address greptile review feedback (greploop iteration 1)

- Add api-version query param to Azure realtime URLs
- Remove Content-Type from Azure realtime_calls headers (httpx sets it)
- Add token expiry validation in proxy_realtime_calls endpoint
- Fix type annotations for upstream_resp

Made-with: Cursor

litellm/llms/azure/realtime/http_transformation.py

@@ -24,9 +24,10 @@ class AzureRealtimeHTTPConfig(BaseRealtimeHTTPConfig):
             or ""
         )
 
-    def get_complete_url(self, api_base: Optional[str], model: str) -> str:
+    def get_complete_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
         base = self.get_api_base(api_base).rstrip("/")
-        return f"{base}/v1/realtime/client_secrets"
+        version = api_version or get_secret_str("AZURE_API_VERSION") or "2024-12-17"
+        return f"{base}/openai/realtime/client_secrets?api-version={version}"
 
     def validate_environment(
         self,
@@ -40,8 +41,12 @@ class AzureRealtimeHTTPConfig(BaseRealtimeHTTPConfig):
             "Content-Type": "application/json",
         }
 
+    def get_realtime_calls_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
+        base = self.get_api_base(api_base).rstrip("/")
+        version = api_version or get_secret_str("AZURE_API_VERSION") or "2024-12-17"
+        return f"{base}/openai/realtime/calls?api-version={version}"
+
     def get_realtime_calls_headers(self, ephemeral_key: str) -> dict:
         return {
             "api-key": ephemeral_key,
-            "Content-Type": "application/sdp",
         }

litellm/proxy/realtime_endpoints/endpoints.py

@@ -1,8 +1,10 @@
 #### Realtime WebRTC Endpoints #####
 
 import json
+import time
 from typing import Any, Dict, Optional
 
+import httpx
 from fastapi import APIRouter, Depends, HTTPException, Request, Response
 from fastapi import status as http_status
 
@@ -148,7 +150,7 @@ async def create_realtime_client_secret(
             llm_router=llm_router,
             user_model=user_model,
         )
-        upstream_resp = await llm_call
+        upstream_resp: httpx.Response = await llm_call  # type: ignore
 
     except Exception as e:
         await proxy_logging_obj.post_call_failure_hook(
@@ -264,6 +266,16 @@ async def proxy_realtime_calls(
     sdp_body: bytes = await request.body()
     decoded_payload = _decode_realtime_token_payload(decrypted_token_value)
     if decoded_payload is not None:
+        # Check token expiry
+        expires_at = decoded_payload.get("expires_at")
+        if expires_at is not None and isinstance(expires_at, int):
+            if time.time() > expires_at:
+                return Response(
+                    content=json.dumps({"error": "Token has expired"}),
+                    status_code=http_status.HTTP_401_UNAUTHORIZED,
+                    media_type="application/json",
+                )
+        
         openai_ephemeral_key = decoded_payload.get("ephemeral_key", "")
         model = (
             decoded_payload.get("model_id")
@@ -319,7 +331,7 @@ async def proxy_realtime_calls(
             llm_router=llm_router,
             user_model=user_model,
         )
-        upstream_resp = await llm_call
+        upstream_resp: httpx.Response = await llm_call  # type: ignore
 
     except Exception as e:
         await proxy_logging_obj.post_call_failure_hook(