diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py index 005e94ebe82..74a1d3e5008 100644 --- a/litellm/litellm_core_utils/get_llm_provider_logic.py +++ b/litellm/litellm_core_utils/get_llm_provider_logic.py @@ -2,7 +2,7 @@ from typing import Final, cast from urllib.parse import urlparse import litellm -from litellm.constants import REPLICATE_MODEL_NAME_WITH_ID_LENGTH +from litellm.constants import PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO, REPLICATE_MODEL_NAME_WITH_ID_LENGTH from litellm.litellm_core_utils.fallback_generalizations import ( match_routing_generalization, ) @@ -127,6 +127,18 @@ def handle_anthropic_text_model_custom_llm_provider( return model, custom_llm_provider +def declared_authenticating_provider(model: str, custom_llm_provider: str | None = None) -> str | None: + """The authenticating provider this pair already names, or None. + + get_llm_provider runs the OAuth device flow for github_copilot and chatgpt, because their + provider info includes the key it unlocks. For a metadata question that flow is pure hazard, + and for a declared pair the resolver's answer is the declaration itself, so metadata callers + adopt the declaration instead of resolving. + """ + declared: Final = custom_llm_provider or model.split("/", 1)[0] + return declared if declared in PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO else None + + def get_llm_provider( model: str, custom_llm_provider: str | None = None, diff --git a/litellm/litellm_core_utils/get_supported_openai_params.py b/litellm/litellm_core_utils/get_supported_openai_params.py index 7a16ffe4d85..915a03025d9 100644 --- a/litellm/litellm_core_utils/get_supported_openai_params.py +++ b/litellm/litellm_core_utils/get_supported_openai_params.py @@ -2,6 +2,7 @@ from typing import Final, Literal import litellm from litellm.exceptions import BadRequestError +from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider from litellm.types.utils import LlmProviders, LlmProvidersSet @@ -30,6 +31,10 @@ def get_supported_openai_params( - List if custom_llm_provider is mapped - None if unmapped """ + if not custom_llm_provider: + custom_llm_provider = declared_authenticating_provider( + model + ) # rebind-ok: resolving would run the provider's OAuth flow if not custom_llm_provider: try: custom_llm_provider = litellm.get_llm_provider(model=model)[1] diff --git a/litellm/router.py b/litellm/router.py index 6d0d2bf74dd..72f53420c57 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -50,7 +50,6 @@ from litellm.constants import ( DEFAULT_HEALTH_CHECK_INTERVAL, DEFAULT_HEALTH_CHECK_STALENESS_MULTIPLIER, DEFAULT_MAX_LRU_CACHE_SIZE, - PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO, SESSION_DEPLOYMENT_AFFINITY_TTL_METADATA_KEY, ) from litellm.integrations.custom_logger import CustomLogger @@ -65,6 +64,7 @@ from litellm.litellm_core_utils.core_helpers import ( from litellm.litellm_core_utils.coroutine_checker import coroutine_checker from litellm.litellm_core_utils.credential_accessor import CredentialAccessor from litellm.litellm_core_utils.dd_tracing import tracer +from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging from litellm.litellm_core_utils.ptu_pricing import ( PTU_COST_ATTRIBUTION_ENV_VAR, @@ -10861,10 +10861,9 @@ class Router: return True if param in Router._declared_param_allowlist(deployment_params): return True - declared_provider: Final = ( - deployment_params.get("custom_llm_provider") or str(deployment_params.get("model") or "").split("/", 1)[0] - ) - if declared_provider in PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO: + if declared_authenticating_provider( + str(deployment_params.get("model") or ""), deployment_params.get("custom_llm_provider") + ): return True deployment_model_info: Final = deployment.get("model_info") base_model: Final = ( diff --git a/litellm/router_strategy/savings_baseline.py b/litellm/router_strategy/savings_baseline.py index e10ec4a1e6f..ea22eccc918 100644 --- a/litellm/router_strategy/savings_baseline.py +++ b/litellm/router_strategy/savings_baseline.py @@ -54,9 +54,17 @@ def canonical_model(model: str, custom_llm_provider: str | None = None) -> str | A deployment may name its vendor in the model prefix or in a separate ``custom_llm_provider``, and the bare name alone is not enough to price: it can resolve to a different vendor's rates, or to nothing at all. + + A github_copilot or chatgpt candidate is qualified by string alone: resolving either + provider runs its OAuth device flow, and for a declared pair the resolver's answer is + the declaration itself, so asking it buys nothing but the block. """ import litellm + from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider + declared: Final = declared_authenticating_provider(model, custom_llm_provider) + if declared is not None: + return f"{declared}/{model.removeprefix(f'{declared}/')}" try: resolved, provider, _, _ = litellm.get_llm_provider(model=model, custom_llm_provider=custom_llm_provider) except Exception as e: # noqa: BLE001 # an unroutable candidate cannot be the baseline diff --git a/litellm/utils.py b/litellm/utils.py index 46e23b900fd..9bfc4051892 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -2556,10 +2556,19 @@ def _supports_factory(model: str, custom_llm_provider: str | None, key: str) -> Raises: Exception: If the given model is not found or there's an error in retrieval. """ + from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider + try: - model, custom_llm_provider, _, _ = litellm.get_llm_provider( - model=model, custom_llm_provider=custom_llm_provider - ) + declared: Final = declared_authenticating_provider(model, custom_llm_provider) + if declared is not None: + model = model.removeprefix( + f"{declared}/" + ) # rebind-ok: mirrors get_llm_provider's split without its OAuth flow + custom_llm_provider = declared # rebind-ok: same + else: + model, custom_llm_provider, _, _ = litellm.get_llm_provider( + model=model, custom_llm_provider=custom_llm_provider + ) model_info: Final = _get_model_info_helper(model=model, custom_llm_provider=custom_llm_provider) @@ -5550,6 +5559,8 @@ def _get_model_info_helper( """ Helper for 'get_model_info'. Separated out to avoid infinite loop caused by returning 'supported_openai_param's """ + from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider + try: azure_llms: Final = {**litellm.azure_llms, **litellm.azure_embedding_models} if model in azure_llms: @@ -5564,7 +5575,9 @@ def _get_model_info_helper( ): model = model + "@latest" ########################## - potential_model_names: Final = _get_potential_model_names(model=model, custom_llm_provider=custom_llm_provider) + potential_model_names: Final = _get_potential_model_names( + model=model, custom_llm_provider=custom_llm_provider or declared_authenticating_provider(model) + ) verbose_logger.debug("checking potential_model_names in litellm.model_cost: %s", potential_model_names) diff --git a/tests/test_litellm/litellm_core_utils/test_get_supported_openai_params.py b/tests/test_litellm/litellm_core_utils/test_get_supported_openai_params.py index 2285cc83cad..cb4e72ab3ad 100644 --- a/tests/test_litellm/litellm_core_utils/test_get_supported_openai_params.py +++ b/tests/test_litellm/litellm_core_utils/test_get_supported_openai_params.py @@ -173,3 +173,41 @@ def test_bedrock_converse_alias_keeps_nova_web_search_options(): assert nova_params is not None assert "web_search_options" in nova_params + + +class TestDeclaredAuthenticatingProvider: + """github_copilot and chatgpt run an OAuth device flow inside get_llm_provider, so every + metadata funnel must adopt a declared prefix instead of resolving it. A raising sentinel + cannot prove the lookup was skipped, because these callers swallow resolver errors.""" + + @pytest.mark.parametrize( + "model, provider, expected", + [ + ("github_copilot/gpt-4o", None, "github_copilot"), + ("chatgpt/gpt-5", None, "chatgpt"), + ("gpt-4o", "github_copilot", "github_copilot"), + ("openai/gpt-4o", None, None), + ("gpt-4o", "openai", None), + ], + ) + def test_names_only_the_providers_whose_resolution_authenticates(self, model, provider, expected): + from litellm.litellm_core_utils.get_llm_provider_logic import declared_authenticating_provider + + assert declared_authenticating_provider(model, provider) == expected + + @pytest.mark.parametrize("model", ["github_copilot/gpt-4o", "chatgpt/gpt-5"]) + def test_supported_params_never_resolve_an_authenticating_prefix(self, model, monkeypatch): + import litellm + + lookups: list = [] + + def _record(*args, **kwargs): + lookups.append((args, kwargs)) + raise RuntimeError("provider resolution must not run for an authenticating provider") + + monkeypatch.setattr(litellm, "get_llm_provider", _record) + + params = get_supported_openai_params(model=model) + + assert params is not None + assert lookups == [] diff --git a/tests/test_litellm/router_strategy/test_complexity_router.py b/tests/test_litellm/router_strategy/test_complexity_router.py index 6f76be18256..99192346861 100644 --- a/tests/test_litellm/router_strategy/test_complexity_router.py +++ b/tests/test_litellm/router_strategy/test_complexity_router.py @@ -2234,6 +2234,63 @@ class TestRouterPreRoutingAliasOverrides: assert deployment["model_name"] == "gpt-5-mini" assert request_kwargs["reasoning_effort"] == "xhigh" + @pytest.mark.asyncio + async def test_routing_never_resolves_an_authenticating_provider(self, monkeypatch, tmp_path): + """Resolving github_copilot runs its OAuth device flow, so the whole routing path must + answer without it: the tier-param filter fails open, the savings baseline qualifies by + string, and model info adopts the declared prefix. The recording wrapper raises for a + copilot-directed resolution rather than calling through, so a regression fails on the + recorded call instead of hanging the suite in a device-code poll.""" + import json + import time + + monkeypatch.setenv("GITHUB_COPILOT_TOKEN_DIR", str(tmp_path)) + (tmp_path / "api-key.json").write_text( + json.dumps({"token": "tid=test", "expires_at": int(time.time()) + 3600}) + ) + router = Router( + model_list=[ + { + "model_name": "smart-router", + "litellm_params": { + "model": "auto_router/complexity_router", + "complexity_router_config": { + "tiers": { + "SIMPLE": { + "model_name": "cop-mixed", + "litellm_params": {"reasoning_effort": "high"}, + } + } + }, + }, + }, + {"model_name": "cop-mixed", "litellm_params": {"model": "openai/gpt-4o-mini", "api_key": "sk-x"}}, + {"model_name": "cop-mixed", "litellm_params": {"model": "github_copilot/gpt-4o"}}, + ] + ) + real_get_llm_provider = litellm.get_llm_provider + copilot_resolutions: List = [] + + def _guarded(*args, **kwargs): + target = str(kwargs.get("model") or (args[0] if args else "")) + str(kwargs.get("custom_llm_provider") or "") + if "github_copilot" in target: + copilot_resolutions.append(target) + raise RuntimeError("routing must not resolve an authenticating provider") + return real_get_llm_provider(*args, **kwargs) + + monkeypatch.setattr(litellm, "get_llm_provider", _guarded) + request_kwargs: Dict = {} + + deployment = await router.async_get_available_deployment( + model="smart-router", + request_kwargs=request_kwargs, + messages=[{"role": "user", "content": "hi"}], + ) + + assert deployment["model_name"] == "cop-mixed" + assert request_kwargs["reasoning_effort"] == "high" + assert copilot_resolutions == [] + @pytest.mark.asyncio async def test_alias_custom_pricing_is_not_applied_to_request_kwargs(self): """Custom pricing on the alias prices the alias, not the tier deployment diff --git a/tests/test_litellm/router_strategy/test_savings_baseline.py b/tests/test_litellm/router_strategy/test_savings_baseline.py index 0766083aed5..5efc73d2dcb 100644 --- a/tests/test_litellm/router_strategy/test_savings_baseline.py +++ b/tests/test_litellm/router_strategy/test_savings_baseline.py @@ -35,6 +35,31 @@ class TestCanonicalModel: def test_returns_none_for_a_name_no_provider_claims(self): assert canonical_model("") is None + @pytest.mark.parametrize( + "model, provider, expected", + [ + ("github_copilot/gpt-4o", None, "github_copilot/gpt-4o"), + ("chatgpt/gpt-5", None, "chatgpt/gpt-5"), + ("gpt-4o", "github_copilot", "github_copilot/gpt-4o"), + ], + ) + def test_never_resolves_a_provider_whose_lookup_authenticates(self, model, provider, expected, monkeypatch): + """Resolving github_copilot or chatgpt runs their OAuth device flow, so the baseline must + qualify these by string alone. A raising sentinel cannot prove the lookup was skipped, + because canonical_model swallows resolver errors into None.""" + import litellm + + lookups: list = [] + + def _record(*args, **kwargs): + lookups.append((args, kwargs)) + raise RuntimeError("provider resolution must not run for an authenticating provider") + + monkeypatch.setattr(litellm, "get_llm_provider", _record) + + assert canonical_model(model, provider) == expected + assert lookups == [] + class TestModelsForGroup: def test_resolves_a_group_to_the_models_its_deployments_call(self, parent):