Fixed rlsapi token refresh + CI config

Author: asimurka

src/app/endpoints/rlsapi_v1.py

@@ -20,6 +20,7 @@
 import constants
 from authentication import get_auth_dependency
 from authentication.interface import AuthTuple
+from authorization.azure_token_manager import AzureEntraIDManager
 from authorization.middleware import authorize
 from client import AsyncLlamaStackClientHolder
 from configuration import configuration
@@ -327,6 +328,16 @@ async def _call_llm(
     """
     client = AsyncLlamaStackClientHolder().get_client()
     resolved_model_id = model_id or await _get_default_model_id()
+
+    # Handle Azure token refresh if needed
+    if (
+        resolved_model_id.startswith("azure")
+        and AzureEntraIDManager().is_entra_id_configured
+        and AzureEntraIDManager().is_token_expired
+        and AzureEntraIDManager().refresh_token()
+    ):
+        client = await AsyncLlamaStackClientHolder().update_azure_token()
+
     logger.debug("Using model %s for rlsapi v1 inference", resolved_model_id)
 
     response = await client.responses.create(

tests/e2e/configs/run-azure.yaml

@@ -22,10 +22,10 @@ providers:
   - provider_id: azure
     provider_type: remote::azure
     config: 
-      api_key: ${env.AZURE_API_KEY}
       base_url: https://ols-test.openai.azure.com/openai/v1
       api_version: 2024-02-15-preview
       allowed_models: ["gpt-4o-mini"]
+      model_validation: false
   - provider_id: openai
     provider_type: remote::openai
     config: