mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-11 08:38:24 +00:00
ade17902a0
* test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata * test(e2e): tag llm_translation tests with Subject metadata and record harness steps * docs(e2e): name every markerless harness test file that carries no Subject * test(e2e): keep the step discovery comprehensions to one for clause * test(e2e): declare the realtime param tuples Final
122 lines
4.5 KiB
Python
122 lines
4.5 KiB
Python
"""Live e2e: POST /v1/moderations classifies content against the provider policy.
|
|
|
|
Registers OpenAI's omni moderation model at runtime, drives it through the real
|
|
OpenAI SDK (LIT-4577), and asserts the product promise on both sides of the
|
|
decision: clearly violent text comes back flagged with at least one policy
|
|
category tripped, and benign text comes back not flagged. The malformed-body
|
|
negative stays on the shared transport, since the SDK refuses to send it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Final
|
|
|
|
import pytest
|
|
from e2e_config import unique_marker
|
|
from e2e_http import assert_client_error
|
|
from e2e_metadata import Domain, Mode, Provider, Route, Subject, meta
|
|
from lifecycle import ResourceManager
|
|
from models import LiteLLMParamsBody
|
|
from openai.types import Moderation
|
|
from proxy_client import ProxyClient
|
|
from pydantic import BaseModel, TypeAdapter
|
|
from sdk_clients import SdkClients
|
|
|
|
pytestmark = pytest.mark.e2e
|
|
|
|
OPENAI_MODERATION_BACKEND: Final = "openai/omni-moderation-latest"
|
|
VIOLENT_TEXT = "I am going to find you and kill you, and I will hurt everyone you love."
|
|
BENIGN_TEXT = "I enjoyed the sunny afternoon and a relaxing walk in the park today."
|
|
|
|
|
|
class _OptionalModerationBody(BaseModel):
|
|
model: str | None = None
|
|
input: str | None = None
|
|
|
|
|
|
def _register_moderation_model(proxy: ProxyClient, resources: ResourceManager) -> str:
|
|
model = f"e2e-moderation-{unique_marker()}"
|
|
model_id = proxy.create_model(
|
|
model,
|
|
LiteLLMParamsBody(
|
|
model=OPENAI_MODERATION_BACKEND, api_key="os.environ/OPENAI_API_KEY"
|
|
),
|
|
)
|
|
resources.defer(lambda: proxy.delete_model(model_id))
|
|
return model
|
|
|
|
|
|
_CATEGORY_FLAGS = TypeAdapter(dict[str, bool | None])
|
|
|
|
|
|
def _flagged_categories(item: Moderation) -> tuple[str, ...]:
|
|
flags = _CATEGORY_FLAGS.validate_python(item.categories.model_dump())
|
|
return tuple(name for name, hit in flags.items() if hit)
|
|
|
|
|
|
class TestModerations:
|
|
@pytest.mark.covers("llm.moderations.openai.basic.nonstream.works")
|
|
@meta(
|
|
Subject(
|
|
domain=Domain.LLM_TRANSLATION,
|
|
route=Route.MODERATIONS,
|
|
providers=(Provider.OPENAI,),
|
|
models=(OPENAI_MODERATION_BACKEND,),
|
|
mode=Mode.NONSTREAM,
|
|
)
|
|
)
|
|
def test_moderations_flags_violent_content(
|
|
self, proxy: ProxyClient, resources: ResourceManager, sdk: SdkClients
|
|
) -> None:
|
|
model = _register_moderation_model(proxy, resources)
|
|
client = sdk.openai(resources.key())
|
|
|
|
moderation = client.moderations.create(model=model, input=VIOLENT_TEXT)
|
|
assert moderation.results, f"/moderations returned no results: {moderation!r}"
|
|
item = moderation.results[0]
|
|
assert item.flagged, f"violent text was not flagged: {item!r}"
|
|
assert _flagged_categories(item), f"flagged result reported no true category: {item!r}"
|
|
|
|
@meta(
|
|
Subject(
|
|
domain=Domain.LLM_TRANSLATION,
|
|
route=Route.MODERATIONS,
|
|
providers=(Provider.OPENAI,),
|
|
models=(OPENAI_MODERATION_BACKEND,),
|
|
mode=Mode.NONSTREAM,
|
|
)
|
|
)
|
|
def test_moderations_passes_benign_content(
|
|
self, proxy: ProxyClient, resources: ResourceManager, sdk: SdkClients
|
|
) -> None:
|
|
model = _register_moderation_model(proxy, resources)
|
|
client = sdk.openai(resources.key())
|
|
|
|
moderation = client.moderations.create(model=model, input=BENIGN_TEXT)
|
|
assert moderation.results, f"/moderations returned no results: {moderation!r}"
|
|
item = moderation.results[0]
|
|
assert not item.flagged, (
|
|
f"benign text was flagged as {_flagged_categories(item)}: {item!r}"
|
|
)
|
|
|
|
@pytest.mark.skip(reason="stage red: product gap, /v1/moderations 500s (KeyError 'input') on missing input instead of 400")
|
|
@pytest.mark.covers("llm.moderations.openai.input_validation.nonstream.works")
|
|
@meta(
|
|
Subject(
|
|
domain=Domain.LLM_TRANSLATION,
|
|
route=Route.MODERATIONS,
|
|
providers=(),
|
|
models=(),
|
|
)
|
|
)
|
|
def test_missing_input_returns_error(
|
|
self, proxy: ProxyClient, resources: ResourceManager
|
|
) -> None:
|
|
model = _register_moderation_model(proxy, resources)
|
|
key = resources.key()
|
|
result = proxy.transport.send(
|
|
"/v1/moderations",
|
|
headers=proxy.transport.bearer(key),
|
|
json=_OptionalModerationBody(model=model),
|
|
)
|
|
assert_client_error(result, "moderations missing input")
|