fix debug print

README.md

@@ -17,3 +17,4 @@ converse with and use for server management.
 - [ ] Figure out system permissions and how to run as a special user.
 - [ ] Give the agent instructions on how to run the system (pulled from the database).
 - [ ] Have the agent run every `n` minutes to check Icinga2 and take action if necessary.
+- [ ] Evaluate using langchain.

run.py

@@ -45,10 +45,9 @@ def main():
         while True:
             temp_context = context
             if i > 0:
+                # Insert a prompt if this is not the first message.
                 temp_context.append({'role': 'system', 'content': 'Run another command or call "talk" to communicate with the user.'})
 
-            print(temp_context)
-
             response = client.chat.completions.create(
                 model="gpt-4",
                 messages=temp_context,