Implement recursion check in response generation

Added a safety check to prevent infinite recursion within the response generation function. When `use_tools` is active, the code now inspects the call stack and terminates the process if a certain recursion depth is exceeded. This ensures that the code is robust against potential infinite loops that could block or crash the service. A default threshold is set with a TODO for revisiting the hard-coded limit, and the recursion detection logs the occurrence for easier debugging and maintenance.

Note: Recursion limit handling may require future adjustments to the `allow_override` parameter based on real-world feedback or testing.

src/gptbot/classes/openai.py

@@ -5,6 +5,7 @@ import tiktoken
 import asyncio
 import json
 import base64
+import inspect
 
 from functools import partial
 from contextlib import closing
@@ -140,6 +141,24 @@ class OpenAI:
             f"Generating response to {len(messages)} messages for user {user} in room {room}..."
         )
 
+        # Check current recursion depth to prevent infinite loops
+
+        if use_tools:
+            frames = inspect.stack()
+            current_function = inspect.getframeinfo(frames[0][0]).function
+            count = sum(1 for frame in frames if inspect.getframeinfo(frame[0]).function == current_function)
+            self.logger.log(f"{current_function} appears {count} times in the call stack")
+            
+            if count > 5:
+                self.logger.log(f"Recursion depth exceeded, aborting.")
+                return self.generate_chat_response(
+                    messages,
+                    user=user,
+                    room=room,
+                    allow_override=False, # TODO: Could this be a problem?
+                    use_tools=False,
+                )
+
         tools = [
             {
                 "type": "function",