[Frontend] Add cache salt and tracing to structured decisions (#60786)

Signed-off-by: Taewoong Kim <ktw2172@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
This commit is contained in:
Taewoong Kim
2026-10-09 08:53:50 +00:00
committed by GitHub
co-authored by Chauncey
parent a6f43e57d6
commit 18c19eaf23
7 changed files with 207 additions and 10 deletions
@@ -13,6 +13,9 @@ request models whose before-validators were missing the same guard.
import pytest
from pydantic import ValidationError
from vllm.entrypoints.generate.structured_decisions.protocol import (
StructuredDecisionRequest,
)
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
@@ -74,6 +77,18 @@ def test_tokenize_chat_request_still_validates_dict_bodies():
CACHE_SALT_MODELS = [
(
StructuredDecisionRequest,
{
"state": "hello",
"questions": {
"lang": {
"type": "choice",
"criteria": {"English": "Text written in English."},
}
},
},
),
(CompletionRequest, {"prompt": "hello"}),
(ChatCompletionRequest, {"messages": [{"role": "user", "content": "hello"}]}),
(ResponsesRequest, {"input": "hello"}),