diff --git a/tests/e2e/llm_translation/test_messages_beta_headers_e2e.py b/tests/e2e/llm_translation/test_messages_beta_headers_e2e.py index 91a31201b0f..59035f8f6b6 100644 --- a/tests/e2e/llm_translation/test_messages_beta_headers_e2e.py +++ b/tests/e2e/llm_translation/test_messages_beta_headers_e2e.py @@ -15,48 +15,85 @@ pytestmark = pytest.mark.e2e _BETA_CONFIG: Final = files("litellm").joinpath("anthropic_beta_headers_config.json") _ANTHROPIC_MODEL: Final = "anthropic/claude-sonnet-5-5" +_VERTEX_MODEL: Final = "vertex_ai/claude-sonnet-5-5" +_VERTEX_LOCATION: Final = "global" +_AZURE_AI_MODEL: Final = "azure_ai/claude-fable-5-1" _BEDROCK_MODEL_ID: Final = "us.anthropic.claude-fable-5-1" _BETA_CONFIG_FILE: Final = TypeAdapter(dict[str, JsonValue]) _BETA_MAPPING: Final = TypeAdapter(dict[str, str | None]) _CODE_EXECUTION: Final[ToolUnionParam] = {"type": "code_execution_20250825", "name": "code_execution"} +# A live Vertex probe on 2026-10-31: each Claude 4.5 and 4.6 model takes one of these and Claude 5.5 takes neither +_VERTEX_PER_MODEL_BETAS: Final = frozenset({"computer-use-2025-01-24", "computer-use-2025-11-24"}) +_NO_PER_MODEL_BETAS: Final[frozenset[str]] = frozenset() -def _mapped_beta_headers(provider: str) -> str: - mapping: Final = _BETA_MAPPING.validate_python(_BETA_CONFIG_FILE.validate_json(_BETA_CONFIG.read_text())[provider]) - return ",".join(name for name, value in mapping.items() if value is not None) +def _mapped_beta_headers(provider: str, per_model: frozenset[str]) -> str: + config: Final = _BETA_CONFIG_FILE.validate_json(_BETA_CONFIG.read_text()) + mapping: Final = _BETA_MAPPING.validate_python(config[provider]) + header_only: Final = _BETA_MAPPING.validate_python(config.get(f"{provider}_header_only", {})) + forwarded: Final = {name for name, value in {**mapping, **header_only}.items() if value is not None} + assert per_model <= forwarded, per_model - forwarded + return ",".join(sorted(forwarded - per_model)) def _deployment(backend: str) -> LiteLLMParamsBody: - if backend.startswith("anthropic/"): - return LiteLLMParamsBody(model=backend, api_key="os.environ/ANTHROPIC_API_KEY") - return LiteLLMParamsBody( - model=backend, - aws_access_key_id="os.environ/AWS_ACCESS_KEY_ID", - aws_secret_access_key="os.environ/AWS_SECRET_ACCESS_KEY", - aws_region_name="us-east-1", - ) + match backend.split("/", 1)[0]: + case "anthropic": + return LiteLLMParamsBody(model=backend, api_key="os.environ/ANTHROPIC_API_KEY") + case "vertex_ai": + return LiteLLMParamsBody( + model=backend, + vertex_project="os.environ/VERTEXAI_PROJECT", + vertex_location=_VERTEX_LOCATION, + vertex_credentials="os.environ/VERTEXAI_CREDENTIALS", + ) + case "azure_ai": + return LiteLLMParamsBody( + model=backend, + api_base="os.environ/AZURE_AI_API_BASE", + api_key="os.environ/AZURE_AI_API_KEY", + ) + case _: + return LiteLLMParamsBody( + model=backend, + aws_access_key_id="os.environ/AWS_ACCESS_KEY_ID", + aws_secret_access_key="os.environ/AWS_SECRET_ACCESS_KEY", + aws_region_name="us-east-1", + ) class TestAnthropicBetaHeaders: @pytest.mark.parametrize( - ("backend", "beta_provider", "tools"), + ("backend", "beta_provider", "tools", "per_model"), [ - pytest.param(_ANTHROPIC_MODEL, "anthropic", [_CODE_EXECUTION], id="anthropic"), - pytest.param(f"bedrock/invoke/{_BEDROCK_MODEL_ID}", "bedrock", [], id="bedrock-invoke"), - pytest.param(f"bedrock/converse/{_BEDROCK_MODEL_ID}", "bedrock_converse", [], id="bedrock-converse"), + pytest.param(_ANTHROPIC_MODEL, "anthropic", [_CODE_EXECUTION], _NO_PER_MODEL_BETAS, id="anthropic"), + pytest.param(_VERTEX_MODEL, "vertex_ai", [], _VERTEX_PER_MODEL_BETAS, id="vertex-ai"), + pytest.param(_AZURE_AI_MODEL, "azure_ai", [], _NO_PER_MODEL_BETAS, id="azure-ai"), + pytest.param( + f"bedrock/invoke/{_BEDROCK_MODEL_ID}", "bedrock", [], _NO_PER_MODEL_BETAS, id="bedrock-invoke" + ), + pytest.param( + f"bedrock/converse/{_BEDROCK_MODEL_ID}", + "bedrock_converse", + [], + _NO_PER_MODEL_BETAS, + id="bedrock-converse", + ), ], ) @pytest.mark.covers( "llm.messages.anthropic.basic.nonstream.works", "llm.messages.bedrock_invoke.basic.nonstream.works", "llm.messages.bedrock_converse.basic.nonstream.works", + "llm.messages.vertex.basic.nonstream.works", + "llm.messages.azure_foundry.basic.nonstream.works", ) @meta( Subject( domain=Domain.LLM_TRANSLATION, route=Route.MESSAGES, - providers=(Provider.ANTHROPIC, Provider.BEDROCK), - models=(_ANTHROPIC_MODEL, _BEDROCK_MODEL_ID), + providers=(Provider.ANTHROPIC, Provider.BEDROCK, Provider.VERTEX_AI, Provider.AZURE_AI), + models=(_ANTHROPIC_MODEL, _BEDROCK_MODEL_ID, _VERTEX_MODEL, _AZURE_AI_MODEL), mode=Mode.NONSTREAM, ) ) @@ -68,6 +105,7 @@ class TestAnthropicBetaHeaders: backend: str, beta_provider: str, tools: list[ToolUnionParam], + per_model: frozenset[str], ) -> None: model: Final = f"e2e-messages-beta-{unique_marker()}" model_id: Final = proxy.create_model(model, _deployment(backend)) @@ -78,7 +116,7 @@ class TestAnthropicBetaHeaders: max_tokens=64, messages=[{"role": "user", "content": "Say 'hello' and nothing else"}], tools=tools, - extra_headers={"anthropic-beta": _mapped_beta_headers(beta_provider)}, + extra_headers={"anthropic-beta": _mapped_beta_headers(beta_provider, per_model)}, extra_body=NO_PROXY_CACHE, )