[BugFix] Add field validators for /v1/audio/generate request (#4741)

Signed-off-by: Shaun Walsh <shaunwalsh24@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Nick Cao <ncao@redhat.com>

tests/dfx/reliability/invalid_param_test/test_invalid_audio_diffusion.py

@@ -13,9 +13,6 @@ from tests.helpers.runtime import OmniServer, OmniServerParams, OnlineOmniClient
 
 pytestmark = [pytest.mark.slow, pytest.mark.diffusion]
 
-# https://github.com/vllm-project/vllm-omni/issues/3649 — invalid inputs still HTTP 200 / timeout / missing validation.
-_SKIP_ISSUE_3649 = pytest.mark.skip(reason="https://github.com/vllm-project/vllm-omni/issues/3649")
-
 _PARAMS = [
     pytest.param(
         OmniServerParams(
@@ -36,10 +33,8 @@ _PARAMS = [
 @pytest.mark.parametrize(
     "overrides, err_message",
     [
-        pytest.param({"input": ""}, ("cannot be empty", "input"), id="input_empty", marks=_SKIP_ISSUE_3649),
-        pytest.param(
-            {"input": "   "}, ("cannot be empty", "input"), id="input_whitespace_only", marks=_SKIP_ISSUE_3649
-        ),
+        pytest.param({"input": ""}, ("cannot be empty", "input"), id="input_empty"),
+        pytest.param({"input": "   "}, ("cannot be empty", "input"), id="input_whitespace_only"),
         pytest.param({"input": 123}, ("input", "a valid string"), id="input_wrong_type"),
         pytest.param(
             {"response_format": "mpeg"},
@@ -54,10 +49,8 @@ _PARAMS = [
             ("sse", "stream_format", "value_error", "not a supported stream_format"),
             id="stream_format_sse_blocked",
         ),
-        pytest.param(
-            {"audio_length": -1.0}, ("audio_end_in_s", "higher than", "audio_start_in_s"), id="audio_length_negative"
-        ),
-        pytest.param({"audio_length": 0}, "audio_length", id="audio_length_zero", marks=_SKIP_ISSUE_3649),
+        pytest.param({"audio_length": -1.0}, ("audio_length", "greater_than", "0"), id="audio_length_negative"),
+        pytest.param({"audio_length": 0}, ("audio_length", "greater_than", "0"), id="audio_length_zero"),
         # ``OmniOpenAIServingAudioGenerate`` only forwards ``audio_start`` when ``audio_length`` is set.
         pytest.param(
             {"audio_start": -0.5, "audio_length": 5.0},
@@ -67,26 +60,30 @@ _PARAMS = [
         pytest.param(
             {"negative_prompt": ["noise"]}, ("negative_prompt", "a valid string"), id="negative_prompt_wrong_type"
         ),
-        pytest.param({"guidance_scale": -1.0}, "guidance_scale", id="guidance_scale_negative", marks=_SKIP_ISSUE_3649),
-        pytest.param({"guidance_scale": 0}, "guidance_scale", id="guidance_scale_zero", marks=_SKIP_ISSUE_3649),
+        pytest.param(
+            {"guidance_scale": -1.0},
+            ("guidance_scale", "greater_than_equal", "0"),
+            id="guidance_scale_negative",
+        ),
         pytest.param(
             {"num_inference_steps": 0},
-            ("num_inference_steps", "greater than or equal to 1"),
+            ("num_inference_steps", "greater_than_equal", "1"),
             id="num_inference_steps_zero",
         ),
         pytest.param(
             {"num_inference_steps": -1},
-            ("num_inference_steps", "greater than or equal to 1"),
+            ("num_inference_steps", "greater_than_equal", "1"),
             id="num_inference_steps_negative",
         ),
         pytest.param(
             {"num_inference_steps": 6000},
-            "num_inference_steps",
+            ("num_inference_steps", "less_than_equal", "1000"),
             id="num_inference_steps_above_max",
-            marks=_SKIP_ISSUE_3649,
         ),
         pytest.param(
-            {"guidance_scale": 1001.0}, "guidance_scale", id="guidance_scale_above_max", marks=_SKIP_ISSUE_3649
+            {"guidance_scale": 1001.0},
+            ("guidance_scale", "less_than_equal", "1000"),
+            id="guidance_scale_above_max",
         ),
         pytest.param(
             {"audio_length": 86401.0}, ("Requested audio length", "exceeds maximum"), id="audio_length_above_max"

vllm_omni/entrypoints/openai/protocol/audio.py

@@ -353,6 +353,14 @@ class OpenAICreateAudioGenerateRequest(BaseModel):
     input: str = Field(
         description="Text prompt describing the audio to generate",
     )
+
+    @field_validator("input")
+    @classmethod
+    def validate_input(cls, v):
+        if not v or not v.strip():
+            raise ValueError("input cannot be empty")
+        return v
+
     model: str | None = None
     response_format: Literal["wav", "pcm", "flac", "mp3", "opus"] = DEFAULT_AUDIO_FORMAT
     speed: float | None = Field(
@@ -363,6 +371,7 @@ class OpenAICreateAudioGenerateRequest(BaseModel):
     stream_format: Literal["sse", "audio"] | None = "audio"
     audio_length: float | None = Field(
         default=None,
+        gt=0,
         description="Audio length in seconds",
     )
     audio_start: float | None = Field(
@@ -375,12 +384,14 @@ class OpenAICreateAudioGenerateRequest(BaseModel):
     )
     guidance_scale: float | None = Field(
         default=None,
+        ge=0,
+        le=1000,
         description="Guidance scale for diffusion models",
     )
     num_inference_steps: int | None = Field(
         default=None,
         ge=1,
-        le=_INT64_MAX,
+        le=1000,
         description="Number of inference steps",
     )
     seed: int | None = Field(