diff --git a/tests/entrypoints/openai/test_openai_schema.py b/tests/entrypoints/openai/test_openai_schema.py index 64fdaf0889..8900c4746f 100644 --- a/tests/entrypoints/openai/test_openai_schema.py +++ b/tests/entrypoints/openai/test_openai_schema.py @@ -90,7 +90,10 @@ def before_generate_case(context: schemathesis.hooks.HookContext, strategy): if ( isinstance(content, list) and len(content) > 0 - and any(item.get("type") == "file" for item in content) + and any( + isinstance(item, dict) and item.get("type") == "file" + for item in content + ) ): return False @@ -139,6 +142,7 @@ def test_openapi_stateless(case: schemathesis.Case): timeout = { # requires a longer timeout ("POST", "/v1/chat/completions"): LONG_TIMEOUT_SECONDS, + ("POST", "/v1/completions"): LONG_TIMEOUT_SECONDS, }.get(key, DEFAULT_TIMEOUT_SECONDS) # No need to verify SSL certificate for localhost diff --git a/vllm/entrypoints/openai/protocol.py b/vllm/entrypoints/openai/protocol.py index f6f725cf0e..845dae7c1b 100644 --- a/vllm/entrypoints/openai/protocol.py +++ b/vllm/entrypoints/openai/protocol.py @@ -577,7 +577,9 @@ class ChatCompletionRequest(OpenAIBaseModel): min_tokens: int = 0 skip_special_tokens: bool = True spaces_between_special_tokens: bool = True - truncate_prompt_tokens: Annotated[int, Field(ge=-1)] | None = None + truncate_prompt_tokens: Annotated[int, Field(ge=-1, le=_LONG_INFO.max)] | None = ( + None + ) prompt_logprobs: int | None = None allowed_token_ids: list[int] | None = None bad_words: list[str] = Field(default_factory=list) @@ -1058,7 +1060,9 @@ class CompletionRequest(OpenAIBaseModel): min_tokens: int = 0 skip_special_tokens: bool = True spaces_between_special_tokens: bool = True - truncate_prompt_tokens: Annotated[int, Field(ge=-1)] | None = None + truncate_prompt_tokens: Annotated[int, Field(ge=-1, le=_LONG_INFO.max)] | None = ( + None + ) allowed_token_ids: list[int] | None = None prompt_logprobs: int | None = None # --8<-- [end:completion-sampling-params]