diff --git a/cogs/chat.py b/cogs/chat.py
index be769af..001b71c 100644
--- a/cogs/chat.py
+++ b/cogs/chat.py
@@ -163,8 +163,27 @@ class ChatCog(commands.Cog):
                 context_parts.append(f"{user_data.offense_count} offense(s)")
             score_context = f"[Server context: {message.author.display_name} — {', '.join(context_parts)}]"
 
+            # Gather user notes and recent messages for richer context
+            extra_context = ""
+            user_notes = self.bot.drama_tracker.get_user_notes(message.author.id)
+            if user_notes:
+                extra_context += f"[Notes about {message.author.display_name}: {user_notes}]\n"
+
+            recent_user_msgs = []
+            try:
+                async for msg in message.channel.history(limit=50, before=message):
+                    if msg.author.id == message.author.id and msg.content and msg.content.strip():
+                        recent_user_msgs.append(msg.content[:200])
+                        if len(recent_user_msgs) >= 10:
+                            break
+            except discord.HTTPException:
+                pass
+            if recent_user_msgs:
+                recent_lines = "\n".join(f"- {m}" for m in reversed(recent_user_msgs))
+                extra_context += f"[{message.author.display_name}'s recent messages:\n{recent_lines}]\n"
+
             self._chat_history[ch_id].append(
-                {"role": "user", "content": f"{score_context}\n{reply_context}{message.author.display_name}: {content}"}
+                {"role": "user", "content": f"{score_context}\n{extra_context}{reply_context}{message.author.display_name}: {content}"}
             )
 
             active_prompt = self._get_active_prompt()
@@ -183,6 +202,8 @@ class ChatCog(commands.Cog):
             response = re.sub(r"\[Server context:[^\]]*\]\n?", "", response)
             response = re.sub(r"\[Replying to bot's message:[^\]]*\]\n?", "", response)
             response = re.sub(r"\[\w[\w ]* said:[^\]]*\]\n?", "", response)
+            response = re.sub(r"\[Notes about [^\]]*\]\n?", "", response)
+            response = re.sub(r"\[[^\]]*'s recent messages:[\s\S]*?\]\n?", "", response)
             # Catch reformatted metadata (LLM drops prefix but keeps content)
             response = re.sub(r"\[[^\]]*#[a-z-]+[^\]]*(?:drama score|offense)[^\]]*\]\n?", "", response, flags=re.IGNORECASE)
             response = response.strip()