vllm-omni/tests/entrypoints/test_realtime_connection_helpers.py

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""Unit tests for AsyncOmni input streaming parameter validation."""

from __future__ import annotations

import pytest
from vllm.sampling_params import RequestOutputKind, SamplingParams

from vllm_omni.entrypoints.async_omni import AsyncOmni

pytestmark = [pytest.mark.core_model, pytest.mark.cpu]


class TestAsyncOmniStreamingParamsValidation:
    def test_accepts_streaming_friendly_params(self) -> None:
        p = SamplingParams(
            n=1,
            stop=[],
            output_kind=RequestOutputKind.DELTA,
        )
        AsyncOmni._validate_streaming_input_sampling_params(p)

    def test_rejects_non_sampling_params(self) -> None:
        with pytest.raises(ValueError, match="Input streaming"):
            AsyncOmni._validate_streaming_input_sampling_params(object())  # type: ignore[arg-type]

    def test_rejects_n_greater_than_one(self) -> None:
        p = SamplingParams(n=2, stop=[], output_kind=RequestOutputKind.DELTA)
        with pytest.raises(ValueError, match="Input streaming"):
            AsyncOmni._validate_streaming_input_sampling_params(p)

    def test_rejects_final_only(self) -> None:
        p = SamplingParams(n=1, stop=[], output_kind=RequestOutputKind.FINAL_ONLY)
        with pytest.raises(ValueError, match="Input streaming"):
            AsyncOmni._validate_streaming_input_sampling_params(p)

    def test_rejects_stop_strings(self) -> None:
        p = SamplingParams(n=1, stop=["\n"], output_kind=RequestOutputKind.DELTA)
        with pytest.raises(ValueError, match="Input streaming"):
            AsyncOmni._validate_streaming_input_sampling_params(p)