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

# 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

View file

@ -12,6 +12,7 @@ from llama_stack.providers.utils.inference.model_registry import RemoteInference
class BedrockBaseConfig(RemoteInferenceProviderConfig):
auth_credential: None = Field(default=None, exclude=True)
aws_access_key_id: str | None = Field(
default_factory=lambda: os.getenv("AWS_ACCESS_KEY_ID"),
description="The AWS access key to use. Default use environment variable: AWS_ACCESS_KEY_ID",