Fix metadata leaking and skip sentiment for bot-directed messages

1. Broader regex to strip leaked metadata even when the LLM drops
   the "Server context:" prefix but keeps the content.

2. Skip sentiment analysis for messages that mention or reply to
   the bot. Users interacting with the bot in roast/chat modes
   shouldn't have those messages inflate their drama score.

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

cogs/sentiment.py

@@ -80,6 +80,17 @@ class SentimentCog(commands.Cog):
         if self.bot.drama_tracker.is_immune(message.author.id):
             return
 
+        # Skip sentiment analysis for messages directed at the bot
+        # (mentions, replies to bot) — users interacting with the bot
+        # in roast/chat modes shouldn't have those messages scored as toxic
+        directed_at_bot = self.bot.user in message.mentions
+        if not directed_at_bot and message.reference and message.reference.message_id:
+            ref = message.reference.cached_message
+            if ref and ref.author.id == self.bot.user.id:
+                directed_at_bot = True
+        if directed_at_bot:
+            return
+
         # Store message in channel history for context
         self._store_context(message)