Initial release: rarelens platform skeleton (AGPL-3.0)

End-to-end variant interpretation platform for rare genetic disease research:
SvelteKit UI, FastAPI + PostgreSQL API, Nextflow/Ensembl VEP pipeline,
LightGBM pathogenicity scoring with MLflow, K8s/ArgoCD/GCP infrastructure.
Public test data only; no clinical claims.

api/app/config.py

@@ -0,0 +1,15 @@
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(env_file=".env", extra="ignore")
+
+    database_url: str = "postgresql+asyncpg://rarelens:rarelens@localhost:5432/rarelens"
+    mlflow_tracking_uri: str = "http://localhost:5000"
+    model_name: str = "rarelens-pathogenicity"
+    model_stage: str = "Production"
+    gcs_bucket: str | None = None          # set in GCP; local uses ./data
+    pubsub_topic: str | None = None        # "vcf-uploaded" in GCP; local runs pipeline inline
+
+
+settings = Settings()