Code review changes

scripts/chat.py

@@ -1,11 +1,11 @@
-from time import sleep
+import time
 import openai
 from dotenv import load_dotenv
 from config import Config
 import token_counter
 from llm_utils import create_chat_completion
-cfg = Config()
 
+cfg = Config()
 
 def create_chat_message(role, content):
     """
@@ -48,10 +48,8 @@ def chat_with_ai(
             """
             model = cfg.fast_llm_model # TODO: Change model from hardcode to argument
             # Reserve 1000 tokens for the response
-
             if debug:
-                print(f"Token limit: {token_limit}")
-            
+                print(f"Token limit: {token_limit}")          
             send_token_limit = token_limit - 1000
 
             current_context = [
@@ -73,7 +71,6 @@ def chat_with_ai(
                 message_to_add = full_message_history[next_message_to_add_index]
 
                 tokens_to_add = token_counter.count_message_tokens([message_to_add], model)
-
                 if current_tokens_used + tokens_to_add > send_token_limit:
                     break
 
@@ -99,16 +96,13 @@ def chat_with_ai(
                 print(f"Send Token Count: {current_tokens_used}")
                 print(f"Tokens remaining for response: {tokens_remaining}")
                 print("------------ CONTEXT SENT TO AI ---------------")
-
                 for message in current_context:
                     # Skip printing the prompt
-
                     if message["role"] == "system" and message["content"] == prompt:
                         continue
                     print(
                         f"{message['role'].capitalize()}: {message['content']}")
                     print()
-
                 print("----------- END OF CONTEXT ----------------")
 
             # TODO: use a model defined elsewhere, so that model can contain temperature and other settings we care about
@@ -130,4 +124,4 @@ def chat_with_ai(
         except openai.error.RateLimitError:
             # TODO: WHen we switch to langchain, this is built in
             print("Error: ", "API Rate Limit Reached. Waiting 10 seconds...")
-            sleep(10)
+            time.sleep(10)