litellm/tests/llm_translation/test_compression.py
devin-ai-integration[bot] 99655b6f86
test: finish the non-proxy half of tests/test_litellm (#43281)
* test: move key-gated tests/test_litellm SDK tests into tests/llm_translation and drop empty folders

* test: make token counter and health check unit tests run offline

* ci: point unit shards, rust path filter, Makefile and docs at tests/unit

* docs: fix stale test_litellm run paths in moved llm_translation tests

* fix: correct databricks e2e sys.path depth and contributing example path

---------

Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-25 22:43:41 -07:00

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