diff --git a/tests/basic/test_coder.py b/tests/basic/test_coder.py
index e72baf1ab..25531d421 100644
--- a/tests/basic/test_coder.py
+++ b/tests/basic/test_coder.py
@@ -846,6 +846,44 @@ This command will print 'Hello, World!' to the console."""
             # Check if handle_shell_commands was called with the correct argument
             coder.handle_shell_commands.assert_not_called()
 
+    def test_show_exhausted_error(self):
+        with GitTemporaryDirectory():
+            io = InputOutput(yes=True)
+            coder = Coder.create(self.GPT35, "diff", io=io)
+
+            # Set up some real done_messages and cur_messages
+            coder.done_messages = [
+                {"role": "user", "content": "Hello, can you help me with a Python problem?"},
+                {"role": "assistant", "content": "Of course! I'd be happy to help. What's the problem you're facing?"},
+                {"role": "user", "content": "I need to write a function that calculates the factorial of a number."},
+                {"role": "assistant", "content": "Sure, I can help you with that. Here's a simple Python function to calculate the factorial of a number:"},
+            ]
+
+            coder.cur_messages = [
+                {"role": "user", "content": "Can you optimize this function for large numbers?"},
+            ]
+
+            # Mock the necessary methods and attributes
+            coder.main_model.token_count = MagicMock(return_value=1000)
+            coder.main_model.info = {
+                "max_input_tokens": 4000,
+                "max_output_tokens": 1000,
+            }
+            coder.partial_response_content = "Here's an optimized version of the factorial function:"
+            coder.io.tool_error = MagicMock()
+
+            # Call the method
+            coder.show_exhausted_error()
+
+            # Check if tool_error was called with the expected message
+            coder.io.tool_error.assert_called()
+            error_message = coder.io.tool_error.call_args[0][0]
+            
+            # Assert that the error message contains the expected information
+            self.assertIn("Model gpt-3.5-turbo has hit a token limit!", error_message)
+            self.assertIn("Input tokens: ~1,000 of 4,000", error_message)
+            self.assertIn("Output tokens: ~1,000 of 1,000", error_message)
+            self.assertIn("Total tokens: ~2,000 of 4,000", error_message)
 
 if __name__ == "__main__":
     unittest.main()