mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
6a0d03914c
* test: drop the cwd-relative sys.path.insert calls from the test suite
TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.
Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.
Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.
* test: drop the duplicate imports the sys.path sweep exposed to F811
* test(pre-call-utils): restore the os import the new bedrock tests need
328 lines
10 KiB
Python
328 lines
10 KiB
Python
"""
|
|
Tests for batch output_expires_after passthrough and team-level expiry enforcement.
|
|
"""
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
|
|
import litellm
|
|
from litellm.caching.caching import DualCache
|
|
from litellm.proxy._types import UserAPIKeyAuth
|
|
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
|
from litellm.proxy.proxy_server import app
|
|
from litellm.proxy.utils import ProxyLogging
|
|
from litellm.router import Router
|
|
from litellm.types.utils import LiteLLMBatch
|
|
|
|
from fastapi.testclient import TestClient
|
|
|
|
client = TestClient(app)
|
|
|
|
TEAM_EXPIRY = {"anchor": "created_at", "seconds": 3600}
|
|
CALLER_EXPIRY = {"anchor": "created_at", "seconds": 86400}
|
|
|
|
|
|
@pytest.fixture
|
|
def llm_router() -> Router:
|
|
return Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "gpt-3.5-turbo",
|
|
"litellm_params": {
|
|
"model": "openai/gpt-3.5-turbo",
|
|
"api_key": "test-key",
|
|
},
|
|
"model_info": {"id": "gpt-3.5-turbo-id"},
|
|
},
|
|
]
|
|
)
|
|
|
|
|
|
def _setup_proxy(monkeypatch, llm_router: Router):
|
|
proxy_logging_obj = ProxyLogging(
|
|
user_api_key_cache=DualCache(default_in_memory_ttl=1)
|
|
)
|
|
monkeypatch.setattr("litellm.proxy.proxy_server.llm_router", llm_router)
|
|
monkeypatch.setattr(
|
|
"litellm.proxy.proxy_server.proxy_logging_obj", proxy_logging_obj
|
|
)
|
|
|
|
|
|
def _make_batch_response() -> LiteLLMBatch:
|
|
return LiteLLMBatch(
|
|
id="batch_abc123",
|
|
completion_window="24h",
|
|
created_at=1234567890,
|
|
endpoint="/v1/chat/completions",
|
|
input_file_id="file-abc123",
|
|
object="batch",
|
|
status="validating",
|
|
)
|
|
|
|
|
|
def test_output_expires_after_passthrough():
|
|
"""output_expires_after flows through create_batch to the provider."""
|
|
captured = {}
|
|
|
|
def capturing_create(**kwargs):
|
|
captured.update(kwargs)
|
|
mock_response = MagicMock()
|
|
mock_response.id = "batch_123"
|
|
return mock_response
|
|
|
|
with patch("litellm.batches.main.openai_batches_instance") as mock_instance:
|
|
mock_instance.create_batch.side_effect = capturing_create
|
|
litellm.create_batch(
|
|
completion_window="24h",
|
|
endpoint="/v1/chat/completions",
|
|
input_file_id="file-abc123",
|
|
output_expires_after=CALLER_EXPIRY,
|
|
custom_llm_provider="openai",
|
|
)
|
|
|
|
assert captured["create_batch_data"]["output_expires_after"] == CALLER_EXPIRY
|
|
|
|
|
|
class TestBatchEndpointTeamOverride:
|
|
"""Verify team-level enforced_batch_output_expires_after in the proxy endpoint."""
|
|
|
|
def _post_batch(
|
|
self,
|
|
monkeypatch,
|
|
llm_router: Router,
|
|
team_metadata: dict,
|
|
request_body: dict,
|
|
) -> dict:
|
|
"""POST /v1/batches with given team_metadata and body, return captured kwargs."""
|
|
_setup_proxy(monkeypatch, llm_router)
|
|
|
|
user_key = UserAPIKeyAuth(
|
|
api_key="test-key",
|
|
team_metadata=team_metadata,
|
|
)
|
|
app.dependency_overrides[user_api_key_auth] = lambda: user_key
|
|
|
|
captured_kwargs = {}
|
|
|
|
async def mock_acreate_batch(**kwargs):
|
|
captured_kwargs.update(kwargs)
|
|
return _make_batch_response()
|
|
|
|
monkeypatch.setattr(litellm, "acreate_batch", mock_acreate_batch)
|
|
|
|
try:
|
|
response = client.post(
|
|
"/v1/batches",
|
|
json=request_body,
|
|
headers={"Authorization": "Bearer test-key"},
|
|
)
|
|
assert response.status_code == 200
|
|
finally:
|
|
app.dependency_overrides.clear()
|
|
|
|
return captured_kwargs
|
|
|
|
def test_team_override_overrides_caller(self, monkeypatch, llm_router):
|
|
"""Team enforcement wins over caller-provided value."""
|
|
kwargs = self._post_batch(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={
|
|
"enforced_batch_output_expires_after": TEAM_EXPIRY,
|
|
},
|
|
request_body={
|
|
"input_file_id": "file-abc123",
|
|
"endpoint": "/v1/chat/completions",
|
|
"completion_window": "24h",
|
|
"output_expires_after": CALLER_EXPIRY,
|
|
},
|
|
)
|
|
assert kwargs["output_expires_after"] == TEAM_EXPIRY
|
|
|
|
def test_no_team_setting_preserves_caller(self, monkeypatch, llm_router):
|
|
"""No team setting = caller value passes through."""
|
|
kwargs = self._post_batch(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={},
|
|
request_body={
|
|
"input_file_id": "file-abc123",
|
|
"endpoint": "/v1/chat/completions",
|
|
"completion_window": "24h",
|
|
"output_expires_after": CALLER_EXPIRY,
|
|
},
|
|
)
|
|
assert kwargs["output_expires_after"] == CALLER_EXPIRY
|
|
|
|
def test_team_injects_when_caller_sends_nothing(self, monkeypatch, llm_router):
|
|
"""Team enforcement applies even when caller sends no expiry."""
|
|
kwargs = self._post_batch(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={
|
|
"enforced_batch_output_expires_after": TEAM_EXPIRY,
|
|
},
|
|
request_body={
|
|
"input_file_id": "file-abc123",
|
|
"endpoint": "/v1/chat/completions",
|
|
"completion_window": "24h",
|
|
},
|
|
)
|
|
assert kwargs["output_expires_after"] == TEAM_EXPIRY
|
|
|
|
|
|
class TestBatchEndpointPolicyMetadata:
|
|
"""Batch create must not forward LiteLLM policy tracking via OpenAI metadata."""
|
|
|
|
def test_create_batch_does_not_forward_applied_policies_metadata(
|
|
self, monkeypatch, llm_router
|
|
):
|
|
from litellm.proxy.policy_engine.attachment_registry import (
|
|
get_attachment_registry,
|
|
)
|
|
from litellm.proxy.policy_engine.policy_registry import get_policy_registry
|
|
from litellm.types.proxy.policy_engine import (
|
|
Policy,
|
|
PolicyAttachment,
|
|
PolicyGuardrails,
|
|
)
|
|
|
|
policy_registry = get_policy_registry()
|
|
policy_registry._policies = {
|
|
"global-baseline": Policy(
|
|
guardrails=PolicyGuardrails(add=["pii_blocker"]),
|
|
),
|
|
}
|
|
policy_registry._initialized = True
|
|
|
|
attachment_registry = get_attachment_registry()
|
|
attachment_registry._attachments = [
|
|
PolicyAttachment(policy="global-baseline", scope="*"),
|
|
]
|
|
attachment_registry._initialized = True
|
|
|
|
_setup_proxy(monkeypatch, llm_router)
|
|
|
|
user_key = UserAPIKeyAuth(
|
|
api_key="test-key",
|
|
team_alias="batch-team",
|
|
key_alias="batch-key",
|
|
)
|
|
app.dependency_overrides[user_api_key_auth] = lambda: user_key
|
|
|
|
captured_kwargs = {}
|
|
|
|
async def mock_acreate_batch(**kwargs):
|
|
captured_kwargs.update(kwargs)
|
|
return _make_batch_response()
|
|
|
|
monkeypatch.setattr(litellm, "acreate_batch", mock_acreate_batch)
|
|
|
|
try:
|
|
response = client.post(
|
|
"/v1/batches",
|
|
json={
|
|
"input_file_id": "file-abc123",
|
|
"endpoint": "/v1/chat/completions",
|
|
"completion_window": "24h",
|
|
},
|
|
headers={"Authorization": "Bearer test-key"},
|
|
)
|
|
assert response.status_code == 200
|
|
finally:
|
|
app.dependency_overrides.clear()
|
|
policy_registry._policies = {}
|
|
policy_registry._initialized = False
|
|
attachment_registry._attachments = []
|
|
attachment_registry._initialized = False
|
|
|
|
assert captured_kwargs.get("metadata") in (None, {})
|
|
assert (
|
|
"global-baseline" in captured_kwargs["litellm_metadata"]["applied_policies"]
|
|
)
|
|
|
|
|
|
class TestBatchEndpointTeamValidation:
|
|
"""Verify validation errors for malformed team metadata on batch endpoint."""
|
|
|
|
def _post_batch_raw(
|
|
self,
|
|
monkeypatch,
|
|
llm_router: Router,
|
|
team_metadata: dict,
|
|
request_body: dict,
|
|
):
|
|
"""POST /v1/batches and return the raw response (no status assertion)."""
|
|
_setup_proxy(monkeypatch, llm_router)
|
|
|
|
user_key = UserAPIKeyAuth(
|
|
api_key="test-key",
|
|
team_metadata=team_metadata,
|
|
)
|
|
app.dependency_overrides[user_api_key_auth] = lambda: user_key
|
|
|
|
async def mock_acreate_batch(**kwargs):
|
|
return _make_batch_response()
|
|
|
|
monkeypatch.setattr(litellm, "acreate_batch", mock_acreate_batch)
|
|
|
|
try:
|
|
response = client.post(
|
|
"/v1/batches",
|
|
json=request_body,
|
|
headers={"Authorization": "Bearer test-key"},
|
|
)
|
|
finally:
|
|
app.dependency_overrides.clear()
|
|
|
|
return response
|
|
|
|
_BATCH_BODY = {
|
|
"input_file_id": "file-abc123",
|
|
"endpoint": "/v1/chat/completions",
|
|
"completion_window": "24h",
|
|
}
|
|
|
|
def test_missing_anchor_key_returns_500(self, monkeypatch, llm_router):
|
|
"""Missing 'anchor' key in team metadata returns 500."""
|
|
response = self._post_batch_raw(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={
|
|
"enforced_batch_output_expires_after": {"seconds": 3600},
|
|
},
|
|
request_body=self._BATCH_BODY,
|
|
)
|
|
assert response.status_code == 500
|
|
assert "malformed" in response.json()["error"]["message"]
|
|
|
|
def test_missing_seconds_key_returns_500(self, monkeypatch, llm_router):
|
|
"""Missing 'seconds' key in team metadata returns 500."""
|
|
response = self._post_batch_raw(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={
|
|
"enforced_batch_output_expires_after": {"anchor": "created_at"},
|
|
},
|
|
request_body=self._BATCH_BODY,
|
|
)
|
|
assert response.status_code == 500
|
|
assert "malformed" in response.json()["error"]["message"]
|
|
|
|
def test_invalid_anchor_returns_500(self, monkeypatch, llm_router):
|
|
"""Invalid anchor value in team metadata returns 500."""
|
|
response = self._post_batch_raw(
|
|
monkeypatch,
|
|
llm_router,
|
|
team_metadata={
|
|
"enforced_batch_output_expires_after": {
|
|
"anchor": "last_active_at",
|
|
"seconds": 3600,
|
|
},
|
|
},
|
|
request_body=self._BATCH_BODY,
|
|
)
|
|
assert response.status_code == 500
|
|
assert "created_at" in response.json()["error"]["message"]
|