Include replied-to message text in LLM context

When a user replies to the bot's message, the original bot message
text is now included in the context sent to the LLM. This prevents
the LLM from misinterpreting follow-up questions like "what does
this even mean?" since it can see what message is being referenced.

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

cogs/chat.py

@@ -48,6 +48,7 @@ class ChatCog(commands.Cog):
 
         should_reply = False
         is_proactive = False
+        reply_context = ""  # Text of the message being replied to
 
         # Check if bot is @mentioned
         if self.bot.user in message.mentions:
@@ -63,6 +64,8 @@ class ChatCog(commands.Cog):
                     )
                 if ref_msg.author.id == self.bot.user.id:
                     should_reply = True
+                    if ref_msg.content:
+                        reply_context = f"[Replying to bot's message: {ref_msg.content[:300]}]\n"
             except discord.HTTPException:
                 pass
 
@@ -143,7 +146,7 @@ class ChatCog(commands.Cog):
             score_context = f"[Server context: {message.author.display_name} — {', '.join(context_parts)}]"
 
             self._chat_history[ch_id].append(
-                {"role": "user", "content": f"{score_context}\n{message.author.display_name}: {content}"}
+                {"role": "user", "content": f"{score_context}\n{reply_context}{message.author.display_name}: {content}"}
             )
 
             active_prompt = self._get_active_prompt()