phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Taking into account review: ignore, asserts, pytest.fixture

Browse source 
Signed-off-by: Akram Ben Aissi <akram.benaissi@gmail.com>
This commit is contained in:
Akram Ben Aissi 2025-09-17 19:49:38 +02:00
parent 5cc605deb5
commit 1a25a17836
2 changed files with 22 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

30
tests/unit/providers/inference/test_remote_vllm.py
View file

@ -680,46 +680,42 @@ async def test_openai_chat_completion_is_async(vllm_inference_adapter):
async def test_should_refresh_models():
"""
Test the should_refresh_models method with different api_token configurations.
Test the should_refresh_models method with different refresh_models configurations.
This test verifies that:
1. When api_token is None or empty, should_refresh_models returns False
2. When api_token is "fake" (default), should_refresh_models returns False
3. When api_token is a real token and refresh_models is True, should_refresh_models returns True
4. When api_token is a real token and refresh_models is False, should_refresh_models returns False
1. When refresh_models is True, should_refresh_models returns True regardless of api_token
2. When refresh_models is False, should_refresh_models returns False regardless of api_token
"""
# Test case 1: api_token is None, refresh_models is True
# Test case 1: refresh_models is True, api_token is None
config1 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token=None, refresh_models=True)
adapter1 = VLLMInferenceAdapter(config1)
result1 = await adapter1.should_refresh_models()
assert result1 is False, "should_refresh_models should return False when api_token is None"
assert result1 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 2: api_token is empty string, refresh_models is True
# Test case 2: refresh_models is True, api_token is empty string
config2 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="", refresh_models=True)
adapter2 = VLLMInferenceAdapter(config2)
result2 = await adapter2.should_refresh_models()
assert result2 is False, "should_refresh_models should return False when api_token is empty"
assert result2 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 3: api_token is "fake" (default), refresh_models is True
# Test case 3: refresh_models is True, api_token is "fake" (default)
config3 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="fake", refresh_models=True)
adapter3 = VLLMInferenceAdapter(config3)
result3 = await adapter3.should_refresh_models()
assert result3 is False, "should_refresh_models should return False when api_token is 'fake'"
assert result3 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 4: api_token is real token, refresh_models is True
# Test case 4: refresh_models is True, api_token is real token
config4 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-123", refresh_models=True)
adapter4 = VLLMInferenceAdapter(config4)
result4 = await adapter4.should_refresh_models()
assert result4 is True, "should_refresh_models should return True when api_token is real and refresh_models is True"
assert result4 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 5: api_token is real token, refresh_models is False
# Test case 5: refresh_models is False, api_token is real token
config5 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-456", refresh_models=False)
adapter5 = VLLMInferenceAdapter(config5)
result5 = await adapter5.should_refresh_models()
assert result5 is False, (
"should_refresh_models should return False when api_token is real but refresh_models is False"
)
assert result5 is False, "should_refresh_models should return False when refresh_models is False"
async def test_provider_data_var_context_propagation(vllm_inference_adapter):