bots talking to each otehr fix

vibe_bot/main.py

@@ -354,47 +354,52 @@ async def talkforme(ctx, *, message: str):
 
     message_counter = 0
     bot_counter = 0
-    current_user = "user"
     current_bot = bot_list[bot_counter]
-    prompt_history = [{"role": current_user, "content": topic}]
+    prompt_histories = [
+        [{"role": "user", "content": topic}],
+        [{"role": "assistant", "content": topic}],
+    ]
 
     first_bot_response = llama_wrapper.chat_completion_with_history(
         system_prompt=current_bot[1]
-        + f"\nKeep your responses under 2-3 sentences. You are talking to {current_bot[flip_counter(bot_counter)]}",
+        + f"\nKeep your responses under 2-3 sentences. You are talking to {current_bot[flip_counter(bot_counter)][0]}",
-        prompts=prompt_history,  # type: ignore
+        prompts=prompt_histories[bot_counter],  # type: ignore
         openai_url=CHAT_ENDPOINT,
         openai_api_key=CHAT_ENDPOINT_KEY,
         model=CHAT_MODEL,
         max_tokens=MAX_COMPLETION_TOKENS,
     )
     await ctx.send(f"## {current_bot[0]}\n{first_bot_response}")
-    prompt_history.append({"role": current_user, "content": first_bot_response})
+    prompt_histories[0].append({"role": "assistant", "content": first_bot_response})
+    prompt_histories[1].append({"role": "user", "content": first_bot_response})
 
-    current_user = flip_user(current_user)
     bot_counter = flip_counter(counter=bot_counter)
 
     while message_counter < min(message_limit, TALK_LIMIT):
         current_bot = bot_list[bot_counter]
-        logger.info(f"Current user is {current_user}")
         logger.info(f"Current bot is {current_bot}")
         bot_response = llama_wrapper.chat_completion_with_history(
             system_prompt=current_bot[1]
             + f"\nKeep your responses under 2-3 sentences. {current_bot[flip_counter(bot_counter)]}",
-            prompts=prompt_history,  # type: ignore
+            prompts=prompt_histories[bot_counter],  # type: ignore
             openai_url=CHAT_ENDPOINT,
             openai_api_key=CHAT_ENDPOINT_KEY,
             model=CHAT_MODEL,
             max_tokens=MAX_COMPLETION_TOKENS,
         )
         message_counter += 1
+        prompt_histories[bot_counter].append(
+            {"role": "assistant", "content": bot_response}
+        )
+        prompt_histories[flip_counter(bot_counter)].append(
+            {"role": "user", "content": bot_response}
+        )
         await ctx.send(f"## {current_bot[0]}")
         while bot_response:
             send_chunk = bot_response[:1000]
             bot_response = bot_response[1000:]
             await ctx.send(send_chunk)
-        prompt_history.append({"role": current_user, "content": bot_response})
         bot_counter = flip_counter(counter=bot_counter)
-        current_user = flip_user(current_user)
         logger.info(f"Message counter is {message_counter}/{limit}")