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
"""basic_messaging_streaming x Vertex AI.
Drive the real `claude` CLI in headless `--output-format stream-json`
mode against a running LiteLLM proxy that routes Claude requests to
Anthropic's models on Google Cloud Vertex AI, and report the outcome
via `compat_result`.
The (feature, provider) for this cell is inferred from the file path by
`tests/e2e/claude_code/conftest.py`:
tests/e2e/claude_code/basic_messaging_streaming/test_vertex_ai.py
^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^
feature_id provider
"""
from __future__ import annotations
import pytest
from e2e_metadata import Domain, Mode, Provider, Route, Subject, meta
from claude_code._basic_messaging import run_basic_messaging_cell
VERTEX_AI_MODELS = [
"claude-haiku-4-5-vertex",
"claude-sonnet-4-5-vertex",
"claude-opus-4-7-vertex",
]
@pytest.mark.covers("llm.messages.vertex.basic.stream.works")
@meta(
Subject(
domain=Domain.LLM_TRANSLATION,
route=Route.MESSAGES,
providers=(Provider.VERTEX_AI,),
models=tuple(VERTEX_AI_MODELS),
mode=Mode.STREAM,
)
)
def test_basic_messaging_streaming_vertex_ai(compat_result):
"""Drive the `claude` CLI against the LiteLLM proxy and assert a
non-empty streamed reply (one row per Claude tier).
"""
run_basic_messaging_cell(
compat_result=compat_result,
models=VERTEX_AI_MODELS,
prompt="Count from 1 to 5, one number per line.",
verify_streaming=True,
)