }, ) _, custom_llm_provider, _, _ = get_llm_provider( model=model, @@ -5680,7 +5683,8 @@ def completion( model = deployment_id custom_llm_provider = "azure" _supplemental_provider_params: Final = { - k: kwargs[k] for k in OPTIONAL_KWARGS_KEYS | {"provider_specific_header"} if k in kwargs + **{k: kwargs[k] for k in OPTIONAL_KWARGS_KEYS | {"provider_specific_header"} if k in kwargs}, + "extra_headers": extra_headers, } model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider( model=model, diff --git a/litellm/responses/main.py b/litellm/responses/main.py index 269a10426ab..d993b05f5b7 100644 --- a/litellm/responses/main.py +++ b/litellm/responses/main.py @@ -911,7 +911,8 @@ async def aresponses( model=model, api_base=local_vars.get("base_url", None), litellm_params=GenericLiteLLMParams( - **cast("dict[str, object]", kwargs) # cast-ok: kwargs is the untyped request dict + extra_headers=extra_headers, + **cast("dict[str, object]", kwargs), # cast-ok: kwargs is the untyped request dict ), ) # Update local_vars with detected provider (fixes #19782) @@ -974,7 +975,7 @@ async def aresponses( original_model=original_model, swapped_model=model, custom_llm_provider=custom_llm_provider, - kwargs=kwargs, + kwargs={**kwargs, "extra_headers": extra_headers}, prompt_id=prompt_id, ) kwargs.pop("prompt_id", None) @@ -1153,7 +1154,7 @@ def _apply_prompt_management_to_responses_call( original_model=original_model, swapped_model=model, custom_llm_provider=custom_llm_provider, - kwargs=kwargs, + kwargs={**kwargs, "extra_headers": local_vars.get("extra_headers")}, prompt_id=prompt_id, ) ) @@ -1509,7 +1510,8 @@ def responses( model=model, api_base=local_vars.get("base_url", None), litellm_params=GenericLiteLLMParams( - **cast("dict[str, object]", kwargs) # cast-ok: kwargs is the untyped request dict + extra_headers=extra_headers, + **cast("dict[str, object]", kwargs), # cast-ok: kwargs is the untyped request dict ), ) local_vars["custom_llm_provider"] = custom_llm_provider @@ -1527,7 +1529,7 @@ def responses( from litellm.litellm_core_utils.core_helpers import attribute_or_none - litellm_params: Final = GenericLiteLLMParams(**kwargs) + litellm_params: Final = GenericLiteLLMParams(extra_headers=extra_headers, **kwargs) provider_headers: Final = ResponsesAPIRequestUtils.merge_provider_specific_headers( extra_headers=extra_headers, provider_specific_header=attribute_or_none(litellm_params, "provider_specific_header"), diff --git a/tests/unit/litellm_core_utils/test_get_llm_provider_logic.py b/tests/unit/litellm_core_utils/test_get_llm_provider_logic.py index 098339657c5..e9e3f7b8174 100644 --- a/tests/unit/litellm_core_utils/test_get_llm_provider_logic.py +++ b/tests/unit/litellm_core_utils/test_get_llm_provider_logic.py @@ -1,5 +1,9 @@ +from collections.abc import Iterator +from pathlib import Path from typing import Final +import respx + import asyncio, httpx, importlib, os import pytest @@ -719,14 +723,14 @@ def test_opencode_affinity_resolution_preserves_existing_transport(prefix: str) @pytest.fixture -def chatgpt_login_tripwire(monkeypatch: pytest.MonkeyPatch, tmp_path) -> None: - from litellm.llms.chatgpt.authenticator import Authenticator - - def _tripwire(self: Authenticator) -> str: - raise AssertionError("metadata lookup ran the ChatGPT OAuth device flow") - - monkeypatch.setenv("CHATGPT_TOKEN_DIR", str(tmp_path / "missing-login")) - monkeypatch.setattr(Authenticator, "get_access_token", _tripwire) +def chatgpt_login_tripwire(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> Iterator[None]: + blocked: Final = tmp_path / "blocked" + blocked.write_text("ordinary file") + monkeypatch.setenv("CHATGPT_TOKEN_DIR", str(blocked / "unused")) + monkeypatch.delenv("CHATGPT_AUTH_FILE", raising=False) + with respx.mock as transport: + yield + assert len(transport.calls) == 0 @pytest.mark.parametrize( diff --git a/tests/unit/llms/chatgpt/chat/test_chatgpt_chat_transformation.py b/tests/unit/llms/chatgpt/chat/test_chatgpt_chat_transformation.py index 6d1097a90fb..91007b20ae8 100644 --- a/tests/unit/llms/chatgpt/chat/test_chatgpt_chat_transformation.py +++ b/tests/unit/llms/chatgpt/chat/test_chatgpt_chat_transformation.py @@ -171,7 +171,9 @@ class TestChatGPTMultiAccountChat: def _subscription_response(request: httpx.Request) -> httpx.Response: account: Final = request.headers["ChatGPT-Account-Id"] - assert request.headers["Authorization"] == f"Bearer token-{account.removeprefix('acct-')}" + assert request.headers["Authorization"] in ( + f"Bearer token-{account.removeprefix('acct-')}", f"Bearer {_client_token(account)}" + ) assert "chatgpt_auth_file" not in request.content.decode() message: Final = { "id": "msg_test", @@ -498,3 +500,54 @@ async def test_cross_provider_fallback_does_not_receive_the_chatgpt_login( assert response.output[0].content[0].text == "fallback" assert fallback.calls.last.request.headers["Authorization"] == "Bearer sk-example-fallback" assert "ChatGPT-Account-Id" not in fallback.calls.last.request.headers + + +@pytest.mark.parametrize("endpoint", ["chat", "responses"]) +@pytest.mark.parametrize("async_call", [False, True]) +@pytest.mark.parametrize("with_prompt", [False, True]) +@pytest.mark.asyncio +async def test_sdk_extra_headers_use_client_login_without_gateway_auth( + tmp_path: Path, monkeypatch: pytest.MonkeyPatch, endpoint: str, async_call: bool, with_prompt: bool +) -> None: + blocked: Final = tmp_path / "blocked" + blocked.write_text("ordinary file") + monkeypatch.setenv("CHATGPT_TOKEN_DIR", str(blocked / "unused")) + monkeypatch.delenv("CHATGPT_AUTH_FILE", raising=False) + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + headers: Final = {"Authorization": f"Bearer {_client_token('acct-client-a')}"} + prompt_params: Final = {"prompt_id": "sdk-client"} if with_prompt else {} + if with_prompt: + monkeypatch.setattr( + litellm, + "callbacks", + [ + DotpromptManager( + prompt_id="sdk-client", + prompt_data={"content": "Hello", "metadata": {"model": "chatgpt/gpt-6-luna"}}, + ) + ], + ) + with respx.mock as transport: + transport.post("https://chatgpt.com/backend-api/codex/responses").mock(side_effect=_subscription_response) + if endpoint == "chat": + params: Final = { + "model": "chatgpt/gpt-6.1-sol", + "messages": [{"role": "user", "content": "Hello"}], + "extra_headers": headers, + **prompt_params, + } + result: Final = await litellm.acompletion(**params) if async_call else litellm.completion(**params) + assert result.choices[0].message.content == "acct-client-a" + else: + response: Final = ( + await litellm.aresponses( + model="chatgpt/gpt-6.1-sol", input="Hello", extra_headers=headers, **prompt_params + ) + if async_call + else litellm.responses( + model="chatgpt/gpt-6.1-sol", input="Hello", extra_headers=headers, **prompt_params + ) + ) + assert response.output[0].content[0].text == "acct-client-a" + assert transport.calls.last.request.headers["Authorization"] == headers["Authorization"] + assert len(transport.calls) == 1