mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-06 08:16:43 +00:00
The v2 resolver skips the diff-and-force recovery that caused schema thrashing when two LiteLLM versions contend for one database during a rolling deploy. The standalone migration Job already defaulted to v2; this aligns the proxy-server path. v1 stays reachable two ways: --use_legacy_migration_resolver on the CLI, and USE_V2_MIGRATION_RESOLVER=false for containerised deploys, where prisma_migration.py calls run_server with a fixed argv and the env var is the only route in. --use_v2_migration_resolver still parses, so existing commands do not die on an unknown option. Because v2 fails fast where v1 retried every failed deploy, a database that is not accepting connections yet, or another instance holding the migration advisory lock, would now kill a boot that used to ride it out. Those two failures are retried, with Prisma's stderr logged each round, and still raise once the attempts are spent. Moves the resolver tests from litellm-proxy-extras/tests, which no CI job runs, into tests/litellm-proxy-extras, and repoints the dedicated Postgres CircleCI job at the legacy path so v1 keeps real-DB and proxy-boot coverage.
320 lines
10 KiB
Python
320 lines
10 KiB
Python
import asyncio
|
|
import os
|
|
import subprocess
|
|
import time
|
|
import traceback
|
|
|
|
import pytest
|
|
|
|
PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
|
|
|
|
|
|
|
|
def _run_uv(*args: str, **kwargs) -> subprocess.CompletedProcess:
|
|
return subprocess.run(["uv", *args], check=True, cwd=PROJECT_ROOT, **kwargs)
|
|
|
|
|
|
def test_using_litellm():
|
|
try:
|
|
import litellm
|
|
|
|
print("litellm imported successfully")
|
|
except Exception as e:
|
|
pytest.fail(f"Error occurred: {e}. Installing litellm failed please retry")
|
|
|
|
|
|
def test_litellm_proxy_server():
|
|
# Sync the local litellm[proxy] dependencies into the project environment
|
|
_run_uv("sync", "--frozen", "--extra", "proxy")
|
|
|
|
# Import through the uv-managed interpreter that uv sync populated.
|
|
try:
|
|
_run_uv("run", "--no-sync", "python", "-c", "import litellm.proxy.proxy_server")
|
|
except subprocess.CalledProcessError:
|
|
pytest.fail("Failed to import litellm.proxy.proxy_server")
|
|
|
|
# Assertion to satisfy the test, you can add other checks as needed
|
|
assert True
|
|
|
|
|
|
def test_package_dependencies():
|
|
"""
|
|
Test that all optional dependency entries are exposed via project optional-dependencies.
|
|
"""
|
|
try:
|
|
import pathlib
|
|
import litellm
|
|
from packaging.requirements import Requirement
|
|
|
|
# Try to import tomllib (Python 3.11+) or tomli (older versions)
|
|
try:
|
|
import tomllib as tomli
|
|
except ImportError:
|
|
try:
|
|
import tomli
|
|
except ImportError:
|
|
pytest.skip("tomli/tomllib not available - skipping dependency check")
|
|
|
|
# Get the litellm package root path
|
|
litellm_path = pathlib.Path(litellm.__file__).parent.parent
|
|
pyproject_path = litellm_path / "pyproject.toml"
|
|
|
|
# Read and parse pyproject.toml
|
|
with open(pyproject_path, "rb") as f:
|
|
pyproject = tomli.load(f)
|
|
|
|
optional_deps = pyproject["project"]["optional-dependencies"]
|
|
assert optional_deps, "Expected project.optional-dependencies to be defined"
|
|
|
|
parsed_requirements = set()
|
|
for extra_name, requirements in optional_deps.items():
|
|
assert requirements, f"Optional dependency group '{extra_name}' is empty"
|
|
for requirement in requirements:
|
|
assert isinstance(
|
|
requirement, str
|
|
), f"Expected string requirement in extra '{extra_name}'"
|
|
parsed = Requirement(requirement)
|
|
parsed_requirements.add(parsed.name.lower())
|
|
|
|
print(parsed_requirements)
|
|
print(
|
|
f"Validated {len(parsed_requirements)} optional dependencies across {len(optional_deps)} extras groups"
|
|
)
|
|
|
|
except Exception as e:
|
|
pytest.fail(
|
|
f"Error occurred while checking dependencies: {str(e)}\n"
|
|
+ traceback.format_exc()
|
|
)
|
|
|
|
|
|
def test_cli_extra_is_a_thin_client_install():
|
|
"""The `cli` extra must install a working `lite` client without dragging in the
|
|
proxy server runtime. It therefore has to declare the CLI's real third-party
|
|
deps (rich, pyyaml, requests) and must never contain a server-only dependency
|
|
from the `proxy` extra; a leak there silently re-bloats the laptop install.
|
|
"""
|
|
import pathlib
|
|
|
|
import litellm
|
|
from packaging.requirements import Requirement
|
|
|
|
try:
|
|
import tomllib as tomli
|
|
except ImportError:
|
|
try:
|
|
import tomli
|
|
except ImportError:
|
|
pytest.skip("tomli/tomllib not available - skipping dependency check")
|
|
|
|
pyproject_path = pathlib.Path(litellm.__file__).parent.parent / "pyproject.toml"
|
|
with open(pyproject_path, "rb") as f:
|
|
optional_deps = tomli.load(f)["project"]["optional-dependencies"]
|
|
|
|
assert "cli" in optional_deps, "Expected a `cli` extra for the thin lite install"
|
|
|
|
cli_names = {Requirement(req).name.lower() for req in optional_deps["cli"]}
|
|
|
|
missing = {"rich", "pyyaml", "requests"} - cli_names
|
|
assert not missing, f"`cli` extra is missing deps the lite CLI imports: {missing}"
|
|
|
|
server_only = {
|
|
"fastapi",
|
|
"uvicorn",
|
|
"gunicorn",
|
|
"granian",
|
|
"starlette",
|
|
"boto3",
|
|
"polars",
|
|
"soundfile",
|
|
"mcp",
|
|
"cryptography",
|
|
"apscheduler",
|
|
"rq",
|
|
"litellm-enterprise",
|
|
"litellm-proxy-extras",
|
|
}
|
|
leaked = cli_names & server_only
|
|
assert not leaked, f"`cli` extra leaks proxy-server deps onto laptops: {leaked}"
|
|
|
|
|
|
AIOHTTP_POOL_POISONING_RANGE = ">=3.14.0,<3.14.2"
|
|
AIOHTTP_POOL_POISONING_RELEASES = ("3.14.0", "3.14.1")
|
|
|
|
|
|
def _load_toml(path):
|
|
try:
|
|
import tomllib as tomli
|
|
except ImportError:
|
|
try:
|
|
import tomli
|
|
except ImportError:
|
|
pytest.skip("tomli/tomllib not available - skipping dependency check")
|
|
|
|
with open(path, "rb") as f:
|
|
return tomli.load(f)
|
|
|
|
|
|
def _declared_aiohttp_specifier():
|
|
from packaging.requirements import Requirement
|
|
|
|
pyproject = _load_toml(os.path.join(PROJECT_ROOT, "pyproject.toml"))
|
|
for requirement in pyproject["project"]["dependencies"]:
|
|
parsed = Requirement(requirement)
|
|
if parsed.name.lower() == "aiohttp":
|
|
return parsed.specifier
|
|
pytest.fail("aiohttp is no longer a declared runtime dependency of litellm")
|
|
|
|
|
|
def _locked_aiohttp_version():
|
|
lock = _load_toml(os.path.join(PROJECT_ROOT, "uv.lock"))
|
|
for package in lock["package"]:
|
|
if package["name"].lower() == "aiohttp":
|
|
return package["version"]
|
|
pytest.fail("aiohttp is missing from uv.lock")
|
|
|
|
|
|
def test_declared_aiohttp_floor_excludes_pool_poisoning_releases():
|
|
"""aiohttp 3.14.0/3.14.1 re-arm the sock_read timer on a keep-alive connection
|
|
after it is back in the idle pool, so the next request to reuse it fails
|
|
instantly with a bogus timeout (aio-libs/aiohttp#12953, fixed in 3.14.2).
|
|
|
|
The wheel's own metadata is what pip resolves against, so the floor declared
|
|
here - not just the lockfile - has to exclude that range.
|
|
"""
|
|
specifier = _declared_aiohttp_specifier()
|
|
|
|
admitted = [v for v in AIOHTTP_POOL_POISONING_RELEASES if specifier.contains(v)]
|
|
assert not admitted, (
|
|
f"litellm declares aiohttp{specifier}, which still admits {admitted}. "
|
|
"Those releases poison pooled keep-alive connections and cause "
|
|
"cross-provider sub-millisecond 'Connection timed out' failures; "
|
|
"keep the floor at >=3.14.2."
|
|
)
|
|
|
|
|
|
def test_locked_aiohttp_version_is_not_pool_poisoning():
|
|
"""uv.lock is what the published Docker images install (uv sync --frozen), so a
|
|
lock that drifts back onto 3.14.0/3.14.1 ships the regression regardless of
|
|
what pyproject.toml declares.
|
|
"""
|
|
from packaging.specifiers import SpecifierSet
|
|
|
|
locked = _locked_aiohttp_version()
|
|
|
|
assert not SpecifierSet(AIOHTTP_POOL_POISONING_RANGE).contains(locked), (
|
|
f"uv.lock resolves aiohttp {locked}, which is inside the pool-poisoning "
|
|
f"range {AIOHTTP_POOL_POISONING_RANGE} (aio-libs/aiohttp#12953). "
|
|
"Re-run `uv lock` against an aiohttp>=3.14.2 floor."
|
|
)
|
|
|
|
|
|
import os
|
|
import subprocess
|
|
|
|
import requests
|
|
|
|
|
|
def _run_proxy_server_smoke_test(extra_proxy_args=None):
|
|
"""Sync deps, generate Prisma client, start proxy with optional extra args,
|
|
send a health check + chat/completions request, and tear down."""
|
|
if extra_proxy_args is None:
|
|
extra_proxy_args = []
|
|
|
|
server_process = None
|
|
try:
|
|
_run_uv(
|
|
"sync",
|
|
"--frozen",
|
|
"--group",
|
|
"proxy-dev",
|
|
"--extra",
|
|
"proxy",
|
|
"--extra",
|
|
"extra_proxy",
|
|
)
|
|
|
|
# Ensure Prisma client is generated
|
|
try:
|
|
print(f"Running prisma generate from: {PROJECT_ROOT}")
|
|
|
|
result = _run_uv(
|
|
"run",
|
|
"--no-sync",
|
|
"prisma",
|
|
"generate",
|
|
capture_output=True,
|
|
text=True,
|
|
)
|
|
print(f"Prisma generate stdout: {result.stdout}")
|
|
except subprocess.CalledProcessError as e:
|
|
print(f"Prisma generate failed: {e}")
|
|
print(f"Prisma generate stderr: {e.stderr}")
|
|
raise
|
|
filepath = os.path.dirname(os.path.abspath(__file__))
|
|
config_fp = f"{filepath}/test_configs/test_config_no_auth.yaml"
|
|
server_process = subprocess.Popen(
|
|
[
|
|
"uv",
|
|
"run",
|
|
"--no-sync",
|
|
"python",
|
|
"-m",
|
|
"litellm.proxy.proxy_cli",
|
|
"--config",
|
|
config_fp,
|
|
*extra_proxy_args,
|
|
],
|
|
cwd=PROJECT_ROOT,
|
|
)
|
|
|
|
# Allow some time for the server to start (increased for CI environments)
|
|
time.sleep(90) # Increased from 60s for slower CI runners
|
|
|
|
# Send a request to the /health/liveliness endpoint
|
|
response = requests.get("http://localhost:4000/health/liveliness")
|
|
|
|
# Check if the response is successful
|
|
assert response.status_code == 200
|
|
assert response.json() == "I'm alive!"
|
|
|
|
# Test /chat/completions
|
|
response = requests.post(
|
|
"http://localhost:4000/chat/completions",
|
|
headers={"Authorization": "Bearer 1234567890"},
|
|
json={
|
|
"model": "test_openai_models",
|
|
"messages": [{"role": "user", "content": "Hello, how are you?"}],
|
|
},
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
|
|
except ImportError:
|
|
pytest.fail("Failed to import litellm.proxy_server")
|
|
except requests.ConnectionError:
|
|
pytest.fail("Failed to connect to the server")
|
|
finally:
|
|
# Shut down the server
|
|
if server_process:
|
|
server_process.terminate()
|
|
server_process.wait()
|
|
|
|
# Additional assertions can be added here
|
|
assert True
|
|
|
|
|
|
def test_litellm_proxy_server_config_no_general_settings():
|
|
"""Exercises the default (v2) migration resolver."""
|
|
_run_proxy_server_smoke_test()
|
|
|
|
|
|
def test_litellm_proxy_server_config_no_general_settings_legacy_resolver():
|
|
"""Exercises the legacy (v1) migration resolver against a real database.
|
|
|
|
v2 is the default, so the no-arg test above already covers it. This one is
|
|
the only place the v1 opt-out gets real-DB migration plus proxy-boot
|
|
coverage, and it runs in a separate CI job against its own Postgres to
|
|
avoid collisions with the default variant.
|
|
"""
|
|
_run_proxy_server_smoke_test(extra_proxy_args=["--use_legacy_migration_resolver"])
|