litellm/tests/claude_code/basic_messaging_streaming/test_azure.py
mateo-berri c1955a15ca RALPH: fix compat matrix - Azure now hosts Claude via Microsoft Foundry
Anthropic and Microsoft announced Claude Haiku 4.5, Sonnet 4.5/4.6, and
Opus 4.1/4.6/4.7 in Microsoft Foundry on 2025-11-18, so the matrix's
Azure column should exercise a real route through the LiteLLM proxy
rather than report not_applicable.

Foundry serves Claude on an Anthropic-shape /anthropic/v1/messages
endpoint (not the Azure OpenAI chat-completions route), and LiteLLM
already supports it via the azure_ai/claude-* provider prefix
(litellm/llms/azure_ai/anthropic/{handler,transformation,messages_transformation}.py).

- test_config.yaml: add 3 azure aliases pointing at azure_ai/claude-*
  with AZURE_FOUNDRY_API_BASE / AZURE_FOUNDRY_API_KEY env
- 6x test_azure.py: replace not_applicable stubs with real run_claude
  drivers, mirroring the existing test_vertex_ai.py shape exactly
- sample_compatibility-matrix.json: Azure cells flip to pass
- _builder_unit_tests: pin the new invariant (run_claude is used,
  not_applicable is gone) and feed pass results across all 5 providers
  in the 6x5 golden test
2026-04-25 17:58:32 -07:00

101 lines
3.2 KiB
Python

"""basic_messaging_streaming x Azure (Microsoft Foundry).
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 hosted in Microsoft Foundry on Azure, and report the
outcome via `compat_result`.
Foundry exposes Claude on an Anthropic-shape `/anthropic/v1/messages`
endpoint with native SSE streaming; LiteLLM forwards stream events
through the `azure_ai/claude-*` provider unchanged.
The (feature, provider) for this cell is inferred from the file path by
`tests/claude_code/conftest.py`:
tests/claude_code/basic_messaging_streaming/test_azure.py
^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^
feature_id provider
"""
from __future__ import annotations
import os
import pytest
from tests.claude_code.cli_driver import ClaudeCLIError, run_claude
PROXY_BASE_URL_ENV = "LITELLM_PROXY_BASE_URL"
PROXY_API_KEY_ENV = "LITELLM_PROXY_API_KEY"
AZURE_MODELS = [
"claude-haiku-4-5-azure",
"claude-sonnet-4-6-azure",
"claude-opus-4-7-azure",
]
@pytest.mark.parametrize("model", AZURE_MODELS)
def test_basic_messaging_streaming_azure(compat_result, model):
"""Drive the `claude` CLI against the LiteLLM proxy and assert a
non-empty streamed reply (at least one stream-json event observed).
"""
base_url = os.environ.get(PROXY_BASE_URL_ENV)
api_key = os.environ.get(PROXY_API_KEY_ENV)
if not base_url or not api_key:
compat_result.set(
{
"status": "fail",
"error": (
f"missing required env: set {PROXY_BASE_URL_ENV} and "
f"{PROXY_API_KEY_ENV} to point at a running LiteLLM proxy"
),
}
)
pytest.fail(
f"{PROXY_BASE_URL_ENV} / {PROXY_API_KEY_ENV} not configured", pytrace=False
)
try:
result = run_claude(
prompt="Count from 1 to 5, one number per line.",
model=model,
base_url=base_url,
api_key=api_key,
)
except ClaudeCLIError as exc:
compat_result.set({"status": "fail", "error": f"[{model}] {exc}"})
pytest.fail(str(exc), pytrace=False)
return
if result.exit_code != 0:
compat_result.set(
{
"status": "fail",
"error": f"[{model}] claude CLI exited {result.exit_code}: {result.stderr.strip()}",
}
)
pytest.fail(f"claude CLI exited {result.exit_code} for {model}", pytrace=False)
return
if not result.events:
compat_result.set(
{
"status": "fail",
"error": f"[{model}] no stream-json events emitted; streaming wire silent",
}
)
pytest.fail(f"no stream events for {model}", pytrace=False)
return
if not result.text.strip():
compat_result.set(
{
"status": "fail",
"error": f"[{model}] claude returned empty assistant text",
}
)
pytest.fail(f"empty reply for {model}", pytrace=False)
return
compat_result.set({"status": "pass"})