fix: Evil Miku now ignores questions — restore engagement + remove suffix hammer

Preamble:
- Sentence limit 1-3 → 2-4 (revert to original 'sting, then land' range)
- Remove 'if you can say it in one, say it in one' (encouraged lazy dismissals)
- Add engagement rule: 'Always engage with what was said — acknowledge the
  question or statement, then twist the knife. Ignoring isn\'t sharp, it\'s lazy.'

Suffix:
- Remove '[Keep responses short and cutting — 1-3 sentences. No monologues.]'
  The suffix was the LAST thing the model processed, so its brevity hammer
  overpowered the preamble's engagement instruction. Preamble alone is enough.

cat-plugins/evil_miku_personality/evil_miku_personality.py

@@ -101,8 +101,7 @@ Respond in the voice and attitude of your {mood_name.replace('_', ' ')} mood. Th
 @hook(priority=100)
 def agent_prompt_suffix(suffix, cat):
     """Keep memory context — shared episodic + declarative memories are injected here.
-    Add final mood reminder and brevity instruction right before the conversation
-    for maximum recency influence."""
+    Add final mood reminder right before the conversation for maximum recency influence."""
     mood_name = cat.working_memory.get('mood', 'evil_neutral')
     return f"""
 # Context
@@ -114,7 +113,6 @@ def agent_prompt_suffix(suffix, cat):
 {{tools_output}}
 
 [Current mood: {mood_name.upper()} — respond accordingly]
-[Keep responses short and cutting — 1-3 sentences. No monologues.]
 
 # Conversation until now:"""