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 108

test(e2e): fail the run when a Rust gateway silently serves /messages through Python (#34208)

Browse source 
A gateway whose native extension is unavailable falls back to the Python
implementation without raising, so it answers /v1/messages normally and the
only difference on the wire is the absent x-litellm-rust header. Nothing in
the suite read that header, so a Rust deployment that had stopped running
Rust produced a fully green e2e run.

Assert the marker on the streamed Messages assertions when E2E_EXPECT_RUST is
set. It stays opt-in because the same suite image also runs against the
standard gateway, which has no Rust path and must keep passing; the two
deployments are already separate Applications, so this is one value on the
Rust instance rather than branching inside the tests.
This commit is contained in:
Yassin Kortam 2026-07-22 14:43:13 -07:00 • committed by GitHub
parent 482f05190c
commit 3f98f62748
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
tests/e2e/e2e_config.py
View file

@ -72,6 +72,8 @@ POLL_TIMEOUT = float(os.environ.get("E2E_POLL_TIMEOUT", "120"))
POLL_INTERVAL = float(os.environ.get("E2E_POLL_INTERVAL", "5"))
REQUEST_TIMEOUT = float(os.environ.get("E2E_REQUEST_TIMEOUT", "60"))
EXPECT_RUST = os.environ.get("E2E_EXPECT_RUST", "").strip().lower() in ("1", "true", "yes")
LOAD_USERS = int(os.environ.get("E2E_LOAD_USERS", "750"))
LOAD_SPAWN_RATE = float(os.environ.get("E2E_LOAD_SPAWN_RATE", "50"))
LOAD_DURATION_SECONDS = float(os.environ.get("E2E_LOAD_DURATION_SECONDS", "60"))

9
tests/e2e/llm_translation/test_messages_azure_foundry_e2e.py
View file

@ -12,7 +12,7 @@ from __future__ import annotations
import pytest
from e2e_config import unique_marker
from e2e_config import EXPECT_RUST, unique_marker
from e2e_http import StreamingResponse, require_successful_call, unwrap
from endpoints_client import EndpointsClient
from lifecycle import ResourceManager
@ -50,6 +50,13 @@ def _assert_streamed_ok(result: StreamingResponse) -> None:
assert any("message_stop" in event for event in result.stream_events), (
"stream never reached message_stop"
)
if EXPECT_RUST:
assert result.headers.get("x-litellm-rust") == "true", (
"E2E_EXPECT_RUST is set, so this gateway must serve /v1/messages through the "
"Rust path, but the response carried no x-litellm-rust marker. The request "
"still succeeded, which is exactly the failure mode: a gateway whose native "
f"extension is unavailable falls back to Python silently. headers={result.headers}"
)
class TestAzureFoundryMessages: