fix: Improve LLM empty response handling with clearer warning messages

aider/coders/base_coder.py

@@ -1721,7 +1721,7 @@ class Coder:
 
     def show_send_output_stream(self, completion):
         received_content = False
-        
+
         for chunk in completion:
             if len(chunk.choices) == 0:
                 continue
@@ -1765,9 +1765,9 @@ class Coder:
                     sys.stdout.write(safe_text)
                 sys.stdout.flush()
                 yield text
-        
+
         if not received_content:
-            self.io.tool_warning("Empty response received from LLM.")
+            self.io.tool_warning("Empty response received from LLM. Check your provider account?")
 
     def live_incremental_response(self, final):
         show_resp = self.render_incremental_response(final)

aider/io.py

@@ -933,6 +933,10 @@ class InputOutput:
         return mdStream
 
     def assistant_output(self, message, pretty=None):
+        if not message:
+            self.tool_warning("Empty response received from LLM. Check your provider account?")
+            return
+
         show_resp = message
 
         # Coder will force pretty off if fence is not triple-backticks
@@ -944,7 +948,7 @@ class InputOutput:
                 message, style=self.assistant_output_color, code_theme=self.code_theme
             )
         else:
-            show_resp = Text(message or "<no response>")
+            show_resp = Text(message or "(empty response)")
 
         self.console.print(show_resp)