The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
import asyncio
from typing import Final
import pytest
import litellm
from litellm.rust_bridge import _native, execution
from litellm.rust_bridge.public_call import NativeCall
from tests.test_litellm_rust.responses.data import REQUEST
from tests.test_litellm_rust.support.callback_recorder import RecordingLogger
from tests.test_litellm_rust.support.recording_server import RecordingServer
pytestmark = pytest.mark.requires_rust_extension
@pytest.mark.asyncio
async def test_unstarted_call_has_no_provider_or_callback_effects(
server: RecordingServer, monkeypatch: pytest.MonkeyPatch
) -> None:
recorder: Final = RecordingLogger()
server.expected_requests = 0
monkeypatch.setattr(litellm, "ssl_verify", object())
monkeypatch.setattr(litellm, "max_budget", 1.0)
monkeypatch.setattr(litellm, "_current_cost", 2.0)
kwargs: Final = {
**REQUEST,
"api_key": "test-key",
"api_base": server.base_url,
"callbacks": [recorder],
}
base: Final = {
**REQUEST,
"stream": None,
"api_key": "test-key",
"api_base": server.base_url,
"custom_llm_provider": "openai",
"extra_headers": None,
}
pending: Final = execution.asynchronous(_native.aresponses)(NativeCall(args=(), kwargs=kwargs, base=base))
assert asyncio.iscoroutine(pending)
pending.close()
assert not server.requests
assert not recorder.events