scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-10 08:28:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

test(routing): expect 503 server_is_overloaded for an upstream overload (#50155)

Browse source 
Co-authored-by: mateo <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-11-05 03:26:45 +00:00 • committed by GitHub
parent c5da69cd13
commit 71fc204495
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
tests/integration/routing/test_prompt_cache_pin_ttl.py
View file

@ -9,7 +9,7 @@ from typing import Final
import anthropic
import openai
import pytest
from integration._support.client import eventually, gateway_from_environment, held
from integration._support.client import eventually, gateway_from_environment, held, object_value
from integration._support.process import OwnedProxy, graceful_stop_seconds, owned_proxy_process
from integration._support.redis_process import owned_redis
from integration._support.wire import Wire, wire_server
@ -56,11 +56,12 @@ from integration.routing._prompt_cache_pin_support import (
vertex_peer,
wire_carries_one_hour,
)
from pydantic import JsonValue
from pydantic import JsonValue, TypeAdapter
from redis import Redis
pytestmark: Final = [pytest.mark.timeout(2 * graceful_stop_seconds() + 300), pytest.mark.shares_worker_state]
_JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue])
_CLAUDE: Final = "pin-claude"
_SLOW: Final = "pin-slow"
_MIXED: Final = "pin-mixed"
@ -539,7 +540,10 @@ def test_failed_first_turn_reports_the_error_and_writes_no_pin(rig: _Rig) -> Non
"/v1/chat/completions",
chat_body(_CLAUDE, _first_turn(new_marker(), f"{new_marker()} {OVERLOAD_TOKEN}", ONE_HOUR_MARK)),
)
assert response.status_code == 500, response.text
assert response.status_code == 503, response.text
error: Final = object_value(_JSON_OBJECT.validate_json(response.text)["error"])
assert error["type"] == "service_unavailable_error", response.text
assert error["code"] == "server_is_overloaded", response.text
assert "overloaded_error" in response.text, response.text
healthy, _ = post_chat(rig.owned.gateway, chat_body(_CLAUDE, _first_turn(new_marker(), new_marker(), None)))
spend_row_lands(healthy)