misc: small fix or general refactoring i did not bother commenting

Author: evilsocket

nerve/generation/litellm.py

@@ -122,6 +122,7 @@ async def _generate_next_message(
         tools_schema = self._get_extended_tooling_schema(extra_tools)
 
         try:
+            # TODO: implement forced rate limit
             # get next message
             return await self._generate(conversation, tools_schema)