fix: handle None root_model in lm_handler

When users call llm_query(prompt) without specifying a model,
request.model is None. The handler correctly uses the default
client but was recording None as root_model, causing TypeError
in verbose printer.

Now falls back to client.model_name when request.model is None.

Author: XiaoConstantine

rlm/core/lm_handler.py

@@ -54,7 +54,7 @@ def _handle_single(self, request: LMRequest, handler: "LMHandler") -> LMResponse
         usage_summary = client.get_last_usage()
         return LMResponse.success_response(
             chat_completion=RLMChatCompletion(
-                root_model=request.model,
+                root_model=request.model or client.model_name,
                 prompt=request.prompt,
                 response=content,
                 usage_summary=usage_summary,
@@ -80,7 +80,7 @@ async def run_all():
 
         chat_completions = [
             RLMChatCompletion(
-                root_model=request.model,
+                root_model=request.model or client.model_name,
                 prompt=prompt,
                 response=content,
                 usage_summary=usage_summary,