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 Delete eight tests the audit found superseded by stronger ones kept in this move.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>
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
import shlex
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
from string import Template
|
|
from types import MappingProxyType
|
|
from typing import Final
|
|
|
|
import pytest
|
|
import yaml
|
|
|
|
_REPO_ROOT: Final = Path(__file__).resolve().parents[2]
|
|
_BASE_WORKFLOW: Final = _REPO_ROOT / ".github" / "workflows" / "_test-unit-base.yml"
|
|
_SHARD_ENV: Final = MappingProxyType({"WORKERS": "2", "RERUNS": "2", "DIST": "loadscope", "TEST_TIMEOUT_SECONDS": "1"})
|
|
_HANG_GUARD_FLAGS: Final = frozenset(("-n", "--dist", "--reruns", "--reruns-delay", "--timeout", "--rerun-except"))
|
|
_HUNG_TEST_MODULE: Final = """
|
|
import threading
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def hangs_on_teardown():
|
|
yield
|
|
threading.Event().wait()
|
|
|
|
|
|
def test_body_waits_forever():
|
|
threading.Event().wait()
|
|
|
|
|
|
def test_fixture_teardown_waits_forever(hangs_on_teardown):
|
|
assert True
|
|
|
|
|
|
def test_passes():
|
|
assert True
|
|
"""
|
|
|
|
|
|
def _run_tests_script() -> str:
|
|
workflow: Final = yaml.safe_load(_BASE_WORKFLOW.read_text())
|
|
return next(step["run"] for step in workflow["jobs"]["run"]["steps"] if step.get("name") == "Run tests")
|
|
|
|
|
|
def _pytest_invocations(script: str) -> tuple[tuple[str, ...], ...]:
|
|
return tuple(tuple(shlex.split(line)) for line in script.replace("\\\n", " ").splitlines() if " pytest " in line)
|
|
|
|
|
|
def _hang_guard_args(invocation: tuple[str, ...]) -> tuple[str, ...]:
|
|
return tuple(
|
|
Template(token).safe_substitute(_SHARD_ENV)
|
|
for previous, token in zip(("", *invocation), invocation)
|
|
if token.split("=", 1)[0] in _HANG_GUARD_FLAGS or previous in _HANG_GUARD_FLAGS
|
|
)
|
|
|
|
|
|
_INVOCATIONS: Final = _pytest_invocations(_run_tests_script())
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"invocation", _INVOCATIONS, ids=tuple("xdist" if "-n" in invocation else "serial" for invocation in _INVOCATIONS)
|
|
)
|
|
def test_a_hung_test_fails_fast_and_names_itself_under_the_shard_flags(
|
|
invocation: tuple[str, ...], tmp_path: Path
|
|
) -> None:
|
|
hung_module: Final = tmp_path / "test_hung.py"
|
|
hung_module.write_text(_HUNG_TEST_MODULE)
|
|
|
|
result: Final = subprocess.run(
|
|
(sys.executable, "-m", "pytest", str(hung_module), "-p", "no:cacheprovider", *_hang_guard_args(invocation)),
|
|
cwd=tmp_path,
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=90,
|
|
check=False,
|
|
)
|
|
|
|
assert result.returncode == 1, result.stdout
|
|
assert "FAILED test_hung.py::test_body_waits_forever" in result.stdout
|
|
assert "ERROR test_hung.py::test_fixture_teardown_waits_forever" in result.stdout
|
|
assert "Timeout (>1.0s) from pytest-timeout" in result.stdout
|
|
assert "1 failed, 2 passed, 1 error" in result.stdout
|