[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

Signed-off-by: Zach Zhu <zzqshu@126.com>
This commit is contained in:
Zach Zhu
2026-07-29 04:20:40 +00:00
committed by GitHub
parent f37f03db4a
commit 58f9659397
46 changed files with 370 additions and 248 deletions
@@ -14,6 +14,7 @@ from vllm.entrypoints.openai.responses.protocol import (
ResponsesRequest,
ResponseTextConfig,
)
from vllm.exceptions import VLLMValidationError
from vllm.sampling_params import StructuredOutputsParams
@@ -163,7 +164,7 @@ class TestResponsesRequestSamplingParams:
text=text_config,
)
with pytest.raises(ValueError) as exc_info:
with pytest.raises(VLLMValidationError) as exc_info:
request.to_sampling_params(default_max_tokens=1000)
assert "Cannot specify both structured_outputs and text.format" in str(