scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

test(integration): accept the 422 budget refusal and a respawned worker's resume

Browse source 
The budget cell pinned a 400 that the proxy stopped answering when budget refusals moved to 422, so it now asserts the status and the budget_exceeded error type the sibling budget tests pin. The later-booting replica cell accepts a claimer that is any worker started after the creates, since uvicorn's supervisor can respawn the creator's worker under load and the respawned worker's boot resume claims the rows by design; the single spend row check is unchanged
This commit is contained in:
mateo-berri 2026-10-02 19:59:31 -07:00
parent 6afd57f9de
commit 57f2ede03f
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
tests/integration/spend/test_background_interaction_settlement.py
View file

@ -1,5 +1,6 @@
import math
import socket
import time
import uuid
from collections.abc import Iterator, Mapping, Sequence
from concurrent.futures import ThreadPoolExecutor
@ -348,6 +349,13 @@ def _claimer_pid(row: Mapping[str, JsonValue]) -> int:
return int(pid)
def _booted_after(pid: int, moment: float) -> bool:
try:
return psutil.Process(pid).create_time() > moment
except psutil.NoSuchProcess:
return False
def _worker_pids(root_pid: int) -> frozenset[int]:
return frozenset(
process.pid for process in group_members(root_pid) if process.pid != root_pid and _is_spawned_worker(process)
@ -438,6 +446,7 @@ def test_a_replica_booting_later_resumes_and_bills_unclaimed_interactions(rig: R
with rig.creator.scenario() as scenario:
model: Final = rig.models.in_progress
key: Final = scenario.key()
created_after: Final = time.time()
created: Final = tuple(_create(rig.creator, model, key) for _ in range(3))
for item in created:
_state(rig, item, _completed())
@ -449,7 +458,8 @@ def test_a_replica_booting_later_resumes_and_bills_unclaimed_interactions(rig: R
assert len(pids) == 2, pids
for item in created:
_assert_billed(_await_spend_row(item, seconds=90), rates)
assert _claimer_pid(_await_outcome(item, "billed")) in pids
claimer: Final = _claimer_pid(_await_outcome(item, "billed"))
assert claimer in pids or _booted_after(claimer, created_after), (claimer, pids)
for item in created:
assert len(_spend_rows(item)) == 1
@ -669,7 +679,7 @@ def test_settlement_on_another_replica_releases_the_creators_budget_reservation(
pinned: Final = rig.creator.request(
"POST", "/v1beta/interactions", {"model": model, "input": "settle pinned", "background": True}, key=key
)
assert pinned.status_code == 400, pinned.text
assert pinned.status_code == 422 and pinned.json()["error"]["type"] == "budget_exceeded", pinned.text
_state(rig, first, _completed())
deleted: Final = _delete(rig.settler, first, key)
assert deleted.status_code == 200, deleted.text