phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 13:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: use SecretStr for inference provider auth credentials (#3724)

Browse source 
# What does this PR do?

use SecretStr for OpenAIMixin providers

- RemoteInferenceProviderConfig now has auth_credential: SecretStr
- the default alias is api_key (most common name)
- some providers override to use api_token (RunPod, vLLM, Databricks)
- some providers exclude it (Ollama, TGI, Vertex AI)

addresses #3517 

## Test Plan

ci w/ new tests
This commit is contained in:
Matthew Farrellee 2025-10-10 10:32:50 -04:00 • committed by GitHub
parent 6d8f61206e
commit 0066d986c5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
57 changed files with 158 additions and 149 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/together/together.py
View file

@ -39,15 +39,12 @@ class TogetherInferenceAdapter(OpenAIMixin, NeedsRequestProviderData):
provider_data_api_key_field: str = "together_api_key"
def get_api_key(self):
return self.config.api_key.get_secret_value() if self.config.api_key else None
def get_base_url(self):
return BASE_URL
def _get_client(self) -> AsyncTogether:
together_api_key = None
config_api_key = self.config.api_key.get_secret_value() if self.config.api_key else None
config_api_key = self.config.auth_credential.get_secret_value() if self.config.auth_credential else None
if config_api_key:
together_api_key = config_api_key
else: