mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-03 02:22:24 +00:00
39e31958f8
* test(proxy): move auth, hooks, policy_engine and client tests into tests/unit/proxy Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): stub HIBP through respx by disabling the aiohttp transport Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): share the httpx transport fixture across proxy unit tests Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): restore proxy globals without a missing-value sentinel Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): package moved dirs and stub the login breach check at the HTTP boundary Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): isolate the mcp server manager per test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yuneng <yuneng@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
44 lines
1.6 KiB
Python
44 lines
1.6 KiB
Python
from datetime import datetime, timezone
|
|
|
|
import pytest
|
|
|
|
from litellm.caching.caching import DualCache
|
|
from litellm.proxy.hooks.dynamic_rate_limiter import (
|
|
DynamicRateLimiterCache,
|
|
_PROXY_DynamicRateLimitHandler,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_sadd_and_get_share_injected_clock_window():
|
|
dual_cache = DualCache()
|
|
cache = DynamicRateLimiterCache(
|
|
cache=dual_cache,
|
|
time_fn=lambda: datetime(2024, 1, 1, 10, 30, 0, tzinfo=timezone.utc),
|
|
)
|
|
await cache.async_set_cache_sadd(model="my-fake-model", value=["p1", "p2", "p3"])
|
|
assert await cache.async_get_cache(model="my-fake-model") == 3
|
|
assert await dual_cache.async_get_cache(key="10-30:my-fake-model") is not None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_minute_rollover_between_sadd_and_get_reads_empty_window():
|
|
ticks = iter(
|
|
(
|
|
datetime(2024, 1, 1, 10, 30, 59, 999999, tzinfo=timezone.utc),
|
|
datetime(2024, 1, 1, 10, 31, 0, 0, tzinfo=timezone.utc),
|
|
)
|
|
)
|
|
cache = DynamicRateLimiterCache(cache=DualCache(), time_fn=lambda: next(ticks))
|
|
await cache.async_set_cache_sadd(model="my-fake-model", value=["p1"])
|
|
assert await cache.async_get_cache(model="my-fake-model") is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handler_threads_time_fn_to_internal_cache():
|
|
handler = _PROXY_DynamicRateLimitHandler(
|
|
internal_usage_cache=DualCache(),
|
|
time_fn=lambda: datetime(2024, 1, 1, 10, 30, 0, tzinfo=timezone.utc),
|
|
)
|
|
await handler.internal_usage_cache.async_set_cache_sadd(model="my-fake-model", value=["p1", "p2"])
|
|
assert await handler.internal_usage_cache.async_get_cache(model="my-fake-model") == 2
|