mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +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 Delete eight tests the audit found superseded by stronger ones kept in this move.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>
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
"""
|
|
Unit tests for litellm.compress().
|
|
"""
|
|
|
|
import os
|
|
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm.types.utils import CallTypes
|
|
|
|
CALL_TYPE = CallTypes.completion
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# BM25 scorer
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Content detection
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Message stubbing
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Retrieval tool
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# compress() — end-to-end
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Embedding scorer — integration test (skipped without API key)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.skipif(not os.environ.get("OPENAI_API_KEY"), reason="Needs OPENAI_API_KEY")
|
|
def test_embedding_scorer():
|
|
result = litellm.compress(
|
|
messages=[
|
|
{"role": "user", "content": "Authentication code " * 2000},
|
|
{"role": "user", "content": "Unrelated cooking recipes " * 2000},
|
|
{"role": "user", "content": "Fix auth"},
|
|
],
|
|
model="gpt-4o",
|
|
call_type=CALL_TYPE,
|
|
compression_trigger=1000,
|
|
embedding_model="text-embedding-3-small",
|
|
)
|
|
assert result["compression_ratio"] > 0
|
|
assert len(result["cache"]) > 0
|