scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 82

fix(ci): add missing provider docs, handle deprecated Azure model, fix realtime tests

Browse source 
- Add black_forest_labs and charity_engine to provider_endpoints_support.json
  (fixes check_code_and_doc_quality job)
- Handle Azure ModelDeprecated (410) error in test_azure_img_gen_health_check
  by gracefully skipping when deployment is deprecated (external infrastructure)
- Replace gpt-4o-realtime-preview-2024-10-01 with gpt-4o-realtime-preview-2024-12-17
  in realtime tests (old model removed from model list)
- Pin websockets==13.1.0 in realtime_translation_testing CI job to match
  other jobs and avoid websockets 15.x import breakage

Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>
This commit is contained in:
Cursor Agent 2026-03-12 03:59:53 +00:00
parent ce80e16755
commit 319eea66ef
4 changed files with 57 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.circleci/config.yml
View file

@ -1320,7 +1320,7 @@ jobs:
pip install "respx==0.22.0"
pip install "pytest-xdist==3.6.1"
pip install "pytest-timeout==2.2.0"
pip install "websockets"
pip install "websockets==13.1.0"
# Run pytest and generate JUnit XML report
- run:
name: Run realtime tests

36
provider_endpoints_support.json
View file

@ -458,6 +458,24 @@
"interactions": true
}
},
"charity_engine": {
"display_name": "Charity Engine (`charity_engine`)",
"url": "https://docs.litellm.ai/docs/providers/charity_engine",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false,
"interactions": false
}
},
"chutes": {
"display_name": "Chutes (`chutes`)",
"endpoints": {
@ -813,6 +831,24 @@
"search": true
}
},
"black_forest_labs": {
"display_name": "Black Forest Labs (`black_forest_labs`)",
"url": "https://docs.litellm.ai/docs/providers/black_forest_labs",
"endpoints": {
"chat_completions": false,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": true,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false,
"interactions": false
}
},
"brave": {
"display_name": "Brave Search (`brave`)",
"url": "https://docs.litellm.ai/docs/search/brave",

12
tests/litellm_utils_tests/test_health_check.py
View file

@ -117,8 +117,20 @@ async def test_azure_img_gen_health_check():
or "internal failure" in error_str
)
# Check if the model deployment has been permanently deprecated by Azure
is_model_deprecated = (
"modeldeprecated" in error_str
or "model deprecated" in error_str
or "deprecated and no longer available" in error_str
)
# If it's the last attempt or not a transient error, fail the test
if attempt == max_retries - 1 or not is_transient_error:
if is_model_deprecated:
pytest.skip(
f"Azure model deployment is deprecated (external infrastructure issue): "
f"{response.get('error', 'Unknown error')}"
)
assert (
isinstance(response, dict) and "error" not in response
), f"Health check failed: {response.get('error', 'Unknown error')}"

16
tests/llm_translation/realtime/test_openai_realtime.py
View file

@ -101,7 +101,7 @@ async def test_openai_realtime_direct_call_no_intent():
try:
await litellm._arealtime(
model="gpt-4o-realtime-preview-2024-10-01",
model="gpt-4o-realtime-preview-2024-12-17",
websocket=websocket_client,
api_key=os.environ.get("OPENAI_API_KEY"),
timeout=60
@ -234,13 +234,13 @@ async def test_openai_realtime_direct_call_with_intent():
caught_exception = None
query_params: RealtimeQueryParams = {
"model": "gpt-4o-realtime-preview-2024-10-01",
"model": "gpt-4o-realtime-preview-2024-12-17",
"intent": "chat"
}
try:
await litellm._arealtime(
model="gpt-4o-realtime-preview-2024-10-01",
model="gpt-4o-realtime-preview-2024-12-17",
websocket=websocket_client,
api_key=os.environ.get("OPENAI_API_KEY"),
query_params=query_params,
@ -296,7 +296,7 @@ def test_realtime_query_params_construction():
from litellm.types.realtime import RealtimeQueryParams
# Test case 1: intent is None (should not be included)
model = "gpt-4o-realtime-preview-2024-10-01"
model = "gpt-4o-realtime-preview-2024-12-17"
intent = None
query_params: RealtimeQueryParams = {"model": model}
@ -334,17 +334,17 @@ async def test_realtime_query_params_use_normalized_model_name(monkeypatch):
)
def fake_get_llm_provider(model, api_base=None, api_key=None):
return ("gpt-4o-realtime-preview-2024-10-01", "openai", None, None)
return ("gpt-4o-realtime-preview-2024-12-17", "openai", None, None)
monkeypatch.setattr(realtime_main, "get_llm_provider", fake_get_llm_provider)
query_params: RealtimeQueryParams = {
"model": "openai/gpt-4o-realtime-preview-2024-10-01",
"model": "openai/gpt-4o-realtime-preview-2024-12-17",
"intent": "chat",
}
await realtime_main._arealtime(
model="openai/gpt-4o-realtime-preview-2024-10-01",
model="openai/gpt-4o-realtime-preview-2024-12-17",
websocket=MagicMock(),
api_key="sk-test",
query_params=query_params,
@ -353,6 +353,6 @@ async def test_realtime_query_params_use_normalized_model_name(monkeypatch):
called_kwargs = mock_async_realtime.call_args.kwargs
assert (
called_kwargs["query_params"]["model"] == "gpt-4o-realtime-preview-2024-10-01"
called_kwargs["query_params"]["model"] == "gpt-4o-realtime-preview-2024-12-17"
)
assert called_kwargs["query_params"]["intent"] == "chat"