scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-13 23:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 152

fix(e2e): give the deepseek reasoner test a per-call timeout so provider thinking latency does not hit the 60s transport default

Browse source
This commit is contained in:
mateo-berri 2026-08-07 23:32:48 -07:00
parent d0758a291c
commit 910ac037ad
3 changed files with 29 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
tests/e2e/llm_translation/test_deepseek_reasoning_e2e.py
View file

@ -29,6 +29,7 @@ pytestmark = pytest.mark.e2e
REASONER = "deepseek/deepseek-v4-pro"
PROMPT = "What is 17 + 26? Answer with just the number."
REASONER_TIMEOUT_SECONDS = 240.0
def _register_reasoner(client: PassthroughClient, resources: ResourceManager) -> str:
@ -63,6 +64,7 @@ class TestDeepSeekReasoningDisable:
messages=[ChatMessage(role="user", content=PROMPT)],
max_tokens=64,
),
timeout=REASONER_TIMEOUT_SECONDS,
)
)
reasoning = _reasoning_content(response)
@ -86,6 +88,7 @@ class TestDeepSeekReasoningDisable:
max_tokens=64,
reasoning_effort="none",
),
timeout=REASONER_TIMEOUT_SECONDS,
)
)
assert not _reasoning_content(response), (
@ -108,6 +111,7 @@ class TestDeepSeekReasoningDisable:
max_tokens=64,
thinking=ThinkingParam(type="disabled"),
),
timeout=REASONER_TIMEOUT_SECONDS,
)
)
assert not _reasoning_content(response), (

3
tests/e2e/proxy_client.py
View file

@ -269,12 +269,13 @@ class ProxyClient:
# ---- LLM calls ------------------------------------------------------
def chat(self, key: str, body: ChatBody) -> Result[ChatResponse]:
def chat(self, key: str, body: ChatBody, timeout: float | None = None) -> Result[ChatResponse]:
return self.transport.post(
"/chat/completions",
headers=self.transport.bearer(key),
json=body,
response_type=ChatResponse,
timeout=timeout,
)
def chat_stream(self, key: str, body: ChatBody) -> StreamingResponse:

28
tests/e2e/transport.py
View file

@ -25,7 +25,13 @@ from e2e_http import (
class Transport(Protocol):
def post[R: BaseModel](
self, path: str, *, headers: BaseModel, json: BaseModel, response_type: type[R]
self,
path: str,
*,
headers: BaseModel,
json: BaseModel,
response_type: type[R],
timeout: float | None = None,
) -> Result[R]: ...
def stream(
@ -119,14 +125,20 @@ class HttpTransport:
return self.bearer(self.master_key)
def post[R: BaseModel](
self, path: str, *, headers: BaseModel, json: BaseModel, response_type: type[R]
self,
path: str,
*,
headers: BaseModel,
json: BaseModel,
response_type: type[R],
timeout: float | None = None,
) -> Result[R]:
return e2e_http.post(
self._url(path),
headers=headers,
json=json,
response_type=response_type,
timeout=self.request_timeout,
timeout=timeout if timeout is not None else self.request_timeout,
)
def get[R: BaseModel](
@ -323,10 +335,16 @@ class SplitTransport:
return self.data.master
def post[R: BaseModel](
self, path: str, *, headers: BaseModel, json: BaseModel, response_type: type[R]
self,
path: str,
*,
headers: BaseModel,
json: BaseModel,
response_type: type[R],
timeout: float | None = None,
) -> Result[R]:
return self._route(path).post(
path, headers=headers, json=json, response_type=response_type
path, headers=headers, json=json, response_type=response_type, timeout=timeout
)
def get[R: BaseModel](