add /api/v3/llm/chat/completions

routes/chat.py

@@ -1018,6 +1018,10 @@ async def llm_passthrough_v3(request: ChatRequestV3, authorization: Optional[str
         - stream: bool - whether to stream the output, default false
         - user_identifier: str - used to resolve the api_key owner
 
+    Authentication:
+        - Authorization header is required: Bearer <token>
+        - token = md5(MASTERKEY:bot_id), same scheme as the v2 API
+
     Returns:
         Union[dict, StreamingResponse]: OpenAI-compatible completion or stream
     """
@@ -1026,12 +1030,21 @@ async def llm_passthrough_v3(request: ChatRequestV3, authorization: Optional[str
         if not bot_id:
             raise HTTPException(status_code=400, detail="bot_id is required")
 
-        # Optional auth check (consistent with v3, non-blocking)
-        if authorization:
-            expected_token = generate_v2_auth_token(bot_id)
-            provided_token = extract_api_key_from_auth(authorization)
-            if provided_token and provided_token != expected_token:
-                logger.warning("Invalid auth token provided for LLM passthrough API, but continuing anyway")
+        # Authentication validation (same auth logic as v2: token = md5(MASTERKEY:bot_id))
+        expected_token = generate_v2_auth_token(bot_id)
+        provided_token = extract_api_key_from_auth(authorization)
+
+        if not provided_token:
+            raise HTTPException(
+                status_code=401,
+                detail="Authorization header is required"
+            )
+
+        if provided_token != expected_token:
+            raise HTTPException(
+                status_code=403,
+                detail=f"Invalid authentication token. Expected: {expected_token[:8]}..., Provided: {provided_token[:8]}..."
+            )
 
         # Build the LLM client from db config
         llm, model_name = await build_llm_from_bot_config(bot_id, request.user_identifier)