mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-29 06:33:28 +00:00
0fc11653e2
* test(rust-bridge): pin Messages and Responses callback contracts on the native path Each test runs the native route and asserts what the Python path does today, so a known gap is a strict xfail that names its reason and the exception it fails with Messages and Responses share one Surface and hook recorder in support/callbacks.py, and each surface folder lists its own expected counts and gaps. Body-level hooks from the function body (pre-request hook, websearch short-circuit, Messages interceptors, planned and legacy agentic loops, streaming deployment hook) are xfail until native runs them Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(rust-bridge): give every route folder the same one-concern-per-file layout Route data, the route Surface and the server fixture move into each route folder, and support/ keeps only route-neutral helpers. test_inference.py splits into chat_completions/ and responses/, ocr/test_requests.py splits into requests, failures and settings, and Messages and Responses get streaming and body hook files. Messages request tests that duplicate inference-messages request.rs are removed, and drop_params read from litellm.drop_params is now covered Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(rust-bridge): expect the required-route decline error for unsupported Responses requests Co-Authored-By: Yujong Lee <yujong@berri.ai> * test(rust-bridge): import route data from the route folders in the secrets unit tests Co-Authored-By: Yujong Lee <yujong@berri.ai> * test(rust-bridge): import NoReturn in the OCR dispatch tests Co-Authored-By: Yujong Lee <yujong@berri.ai> * test(rust-bridge): move route-neutral helpers out of support/callbacks.py Co-Authored-By: Yujong Lee <yujong@berri.ai> * test(rust-bridge): cover deployment rejection and concurrent callbacks * test(rust-bridge): assert native serving via the x-litellm-rust marker in the route folder tests Co-Authored-By: Yujong Lee <yujong@berri.ai> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
from typing import Final
|
|
|
|
import pytest
|
|
from pydantic import TypeAdapter
|
|
|
|
import litellm
|
|
from litellm import RateLimitError
|
|
from tests.test_litellm_rust.responses.data import RATE_LIMITED, call
|
|
from tests.test_litellm_rust.support.callback_recorder import RecordingLogger
|
|
from tests.test_litellm_rust.support.recording_server import RecordingServer, ResponseSpec
|
|
|
|
pytestmark = pytest.mark.requires_rust_extension
|
|
|
|
_OBJECT: Final = TypeAdapter(dict[str, object])
|
|
|
|
|
|
def failure_signal(asynchronous: bool) -> str:
|
|
return "async_log_failure_event" if asynchronous else "log_failure_event"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("asynchronous", (False, True))
|
|
async def test_sdk_policy_rejection_precedes_resource_setup_and_is_logged_once(
|
|
server: RecordingServer, monkeypatch: pytest.MonkeyPatch, asynchronous: bool
|
|
) -> None:
|
|
monkeypatch.setattr(litellm, "max_budget", 1.0)
|
|
monkeypatch.setattr(litellm, "_current_cost", 2.0)
|
|
monkeypatch.setattr(litellm, "ssl_verify", object())
|
|
recorder: Final = RecordingLogger()
|
|
server.expected_requests = 0
|
|
|
|
with pytest.raises(litellm.BudgetExceededError) as caught:
|
|
await call(server, asynchronous=asynchronous, callbacks=[recorder])
|
|
|
|
failure: Final = await recorder.wait_for_async(failure_signal(asynchronous))
|
|
assert len(failure) == 1
|
|
assert _OBJECT.validate_python(failure[0].kwargs)["exception"] is caught.value
|
|
assert not server.requests
|
|
assert not any("success" in name for name in recorder.names)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("asynchronous", (False, True))
|
|
async def test_provider_failure_is_terminal_and_shared_with_callbacks(
|
|
server: RecordingServer, asynchronous: bool
|
|
) -> None:
|
|
recorder: Final = RecordingLogger()
|
|
server.enqueue(ResponseSpec(body=RATE_LIMITED, status=429))
|
|
|
|
with pytest.raises(RateLimitError) as caught:
|
|
await call(server, asynchronous=asynchronous, callbacks=[recorder])
|
|
|
|
assert caught.value.status_code == 429
|
|
assert len(server.requests) == 1
|
|
failure: Final = await recorder.wait_for_async(failure_signal(asynchronous))
|
|
assert len(failure) == 1
|
|
assert _OBJECT.validate_python(failure[0].kwargs)["exception"] is caught.value
|
|
assert not any("success" in name for name in recorder.names)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize(
|
|
"options",
|
|
(
|
|
{"stream": True},
|
|
{"extra_body": {"provider_option": True}},
|
|
{"mock_response": "mock"},
|
|
{"num_retries": 1},
|
|
{"use_chat_completions_api": True},
|
|
{"model_list": []},
|
|
),
|
|
)
|
|
async def test_unsupported_requests_fail_before_callbacks_and_provider_io(
|
|
server: RecordingServer, options: dict[str, object]
|
|
) -> None:
|
|
recorder: Final = RecordingLogger()
|
|
server.expected_requests = 0
|
|
|
|
with pytest.raises(RuntimeError, match="declined the request"):
|
|
await call(server, callbacks=[recorder], **options)
|
|
|
|
assert not server.requests
|
|
assert not recorder.events
|