mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-27 01:22:18 +00:00
f6882246d4
* ci: run the unit_selection.sh shard files on every event instead of only fork pull requests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * ci: rename fork-flag to unit-flag now that it applies on every event * test: move tests/test_litellm root and small trees into tests/unit Pure renames, no content changes. Follow-up commits in this PR fix references, merge the three files that already existed in tests/unit, keep live-provider tests in tests/test_litellm and wire CI. * test: carry tests/test_litellm conftest isolation into tests/unit Callback lists, routing fallbacks, cached HTTP clients, logger state, AWS, proxy-URL and keychain env, and session-end client cleanup now reset for unit tests too. The environment isolation owns its MonkeyPatch so a test's own monkeypatch is undone before the model-cost teardown runs. * test: merge, split and prune the moved root and small-tree tests Merge batches/test_batch_utils.py and the chat_completions and messages dispatch tests into the files that already existed in tests/unit. Keep the live Gemini interactions tests, the async image-fetch format test and the OpenAI embedding scorer test in tests/test_litellm since they need real network or keys. Put test_router.py under tests/unit/test_router so the existing package no longer shadows it. Delete eight tests the audit found superseded by stronger ones kept in this move. * ci: run the moved root and small-tree tests under their legacy flags Add the misc and responses-caching-types flags to unit_selection.sh and CircleCI, extend enterprise-routing and mcp-integration, and point the legacy GHA shards, Makefile, redis-compat workflow, merge smoke manifest and change classifier at the new paths. * test: make the new tests/unit directories packages tests/unit/test_package_layout.py requires every directory to carry an __init__.py, and without one the moved and retained test_litellm_responses_bridge.py modules collide on import. * test: scope the unit socket block to tests/unit in shared sessions The GHA shards collect the legacy test-path and the unit selection in one pytest session. The unit conftest's loopback-only block leaked into legacy modules that reach the network at import. The legacy conftest now lifts the restriction at collect and setup time, and the unit conftest re-applies it when collecting its own modules. * test: give the shard-script tests their own GITHUB_OUTPUT They only passed where the runner set it. The CircleCI unit job's env allowlist drops it, so the script's redirect failed there. * test: point the router and module-deletion checks at tests/unit router_code_coverage and code_qa_check_tests only searched tests/test_litellm, so the moved router tests no longer counted. The two silent-experiment tests the audit deleted were the only direct callers of those methods; they are replaced with tests that assert the forwarded shadow request and the recursion guard. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
88 lines
2.7 KiB
Python
88 lines
2.7 KiB
Python
"""
|
|
Tests for router retry backoff behavior.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm import Router
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_retry_backoff_uses_current_exception_headers():
|
|
"""
|
|
Ensure retry backoff uses the current retry exception, not the initial one.
|
|
"""
|
|
router = Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "gpt-3.5-turbo",
|
|
"litellm_params": {
|
|
"model": "gpt-3.5-turbo",
|
|
"api_key": "sk-test",
|
|
},
|
|
}
|
|
],
|
|
num_retries=2,
|
|
)
|
|
|
|
first_error = litellm.RateLimitError(
|
|
message="Rate limited on first attempt",
|
|
model="gpt-3.5-turbo",
|
|
llm_provider="openai",
|
|
)
|
|
first_error.litellm_response_headers = httpx.Headers({"retry-after": "1"})
|
|
|
|
second_error = litellm.RateLimitError(
|
|
message="Rate limited on second attempt",
|
|
model="gpt-3.5-turbo",
|
|
llm_provider="openai",
|
|
)
|
|
second_error.litellm_response_headers = httpx.Headers({"retry-after": "15"})
|
|
|
|
third_error = litellm.RateLimitError(
|
|
message="Rate limited on third attempt",
|
|
model="gpt-3.5-turbo",
|
|
llm_provider="openai",
|
|
)
|
|
third_error.litellm_response_headers = httpx.Headers({"retry-after": "30"})
|
|
|
|
raised_errors = [first_error, second_error, third_error]
|
|
captured_backoff_errors = []
|
|
|
|
async def mock_make_call(*args, **kwargs):
|
|
raise raised_errors.pop(0)
|
|
|
|
def mock_time_to_sleep_before_retry(*args, **kwargs):
|
|
captured_backoff_errors.append(kwargs["e"])
|
|
return 0.01
|
|
|
|
with patch.object(router, "make_call", side_effect=mock_make_call):
|
|
with patch.object(
|
|
router,
|
|
"_async_get_healthy_deployments",
|
|
return_value=(
|
|
[{"model_info": {"id": "test-id"}}],
|
|
[{"model_info": {"id": "test-id"}}],
|
|
),
|
|
):
|
|
with patch.object(
|
|
router,
|
|
"_time_to_sleep_before_retry",
|
|
side_effect=mock_time_to_sleep_before_retry,
|
|
):
|
|
with pytest.raises(litellm.RateLimitError):
|
|
await router.acompletion(
|
|
model="gpt-3.5-turbo",
|
|
messages=[{"role": "user", "content": "Hello"}],
|
|
)
|
|
|
|
# Router computes backoff once after the initial failure, then once per failed retry.
|
|
# With num_retries=2 and all attempts failing, that's 1 + 2 = 3 invocations.
|
|
assert len(captured_backoff_errors) == router.num_retries + 1
|
|
assert captured_backoff_errors[0] is first_error
|
|
assert captured_backoff_errors[1] is second_error
|
|
assert captured_backoff_errors[2] is third_error
|