Fix repetitive roast responses with anti-repetition mechanisms

Add frequency_penalty (0.8) and presence_penalty (0.6) to LLM chat
calls to discourage repeated tokens. Inject the bot's last 5 responses
into the system prompt so the model knows what to avoid. Strengthen
the roast prompt with explicit anti-repetition rules and remove example
lines the model was copying verbatim ("Real ___ energy", etc.).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

cogs/chat.py

@@ -188,10 +188,17 @@ class ChatCog(commands.Cog):
 
             active_prompt = self._get_active_prompt()
 
+            # Collect recent bot replies so the LLM can avoid repeating itself
+            recent_bot_replies = [
+                m["content"][:150] for m in self._chat_history[ch_id]
+                if m["role"] == "assistant"
+            ][-5:]
+
             response = await self.bot.llm.chat(
                 list(self._chat_history[ch_id]),
                 active_prompt,
                 on_first_token=start_typing,
+                recent_bot_replies=recent_bot_replies,
             )
 
         if typing_ctx:
@@ -302,9 +309,15 @@ class ChatCog(commands.Cog):
         self._chat_history[ch_id].append({"role": "user", "content": context})
         active_prompt = self._get_active_prompt()
 
+        recent_bot_replies = [
+            m["content"][:150] for m in self._chat_history[ch_id]
+            if m["role"] == "assistant"
+        ][-5:]
+
         response = await self.bot.llm.chat(
             list(self._chat_history[ch_id]),
             active_prompt,
+            recent_bot_replies=recent_bot_replies,
         )
 
         # Strip leaked metadata