mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-12 03:48:56 +00:00
3eeca75ca0
* test: move offline router, latency-routing, retry and exception tests from local_testing into tests/unit Moves 29 offline nodes into the tests/unit files that mirror the code they exercise. Hosted-provider calls are mocked at the HTTP boundary with respx, and sleeps that only built a start/end gap are replaced by explicit timestamps. Legacy files left empty are deleted. * ci: record the live prompt caching cases left in tests/local_testing as unrun Moving the router prompt caching test to tests/unit leaves only live Anthropic and Vertex cases in tests/local_testing/test_anthropic_prompt_caching.py, which every CircleCI -k already deselects * test: freeze the clock in the moved lowest-latency routing tests The latency logger buckets usage by the current minute, so a run that crosses a minute boundary could grow the cache and fail the memory check. The moved tests now use fixed timestamps and a frozen clock in the logger module * ci: describe the mixed prompt caching file accurately in the coverage allowlist
75 lines
1.8 KiB
Python
75 lines
1.8 KiB
Python
import sys, os
|
|
import traceback
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
import pytest
|
|
import openai
|
|
import litellm
|
|
from litellm import completion
|
|
from litellm import (
|
|
AuthenticationError,
|
|
BadRequestError,
|
|
RateLimitError,
|
|
ServiceUnavailableError,
|
|
OpenAIError,
|
|
)
|
|
|
|
user_message = "Hello, whats the weather in San Francisco??"
|
|
messages = [{"content": user_message, "role": "user"}]
|
|
|
|
|
|
def logger_fn(user_model_dict):
|
|
# print(f"user_model_dict: {user_model_dict}")
|
|
pass
|
|
|
|
|
|
# test_completion_with_num_retries()
|
|
def test_completion_with_0_num_retries():
|
|
try:
|
|
litellm.set_verbose = False
|
|
print("making request")
|
|
|
|
# Use the completion function
|
|
response = completion(
|
|
model="gpt-3.5-turbo",
|
|
messages=[{"gm": "vibe", "role": "user"}],
|
|
max_retries=4,
|
|
)
|
|
|
|
print(response)
|
|
|
|
# print(response)
|
|
except Exception as e:
|
|
print("exception", e)
|
|
pass
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("sync_mode", [True, False])
|
|
async def test_completion_with_retry_policy_no_error(sync_mode):
|
|
"""
|
|
Test that the completion function does not throw an error when the retry policy is set
|
|
"""
|
|
from unittest.mock import patch, MagicMock, AsyncMock
|
|
from litellm.types.router import RetryPolicy
|
|
|
|
retry_number = 1
|
|
retry_policy = RetryPolicy(
|
|
ContentPolicyViolationErrorRetries=retry_number, # run 3 retries for ContentPolicyViolationErrors
|
|
AuthenticationErrorRetries=0, # run 0 retries for AuthenticationErrorRetries
|
|
)
|
|
|
|
data = {
|
|
"model": "gpt-3.5-turbo",
|
|
"messages": [{"gm": "vibe", "role": "user"}],
|
|
"retry_policy": retry_policy,
|
|
}
|
|
try:
|
|
if sync_mode:
|
|
completion(**data)
|
|
else:
|
|
await completion(**data)
|
|
except Exception as e:
|
|
print(e)
|