litellm/tests/unit/router_strategy/test_base_routing_strategy.py
yuneng-jiang a11a93f44a
test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)
* 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found superseded by stronger ones kept in this move.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: move tests/test_litellm/llms into tests/unit/llms

Rename-only. Moves the provider tests and the fine-tuning fixtures they
load, mirroring the old paths. Follow-up commits merge, split and wire them.

* test: merge, split and prune the moved llms tests

Merges the Databricks chat transformation tests into the existing unit
file, keeps the tests that need real keys or the network in
tests/test_litellm, deletes the audited tests a stronger unit test
already covers, and points imports at tests.unit.llms.

* ci: run the moved llms tests under their legacy flags

The Vertex AI and All Other Providers shards keep their legacy test-path
for the retained files and add the llm-vertex-ai and llm-other-providers
unit selections. CircleCI gets matching unit jobs.

* test: make the tests/unit/llms directories packages

Adds __init__.py to the moved dirs and drops the legacy ones whose
directories no longer hold tests.

* test: drop script runners and path hacks the llms split left dangling

The __main__ runners in the split openai_like files and the Databricks e2e
runner called tests that now live in the other half of the split or were
deleted. The retained legacy halves also no longer need sys.path edits.

* 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.

* test: move tests/test_litellm integrations and secret_managers into tests/unit

Rename-only. Mirrors the old paths, including the directory conftests
and the prompt and JSON fixtures. Follow-up commits prune and wire them.

* test: prune and repoint the moved integrations tests

Deletes the 7 audited tests a stronger test in the same tree already
covers, imports the TLS sink helpers from their new conftest path, and
restores os.environ after each integrations test. Some presets write
OTEL_EXPORTER_OTLP_HEADERS straight into os.environ, and without the
legacy tree's test ordering that header leaked into the AgentOps tests.

* ci: run the moved integrations tests under their legacy flag

The integrations GHA shard and a new CircleCI job run the integrations
unit selection. secret_managers joins the misc selection.

* docs: point integrations and secret_managers references at tests/unit

* test: make the moved integrations directories packages

* test: keep the Databricks manual e2e runner and fix the SageMaker Nova run path

The Databricks e2e file is a manual script whose main() calls the tests
that were pruned, so pruning them broke the documented run. It is back to
its main version. The SageMaker Nova docstring now points at the file's
real location in tests/local_testing.

* test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit

Rename-only. Mirrors the old paths, including fixtures, the stubtest config
and the native-route wheel script. Two files that collide with existing unit
files are merged in a follow-up commit.

* test: merge, prune and repoint the moved core, routing, responses, caching and rust_bridge tests

Merges the two files that collided with existing unit files, folding the
legacy extra case into test_is_chat_completion_cached_dict, and deletes the
9 audited tests a stronger test in the same file already covers.

Keeps what needs the network in tests/test_litellm: test_tokenizers pulls a
tokenizer from the Hugging Face hub, and the gpt2 and r50k_base tokenizer
cases download their BPE files. The unit core_utils conftest points
TIKTOKEN_CACHE_DIR at litellm's bundled encodings so the rest never depend on
import order to stay offline, and FakeSecretVault moves to a shared module
so both trees can build it.

* ci: run the moved core, routing, responses, caching and rust_bridge tests under their flags

core_utils gets a core-utils flag and CircleCI job, and its GHA shard keeps
the legacy path for the retained network tests. router_utils and
router_strategy join enterprise-routing, responses joins
responses-caching-types (minus responses/mcp, which mcp-integration owns),
caching joins caching-local and rust_bridge joins misc. The redis-compat,
test-rust, stubtest and merge-smoke paths follow the move.

* docs: point the Rust crate references at tests/unit

* test: make the moved core, routing and rust_bridge directories packages

* test: keep the no-loop DualCache batch_get_cache regression test

It runs the sync path outside any event loop, which the inside-loop test
cannot, so a change that picks the Redis client by loop state would only
show up there.

* test: keep the job's UNIT_FLAG out of the shard-script tests

* fix(url_utils): block 192.0.0.0/24 on every Python patch release

* test: move the new budget limiter tests into tests/unit/router_strategy

* test: move the new sentry scrubbing tests into tests/unit/litellm_core_utils

* test: move the new zerobus tests into tests/unit/integrations

* test: make tests/unit/integrations/zerobus a package

* test: load litellm's own tiktoken cache setup once instead of resetting it per test

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-25 17:10:13 -07:00

164 lines
6 KiB
Python

import json
import logging
from typing import Any, Dict, List, Optional, Set, Union
import pytest
import asyncio
from unittest.mock import MagicMock, patch
from litellm.caching.caching import DualCache
from litellm.caching.redis_cache import RedisCircuitBreakerOpenError, RedisPipelineIncrementOperation
from litellm.router_strategy.base_routing_strategy import BaseRoutingStrategy
@pytest.fixture
async def mock_dual_cache():
dual_cache = MagicMock(spec=DualCache)
dual_cache.in_memory_cache = MagicMock()
dual_cache.redis_cache = MagicMock()
# Set up async method mocks to return coroutines
future1: asyncio.Future[None] = asyncio.Future()
future1.set_result(None)
dual_cache.in_memory_cache.async_increment.return_value = future1
future2: asyncio.Future[None] = asyncio.Future()
future2.set_result(None)
dual_cache.redis_cache.async_increment_pipeline.return_value = future2
future3: asyncio.Future[None] = asyncio.Future()
future3.set_result(None)
dual_cache.in_memory_cache.async_set_cache.return_value = future3
# Fix for async_batch_get_cache
batch_future: asyncio.Future[Dict[str, str]] = asyncio.Future()
batch_future.set_result({"key1": "10.0", "key2": "20.0"})
dual_cache.redis_cache.async_batch_get_cache.return_value = batch_future
return dual_cache
@pytest.fixture
async def base_strategy(mock_dual_cache):
return BaseRoutingStrategy(
dual_cache=mock_dual_cache,
should_batch_redis_writes=False,
default_sync_interval=1,
)
@pytest.mark.asyncio
async def test_increment_value_in_current_window(base_strategy, mock_dual_cache):
# Test incrementing value in current window
key = "test_key"
value = 10.0
ttl = 3600
await base_strategy._increment_value_in_current_window(key, value, ttl)
# Verify in-memory cache was incremented
mock_dual_cache.in_memory_cache.async_increment.assert_called_once_with(
key=key, value=value, ttl=ttl
)
# Verify operation was queued for Redis
assert len(base_strategy.redis_increment_operation_queue) == 1
queued_op = base_strategy.redis_increment_operation_queue[0]
assert isinstance(queued_op, dict)
assert queued_op["key"] == key
assert queued_op["increment_value"] == value
assert queued_op["ttl"] == ttl
@pytest.mark.asyncio
async def test_push_in_memory_increments_to_redis(base_strategy, mock_dual_cache):
# Add some operations to the queue
base_strategy.redis_increment_operation_queue = [
RedisPipelineIncrementOperation(key="key1", increment_value=10, ttl=3600),
RedisPipelineIncrementOperation(key="key2", increment_value=20, ttl=3600),
]
await base_strategy._push_in_memory_increments_to_redis()
# Verify Redis pipeline was called
mock_dual_cache.redis_cache.async_increment_pipeline.assert_called_once()
# Verify queue was cleared
assert len(base_strategy.redis_increment_operation_queue) == 0
@pytest.mark.asyncio
async def test_sync_in_memory_spend_with_redis(base_strategy, mock_dual_cache):
from litellm.types.caching import RedisPipelineIncrementOperation
# Setup test data
base_strategy.in_memory_keys_to_update = {"key1"}
base_strategy.redis_increment_operation_queue = [
RedisPipelineIncrementOperation(key="key1", increment_value=10, ttl=3600),
]
# Mock the in-memory cache batch get responses for before snapshot
in_memory_before_future: asyncio.Future[List[str]] = asyncio.Future()
in_memory_before_future.set_result(["5.0"]) # Initial values
mock_dual_cache.in_memory_cache.async_batch_get_cache.return_value = (
in_memory_before_future
)
# Mock Redis batch get response
redis_future: asyncio.Future[Dict[str, str]] = asyncio.Future()
redis_future.set_result([15.0]) # Redis values
mock_dual_cache.redis_cache.async_increment_pipeline.return_value = redis_future
# Mock in-memory get for after snapshot
in_memory_after_future: asyncio.Future[Optional[str]] = asyncio.Future()
in_memory_after_future.set_result("8.0") # Value after potential updates
mock_dual_cache.in_memory_cache.async_get_cache.return_value = (
in_memory_after_future
)
await base_strategy._sync_in_memory_spend_with_redis()
# Verify the final merged values
set_cache_calls = mock_dual_cache.in_memory_cache.async_set_cache.call_args_list
print(f"set_cache_calls: {set_cache_calls}")
assert any(
call.kwargs["key"] == "key1" and float(call.kwargs["value"]) == 18.0
for call in set_cache_calls
)
# Verify cache keys still exist
assert len(base_strategy.in_memory_keys_to_update) == 1
@pytest.mark.asyncio
async def test_cache_keys_management(base_strategy):
# Test adding and getting cache keys
base_strategy.add_to_in_memory_keys_to_update("key1")
base_strategy.add_to_in_memory_keys_to_update("key2")
base_strategy.add_to_in_memory_keys_to_update("key1") # Duplicate should be ignored
cache_keys = base_strategy.get_in_memory_keys_to_update()
assert len(cache_keys) == 2
assert "key1" in cache_keys
assert "key2" in cache_keys
# Test resetting cache keys
base_strategy.reset_in_memory_keys_to_update()
assert len(base_strategy.get_in_memory_keys_to_update()) == 0
@pytest.mark.asyncio
async def test_push_refused_by_the_open_circuit_breaker_is_not_logged_as_an_error(base_strategy, mock_dual_cache, caplog):
"""The sync loop pushes every 100 ms under usage-based routing, so an open breaker must not add an error line per cycle."""
mock_dual_cache.redis_cache.async_increment_pipeline.side_effect = RedisCircuitBreakerOpenError(
"Redis circuit breaker is open - skipping async_increment_pipeline"
)
base_strategy.redis_increment_operation_queue = [{"key": "k", "increment_value": 1.0, "ttl": 60}]
with caplog.at_level(logging.ERROR):
await base_strategy._push_in_memory_increments_to_redis()
assert caplog.records == []
assert base_strategy.redis_increment_operation_queue == []