fix: address review feedback for proactive reply logic

- Parse display names with ': ' split to handle colons in names
- Reset cooldown to half instead of subtract-3 to reduce LLM call frequency
- Remove redundant message.guild check

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

cogs/chat.py

@@ -250,8 +250,8 @@ class ChatCog(commands.Cog):
                     memory_parts = []
                     seen_users = set()
                     for line in recent_for_check:
-                        name = line.split(":")[0]
-                        if name not in seen_users and message.guild:
+                        name = line.split(": ", 1)[0]
+                        if name not in seen_users:
                             seen_users.add(name)
                             member = discord.utils.find(
                                 lambda m, n=name: m.display_name == n,
@@ -274,10 +274,8 @@ class ChatCog(commands.Cog):
                             should_reply = True
                             is_proactive = True
                     else:
-                        # Not relevant — partially reset cooldown so we check again sooner
-                        self._messages_since_reply[ch_id] = max(
-                            0, self._messages_since_reply[ch_id] - 3
-                        )
+                        # Not relevant — reset to half cooldown so we wait a bit before rechecking
+                        self._messages_since_reply[ch_id] = cooldown // 2
 
         if not should_reply:
             return