From a276690ce200bebe3547c110ac9a830b32052173 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Fri, 4 Sep 2026 23:32:26 -0700 Subject: [PATCH] fix(router): keep a model's own provider prefix for generic SDK calls Generic passthrough calls inferred the provider from the bare model name, so an azure_ai/gpt-* deployment on an Azure OpenAI host flipped to azure and get_llm_provider re-prefixed the deployment name into azure_ai/gpt-5.4-mini, a 404 DeploymentNotFound. provider_for_generic_call takes the declared custom_llm_provider first, then the model's own prefix, and only infers for unprefixed models --- litellm/router.py | 24 ++--------- litellm/router_utils/common_utils.py | 27 ++++++++++++ .../test_router_utils_common_utils.py | 18 ++++++++ tests/test_litellm/test_router.py | 43 +++++++++++++++++++ 4 files changed, 91 insertions(+), 21 deletions(-) diff --git a/litellm/router.py b/litellm/router.py index b84f790287f..9b7a7ee7ce8 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -135,6 +135,7 @@ from litellm.router_utils.common_utils import ( _is_proxy_admin_request, filter_team_based_models, filter_web_search_deployments, + provider_for_generic_call, resolve_model_group_alias, truncate_fallback_error_detail, warn_on_provider_credential_mismatch, @@ -5045,17 +5046,7 @@ class Router: kwargs=kwargs, model=model, model_name=model_name ) - # Get custom_llm_provider from deployment params - try: - custom_llm_provider = data.get("custom_llm_provider") - _, inferred_custom_llm_provider, _, _ = get_llm_provider( - model=data["model"], - custom_llm_provider=custom_llm_provider, - api_base=data.get("api_base"), - ) - custom_llm_provider = custom_llm_provider or inferred_custom_llm_provider - except Exception: - custom_llm_provider = None + custom_llm_provider: Final = provider_for_generic_call(data) response_kwargs: Final = { **data, @@ -5566,16 +5557,7 @@ class Router: # Perform pre-call checks for routing strategy self.routing_strategy_pre_call_checks(deployment=deployment) - try: - custom_llm_provider = data.get("custom_llm_provider") - _, inferred_custom_llm_provider, _, _ = get_llm_provider( - model=data["model"], - custom_llm_provider=custom_llm_provider, - api_base=data.get("api_base"), - ) - custom_llm_provider = custom_llm_provider or inferred_custom_llm_provider - except Exception: - custom_llm_provider = None + custom_llm_provider: Final = provider_for_generic_call(data) response: Final = original_function( **{ diff --git a/litellm/router_utils/common_utils.py b/litellm/router_utils/common_utils.py index 280a7defcf8..ec3ffa1247e 100644 --- a/litellm/router_utils/common_utils.py +++ b/litellm/router_utils/common_utils.py @@ -7,6 +7,7 @@ from typing import TYPE_CHECKING, Final if TYPE_CHECKING: from litellm.types.llms.openai import OpenAIFileObject +import litellm from litellm._logging import verbose_logger, verbose_router_logger from litellm.constants import ROUTER_FALLBACK_ERROR_DETAIL_MAX_CHARS from litellm.exceptions import BadRequestError @@ -244,6 +245,32 @@ PROVIDER_SCOPED_CREDENTIAL_PARAMS: Final[Mapping[str, frozenset[str]]] = Mapping ) +def provider_for_generic_call(litellm_params: Mapping[str, object]) -> str | None: + """ + The provider the router hands a deployment's generic SDK call, or None when it cannot be resolved. + + A model that carries its own provider prefix keeps that prefix even where get_llm_provider + would resolve it to a sibling provider (azure_ai/ on an Azure OpenAI host + resolves to azure): the SDK call still receives the prefixed model, and an explicit provider + that contradicts the prefix makes get_llm_provider re-prefix it into a deployment name that + does not exist upstream. + """ + declared: Final = litellm_params.get("custom_llm_provider") + if isinstance(declared, str) and declared: + return declared + model: Final = litellm_params.get("model") + if not isinstance(model, str) or not model: + return None + prefix: Final = model.split("/", 1)[0] + if "/" in model and prefix in litellm.provider_list: + return prefix + try: + _, inferred, _, _ = get_llm_provider(model=model) + except BadRequestError: + return None + return inferred + + def warn_on_provider_credential_mismatch(model_name: str, litellm_params: Mapping[str, object]) -> str | None: """ Warn when a deployment carries one provider's credentials but resolves to another. diff --git a/tests/test_litellm/router_utils/test_router_utils_common_utils.py b/tests/test_litellm/router_utils/test_router_utils_common_utils.py index 30f658d7ea2..ac18b4889dd 100644 --- a/tests/test_litellm/router_utils/test_router_utils_common_utils.py +++ b/tests/test_litellm/router_utils/test_router_utils_common_utils.py @@ -12,6 +12,7 @@ from litellm.router_utils.common_utils import ( add_model_file_id_mappings, filter_team_based_models, filter_web_search_deployments, + provider_for_generic_call, resolve_model_group_alias, truncate_fallback_error_detail, PROVIDER_SCOPED_CREDENTIAL_PARAMS, @@ -756,3 +757,20 @@ class TestWarnOnProviderCredentialMismatch: ) is None ) + + +@pytest.mark.parametrize( + ("litellm_params", "expected"), + [ + ({"model": "azure_ai/gpt-5.4-mini", "custom_llm_provider": "azure"}, "azure"), + ({"model": "azure_ai/gpt-5.4-mini", "api_base": "https://my-resource.openai.azure.com"}, "azure_ai"), + ({"model": "cohere/command-r"}, "cohere"), + ({"model": "gpt-5.4-mini"}, "openai"), + ({"model": "no-provider-knows-this-model"}, None), + ({"api_base": "https://my-resource.openai.azure.com"}, None), + ], + ids=["declared_wins", "prefix_beats_host_flip", "prefix_beats_cohere_chat_flip", "unprefixed_inferred", "unknown", "no_model"], +) +def test_provider_for_generic_call(litellm_params, expected, monkeypatch): + monkeypatch.setenv("AZURE_AI_API_BASE", "https://unrelated.openai.azure.com") + assert provider_for_generic_call(litellm_params) == expected diff --git a/tests/test_litellm/test_router.py b/tests/test_litellm/test_router.py index 31eb46f1458..b220b23c338 100644 --- a/tests/test_litellm/test_router.py +++ b/tests/test_litellm/test_router.py @@ -12938,3 +12938,46 @@ async def test_router_retry_policy_controls_upstream_attempt_count( await router.acompletion(model="gpt-5.6", messages=[{"role": "user", "content": "hi"}]) assert upstream.call_count == expected_upstream_calls + + +@pytest.mark.asyncio +async def test_generic_call_keeps_the_deployment_name_of_an_azure_ai_model_on_an_azure_openai_host(monkeypatch): + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + router = litellm.Router( + model_list=[ + { + "model_name": "aoai-gpt", + "litellm_params": { + "model": "azure_ai/gpt-5.4-mini", + "api_base": "https://my-resource.openai.azure.com", + "api_key": "deployment-key", + }, + } + ] + ) + + with respx.mock(assert_all_called=True) as respx_mock: + upstream = respx_mock.post(host="my-resource.openai.azure.com", path__regex=r"^/openai/.*responses$").mock( + return_value=httpx.Response( + 200, + json={ + "id": "resp_1", + "object": "response", + "created_at": 1, + "status": "completed", + "model": "gpt-5.4-mini", + "output": [ + { + "type": "message", + "id": "msg_1", + "role": "assistant", + "status": "completed", + "content": [{"type": "output_text", "text": "hi", "annotations": []}], + } + ], + }, + ) + ) + await router.aresponses(model="aoai-gpt", input="hi") + + assert json.loads(upstream.calls.last.request.content)["model"] == "gpt-5.4-mini"