feat(chat): support chat resources, implement chat-based remote discovery via resource messages

backend/src/inference.py

@@ -350,6 +350,8 @@ async def openrouter_chat_completion(app, messages, model, tools=[], opts={}, ag
         if formatted_tools:
             kwargs['tools'] = formatted_tools
 
+        print("all kwargs: " + repr(kwargs))
+
         stream_response = await app.openrouter_client.chat.send_async(**kwargs)
 
         # OpenAI format streams tool calls in parts