mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-16 04:29:31 +00:00
* fix(config): treat blank numeric env values as unset instead of crashing at import
A numeric knob exported as an empty string, which is what a Helm value: "" or an
emptied .env line produces, raised ValueError inside litellm/constants.py and the
proxy crash-looped before serving traffic. Every int(os.getenv(...)) and
float(os.getenv(...)) in constants.py now goes through get_env_int / get_env_float,
which treat blank as unset and fall back to the default with a warning on garbage.
* fix(guardrails): treat blank litellm_params values as unset so the guardrail still loads
A guardrail whose litellm_params read os.environ/X resolves X to "" when the
variable is exported but empty. Pydantic rejected "" for bool and typed fields
such as default_on and fail_on_error, the boot log reported the guardrail as
skipped and the proxy came up without it. A before-validator on BaseLitellmParams
now drops blank string values so each field takes its default, and the
default_on shortcut in LitellmParams treats a blank value as False.
* fix(config): warn once about an unparsable numeric env value so logging cannot recurse
The LiteLLM loggers' filter reads MAX_STRING_LENGTH_STDOUT_LOG and MAX_BASE64_LENGTH_STDOUT_LOG through get_env_int on every record. Warning about a garbage value from inside that read re-entered the filter, so every log call raised RecursionError. The value is now marked as reported before the warning is logged, which also stops per-record readers from repeating it. get_env_int_or_none and the new get_env_float_or_none share the same parser
* fix(config): treat blank values as unset for the remaining import-time numeric knobs
LITELLM_MAX_STREAMING_DURATION_SECONDS, REALTIME_WEBSOCKET_MAX_MESSAGE_SIZE_BYTES, a whitespace CLI_JWT_EXPIRATION_HOURS, LITELLM_CONFIG_PARAM_CACHE_TTL_SECONDS, the agent health check timeouts and the Prisma reconnect knobs still crashed the proxy at boot when blank. A blank or unparsable REQUEST_TIMEOUT no longer counts as explicitly set, so chat completion() keeps its 600s fallback
* fix(guardrails): map blank litellm_params to the field default so PATCH can still clear a value
Dropping blank keys before validation made PATCH /guardrails/{id} with api_base "" a silent no-op. Blank values of optional fields now resolve to the field default and stay in the set fields, so the PATCH clears the stored value. Required fields and unknown keys keep the value as given
* test: cover proxy numeric knobs in-process and expect no warning for a blank Straiker api_version
The three proxy import-time numeric knobs move into litellm/constants.py so the existing in-process blank-env test covers them, replacing the subprocess test. A blank api_version now means unset, so the Straiker test asserts the key-prefix version with no warning.
* fix(guardrails): keep LitellmParams kwargs typed without adding argument-type errors
---------
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
339 lines
12 KiB
Python
339 lines
12 KiB
Python
import ast, asyncio, os
|
|
import inspect
|
|
import json
|
|
from unittest import mock
|
|
|
|
import httpx
|
|
import pytest
|
|
import respx
|
|
from fastapi.testclient import TestClient
|
|
|
|
|
|
import importlib
|
|
|
|
import litellm
|
|
from litellm import constants, get_llm_provider, MorphChatConfig
|
|
from tests._vcr_conftest_common import install_live_call_probe, record_vcr_outcome
|
|
from unittest.mock import patch
|
|
|
|
|
|
_ENV_HELPERS = frozenset(
|
|
{"get_env_int", "get_env_float", "get_env_int_in_range", "get_env_int_or_none", "get_env_float_or_none"}
|
|
)
|
|
|
|
|
|
def _single_name_target(node: ast.stmt) -> str | None:
|
|
if isinstance(node, ast.AnnAssign) and isinstance(node.target, ast.Name):
|
|
return node.target.id
|
|
if isinstance(node, ast.Assign) and len(node.targets) == 1 and isinstance(node.targets[0], ast.Name):
|
|
return node.targets[0].id
|
|
return None
|
|
|
|
|
|
def _build_constant_env_var_map() -> dict[str, str]:
|
|
"""
|
|
Build a mapping of CONSTANT_NAME -> ENV_VAR_NAME by parsing constants.py.
|
|
|
|
This keeps the test resilient when a constant name and env var name differ
|
|
(e.g., aliases like LITELLM_* env vars).
|
|
"""
|
|
env_var_map: dict[str, str] = {}
|
|
constants_source = inspect.getsource(constants)
|
|
parsed = ast.parse(constants_source)
|
|
|
|
for node in parsed.body:
|
|
constant_name = _single_name_target(node)
|
|
if constant_name is None or not isinstance(node, (ast.Assign, ast.AnnAssign)) or node.value is None:
|
|
continue
|
|
|
|
env_var_name = None
|
|
|
|
for child in ast.walk(node.value):
|
|
if not isinstance(child, ast.Call):
|
|
continue
|
|
|
|
# os.getenv("ENV_NAME", default)
|
|
if (
|
|
isinstance(child.func, ast.Attribute)
|
|
and isinstance(child.func.value, ast.Name)
|
|
and child.func.value.id == "os"
|
|
and child.func.attr == "getenv"
|
|
and len(child.args) >= 1
|
|
and isinstance(child.args[0], ast.Constant)
|
|
and isinstance(child.args[0].value, str)
|
|
):
|
|
env_var_name = child.args[0].value
|
|
break
|
|
|
|
# get_env_int("ENV_NAME", default) and its siblings
|
|
if (
|
|
isinstance(child.func, ast.Name)
|
|
and child.func.id in _ENV_HELPERS
|
|
and len(child.args) >= 1
|
|
and isinstance(child.args[0], ast.Constant)
|
|
and isinstance(child.args[0].value, str)
|
|
):
|
|
env_var_name = child.args[0].value
|
|
break
|
|
|
|
if env_var_name:
|
|
env_var_map[constant_name] = env_var_name
|
|
|
|
return env_var_map
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("cli_value", "litellm_cli_value", "expected"),
|
|
[
|
|
("48", None, 48),
|
|
(None, "48", 48),
|
|
(None, None, 24),
|
|
("48", "72", 48),
|
|
(" ", None, 24),
|
|
("", "48", 48),
|
|
],
|
|
ids=("canonical-only", "alias-only", "default", "canonical-wins", "blank-canonical", "blank-canonical-alias-set"),
|
|
)
|
|
def test_cli_jwt_expiration_hours_from_environment(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
cli_value: str | None,
|
|
litellm_cli_value: str | None,
|
|
expected: int,
|
|
) -> None:
|
|
monkeypatch.delenv("CLI_JWT_EXPIRATION_HOURS", raising=False)
|
|
monkeypatch.delenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", raising=False)
|
|
|
|
try:
|
|
if cli_value is not None:
|
|
monkeypatch.setenv("CLI_JWT_EXPIRATION_HOURS", cli_value)
|
|
if litellm_cli_value is not None:
|
|
monkeypatch.setenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", litellm_cli_value)
|
|
|
|
importlib.reload(litellm.constants)
|
|
assert litellm.constants.CLI_JWT_EXPIRATION_HOURS == expected
|
|
finally:
|
|
monkeypatch.delenv("CLI_JWT_EXPIRATION_HOURS", raising=False)
|
|
monkeypatch.delenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", raising=False)
|
|
importlib.reload(litellm.constants)
|
|
|
|
|
|
def _is_blank(value: object) -> bool:
|
|
return isinstance(value, str) and not value.strip()
|
|
|
|
|
|
@pytest.mark.parametrize("blank", ["", " "])
|
|
def test_constants_import_treats_blank_env_values_as_unset(blank: str) -> None:
|
|
"""
|
|
Regression: a numeric knob exported as a blank string (a Helm `value: ""` or an emptied .env
|
|
line) raised ValueError while importing litellm.constants, so the proxy crash-looped at boot.
|
|
Blank now means unset, so import succeeds with every env-backed constant blank, and every
|
|
numeric or optional constant keeps the value it has with the variable absent.
|
|
"""
|
|
constant_env_vars = _build_constant_env_var_map()
|
|
assert {"ROUTER_MAX_FALLBACKS", "LITELLM_MAX_STREAMING_DURATION_SECONDS"} <= constant_env_vars.keys()
|
|
env_vars = set(constant_env_vars.values())
|
|
try:
|
|
with mock.patch.dict(os.environ):
|
|
for env_var in env_vars:
|
|
os.environ.pop(env_var, None)
|
|
importlib.reload(litellm.constants)
|
|
unset = {name: getattr(litellm.constants, name) for name in constant_env_vars}
|
|
with mock.patch.dict(os.environ, {env_var: blank for env_var in env_vars}):
|
|
importlib.reload(litellm.constants)
|
|
with_blank_env = {name: getattr(litellm.constants, name) for name in constant_env_vars}
|
|
finally:
|
|
importlib.reload(litellm.constants)
|
|
|
|
numeric_or_optional = {name for name, value in unset.items() if value is None or type(value) in (int, float)}
|
|
changed = {
|
|
name: (unset[name], with_blank_env[name])
|
|
for name in numeric_or_optional
|
|
if with_blank_env[name] != unset[name] and not _is_blank(with_blank_env[name])
|
|
}
|
|
assert changed == {}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("raw", "expected_timeout", "expected_explicit"),
|
|
[
|
|
(None, constants.DEFAULT_REQUEST_TIMEOUT_SECONDS, False),
|
|
("", constants.DEFAULT_REQUEST_TIMEOUT_SECONDS, False),
|
|
(" ", constants.DEFAULT_REQUEST_TIMEOUT_SECONDS, False),
|
|
("fast", constants.DEFAULT_REQUEST_TIMEOUT_SECONDS, False),
|
|
(" 30 ", 30.0, True),
|
|
],
|
|
)
|
|
def test_request_timeout_counts_as_explicit_only_when_it_parses(
|
|
monkeypatch: pytest.MonkeyPatch, raw: str | None, expected_timeout: float, expected_explicit: bool
|
|
) -> None:
|
|
"""
|
|
Regression: a blank REQUEST_TIMEOUT fell back to the 6000s sentinel but was still flagged as
|
|
explicitly set, so chat completion() kept the 6000s sentinel instead of its 600s fallback.
|
|
"""
|
|
if raw is None:
|
|
monkeypatch.delenv("REQUEST_TIMEOUT", raising=False)
|
|
else:
|
|
monkeypatch.setenv("REQUEST_TIMEOUT", raw)
|
|
try:
|
|
importlib.reload(litellm.constants)
|
|
assert litellm.constants.request_timeout == expected_timeout
|
|
assert litellm.constants.request_timeout_explicitly_set is expected_explicit
|
|
finally:
|
|
monkeypatch.undo()
|
|
importlib.reload(litellm.constants)
|
|
|
|
|
|
@pytest.fixture()
|
|
def _vcr_outcome_gate(request, vcr):
|
|
install_live_call_probe(request, vcr)
|
|
yield
|
|
record_vcr_outcome(request, vcr)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def event_loop():
|
|
try:
|
|
loop = asyncio.get_running_loop()
|
|
except RuntimeError:
|
|
loop = asyncio.new_event_loop()
|
|
yield loop
|
|
loop.close()
|
|
|
|
|
|
@pytest.fixture(scope="function")
|
|
def setup_and_teardown(event_loop):
|
|
import litellm
|
|
|
|
original_state = {}
|
|
for attr in (
|
|
"callbacks",
|
|
"success_callback",
|
|
"failure_callback",
|
|
"_async_success_callback",
|
|
"_async_failure_callback",
|
|
):
|
|
if hasattr(litellm, attr):
|
|
val = getattr(litellm, attr)
|
|
original_state[attr] = val.copy() if val else []
|
|
for attr in _SCALAR_DEFAULTS:
|
|
if hasattr(litellm, attr):
|
|
original_state[attr] = getattr(litellm, attr)
|
|
from litellm.litellm_core_utils.logging_worker import GLOBAL_LOGGING_WORKER
|
|
|
|
asyncio.run(GLOBAL_LOGGING_WORKER.clear_queue())
|
|
importlib.reload(litellm)
|
|
asyncio.set_event_loop(event_loop)
|
|
yield
|
|
for attr, original_value in original_state.items():
|
|
if hasattr(litellm, attr):
|
|
setattr(litellm, attr, original_value)
|
|
pending = asyncio.all_tasks(event_loop)
|
|
for task in pending:
|
|
task.cancel()
|
|
if pending:
|
|
event_loop.run_until_complete(asyncio.gather(*pending, return_exceptions=True))
|
|
|
|
|
|
_SCALAR_DEFAULTS = {
|
|
"num_retries": getattr(litellm, "num_retries", None),
|
|
"set_verbose": getattr(litellm, "set_verbose", False),
|
|
"cache": getattr(litellm, "cache", None),
|
|
"allowed_fails": getattr(litellm, "allowed_fails", 3),
|
|
"disable_aiohttp_transport": getattr(litellm, "disable_aiohttp_transport", False),
|
|
"force_ipv4": getattr(litellm, "force_ipv4", False),
|
|
"drop_params": getattr(litellm, "drop_params", None),
|
|
"modify_params": getattr(litellm, "modify_params", False),
|
|
"api_base": getattr(litellm, "api_base", None),
|
|
"api_key": getattr(litellm, "api_key", None),
|
|
"cohere_key": getattr(litellm, "cohere_key", None),
|
|
}
|
|
|
|
|
|
@pytest.fixture
|
|
def _populate_known_models_for_morph_tests(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
for attr, value in vars(litellm).items():
|
|
if attr.endswith("_models") and isinstance(value, set):
|
|
monkeypatch.setattr(litellm, attr, value.copy())
|
|
monkeypatch.setattr(
|
|
litellm,
|
|
"models_by_provider",
|
|
{provider: models.copy() for provider, models in litellm.models_by_provider.items()},
|
|
)
|
|
litellm.add_known_models()
|
|
|
|
|
|
@pytest.mark.usefixtures("_vcr_outcome_gate", "setup_and_teardown", "_populate_known_models_for_morph_tests")
|
|
def test_morph_config_get_provider_info():
|
|
"""Test that MorphChatConfig returns correct provider info."""
|
|
config = MorphChatConfig()
|
|
|
|
# Test with environment variable
|
|
with patch.dict(os.environ, {"MORPH_API_KEY": "test-key-from-env"}):
|
|
api_base, api_key = config.get_openai_compatible_provider_info(None, None)
|
|
assert api_base == "https://api.morphllm.com/v1"
|
|
assert api_key == "test-key-from-env"
|
|
|
|
# Test with passed api_key
|
|
api_base, api_key = config.get_openai_compatible_provider_info(None, "direct-key")
|
|
assert api_base == "https://api.morphllm.com/v1"
|
|
assert api_key == "direct-key"
|
|
|
|
# Test with custom api_base
|
|
api_base, api_key = config.get_openai_compatible_provider_info("https://custom.morph.com", "key")
|
|
assert api_base == "https://custom.morph.com"
|
|
assert api_key == "key"
|
|
|
|
|
|
@pytest.mark.usefixtures("_vcr_outcome_gate", "setup_and_teardown", "_populate_known_models_for_morph_tests")
|
|
def test_morph_get_llm_provider():
|
|
"""Test that get_llm_provider correctly identifies morph models."""
|
|
# Test with morph/model format
|
|
_, custom_llm_provider, _, _ = get_llm_provider("morph/morph-v3-large")
|
|
assert custom_llm_provider == "morph"
|
|
|
|
_, custom_llm_provider, _, _ = get_llm_provider("morph/morph-v3-fast")
|
|
assert custom_llm_provider == "morph"
|
|
|
|
|
|
@pytest.mark.usefixtures("_vcr_outcome_gate", "setup_and_teardown", "_populate_known_models_for_morph_tests")
|
|
def test_morph_in_provider_lists():
|
|
"""Test that morph is included in all necessary provider lists."""
|
|
import litellm
|
|
from litellm.constants import (
|
|
openai_compatible_endpoints,
|
|
openai_compatible_providers,
|
|
)
|
|
|
|
# Check morph is in openai_compatible_providers
|
|
assert "morph" in openai_compatible_providers
|
|
|
|
# Check morph endpoint is in openai_compatible_endpoints
|
|
assert "https://api.morphllm.com/v1" in openai_compatible_endpoints
|
|
|
|
# Check morph is in provider_list
|
|
assert "morph" in litellm.provider_list
|
|
|
|
# Check models are in model_list after initialization
|
|
assert all(model in litellm.model_list for model in ["morph/morph-v3-large", "morph/morph-v3-fast"])
|
|
|
|
|
|
@pytest.mark.usefixtures("_vcr_outcome_gate", "setup_and_teardown", "_populate_known_models_for_morph_tests")
|
|
def test_morph_supported_params():
|
|
"""Test that MorphChatConfig returns correct supported parameters."""
|
|
config = MorphChatConfig()
|
|
supported_params = config.get_supported_openai_params("morph/morph-v3-large")
|
|
|
|
expected_params = [
|
|
"messages",
|
|
"model",
|
|
"stream",
|
|
]
|
|
|
|
assert all(param in supported_params for param in expected_params)
|
|
|
|
|
|
@pytest.mark.usefixtures("_vcr_outcome_gate", "setup_and_teardown", "_populate_known_models_for_morph_tests")
|
|
def test_morph_custom_llm_provider():
|
|
"""Test that morph models are correctly identified."""
|
|
config = MorphChatConfig()
|
|
assert config.custom_llm_provider == "morph"
|