phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 05:08:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add refresh_models support to inference adapters (default: false) (#3719)

Browse source 
# What does this PR do?

inference adapters can now configure `refresh_models: bool` to control
periodic model listing from their providers

BREAKING CHANGE: together inference adapter default changed. previously
always refreshed, now follows config.

addresses "models: refresh" on #3517

## Test Plan

ci w/ new tests
This commit is contained in:
Matthew Farrellee 2025-10-07 09:19:56 -04:00 • committed by GitHub
parent 8b9af03a1b
commit e892a3f7f4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 33 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/unit/providers/utils/inference/test_openai_mixin.py
View file

@ -466,10 +466,16 @@ class TestOpenAIMixinModelRegistration:
assert result is None
async def test_should_refresh_models(self, mixin):
"""Test should_refresh_models method (should always return False)"""
"""Test should_refresh_models method returns config value"""
# Default config has refresh_models=False
result = await mixin.should_refresh_models()
assert result is False
config_with_refresh = RemoteInferenceProviderConfig(refresh_models=True)
mixin_with_refresh = OpenAIMixinImpl(config=config_with_refresh)
result_with_refresh = await mixin_with_refresh.should_refresh_models()
assert result_with_refresh is True
async def test_register_model_error_propagation(self, mixin, mock_client_with_exception, mock_client_context):
"""Test that errors from provider API are properly propagated during registration"""
model = Model(