fix: correct patch path in langfuse test for MAX_LANGFUSE_INITIALIZED_CLIENTS (#13192)

The test was failing because it was trying to patch MAX_LANGFUSE_INITIALIZED_CLIENTS
at the wrong path. The constant is imported from litellm.constants into the langfuse
module namespace, so we need to use patch.object on the imported module reference.

Changes:
- Import langfuse module explicitly for patching
- Use patch.object instead of patch string path
- This fixes the AttributeError that was causing CI failures
This commit is contained in:
Cole McIntosh 2025-07-31 18:11:28 -06:00 • committed by GitHub
parent 56fc0cf374
commit 0666ede8e3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -12,6 +12,7 @@ from unittest.mock import patch
import pytest
import litellm
from litellm.integrations.langfuse import langfuse as langfuse_module
from litellm.integrations.langfuse.langfuse import LangFuseLogger
@ -20,9 +21,7 @@ def test_max_langfuse_clients_limit():
Test that the max langfuse clients limit is respected when initializing multiple clients
"""
# Set max clients to 2 for testing
with patch(
"litellm.integrations.langfuse.langfuse.MAX_LANGFUSE_INITIALIZED_CLIENTS", 2
):
with patch.object(langfuse_module, "MAX_LANGFUSE_INITIALIZED_CLIENTS", 2):
# Reset the counter
litellm.initialized_langfuse_clients = 0