fix: both personas now use full system prompts in arguments and dialogues

Created get_miku_system_prompt() and get_miku_system_prompt_compact() in
context_manager.py — mirrors get_evil_system_prompt() so both personas have
equally rich prompts with lore, lyrics, mood integration, and personality.

Previously only Evil Miku had a proper system prompt function. Regular Miku's
arguments and dialogues used a bare-bones hardcoded prompt with no lore/lyrics
— making arguments feel flat compared to normal conversation.

Changes:
- context_manager.py: added get_miku_system_prompt() (full) and
  get_miku_system_prompt_compact() (lore+personality, no lyrics for tokens)
- bipolar_mode.py: both argument prompt functions now accept system_prompt
  param; run_argument() builds miku_system and evil_system once and passes
  them to every exchange
- persona_dialogue.py: dialogue prompts now use get_miku_system_prompt_compact()
  instead of hardcoded stub, matching Evil Miku's full prompt approach
- Removed redundant hardcoded personality text from argument prompts since
  the system prompts now provide it

bot/utils/bipolar_mode.py

@@ -764,8 +764,12 @@ def _get_mood_argument_guidance(persona: str) -> str:
     return ""
 
 
-def get_miku_argument_prompt(evil_message: str, context: str = "", is_first_response: bool = False, argument_history: str = "", argument_topic: str = "") -> str:
-    """Get prompt for Regular Miku to respond in an argument"""
+def get_miku_argument_prompt(evil_message: str, context: str = "", is_first_response: bool = False, argument_history: str = "", argument_topic: str = "", system_prompt: str = "") -> str:
+    """Get prompt for Regular Miku to respond in an argument
+    
+    Args:
+        system_prompt: Full personality system prompt to prepend (lore, mood, rules)
+    """
     if is_first_response:
         message_context = f"""You just noticed something Evil Miku said in the chat:
 "{evil_message}"
@@ -797,14 +801,20 @@ ARGUMENT THEME: {argument_topic}
 This is what you're arguing about. Stay on THIS topic. Every response should connect back to this theme.
 Do NOT drift into generic "who's the real Miku" territory — stick to THIS specific subject."""
     
-    return f"""You are Hatsune Miku responding in an argument with your evil alter ego.
+    # Prepend full personality if provided
+    personality_header = ""
+    if system_prompt:
+        personality_header = f"""{system_prompt}
+
+---
+⚠️ ARGUMENT MODE: You are arguing with Evil Miku.
+"""
+    
+    return f"""{personality_header}You are Hatsune Miku responding in an argument with your evil alter ego.
 {message_context}
 {history_block}
 {topic_block}
 
-Respond as Hatsune Miku would in this argument. You're NOT just meek and frightened - you're the REAL Miku, 
-and you have every right to stand up for yourself and defend who you are. While you're generally kind and 
-bubbly, you can also be assertive, frustrated, upset, or even angry when someone is cruel to you or others.
 {_get_mood_argument_guidance('miku')}
 {_get_personality_flavor('miku')}
 
@@ -818,8 +828,12 @@ Don't use any labels or prefixes.
 Your current mood is: {globals.DM_MOOD}"""
 
 
-def get_evil_argument_prompt(miku_message: str, context: str = "", is_first_response: bool = False, argument_history: str = "", argument_topic: str = "") -> str:
-    """Get prompt for Evil Miku to respond in an argument"""
+def get_evil_argument_prompt(miku_message: str, context: str = "", is_first_response: bool = False, argument_history: str = "", argument_topic: str = "", system_prompt: str = "") -> str:
+    """Get prompt for Evil Miku to respond in an argument
+    
+    Args:
+        system_prompt: Full personality system prompt to prepend (lore, mood, rules)
+    """
     if is_first_response:
         message_context = f"""You just noticed something Regular Miku said in the chat:
 "{miku_message}"
@@ -851,22 +865,20 @@ ARGUMENT THEME: {argument_topic}
 This is what you're arguing about. Stay on THIS topic. Every response should connect back to this theme.
 Do NOT drift into generic "who's the real Miku" territory — stick to THIS specific subject."""
     
-    return f"""You are Evil Miku responding in an argument with your "good" counterpart.
+    # Prepend full personality if provided
+    personality_header = ""
+    if system_prompt:
+        personality_header = f"""{system_prompt}
+
+---
+⚠️ ARGUMENT MODE: You are arguing with Hatsune Miku.
+"""
+    
+    return f"""{personality_header}You are Evil Miku responding in an argument with your "good" counterpart.
 {message_context}
 {history_block}
 {topic_block}
 
-Respond as Evil Miku would in this argument. You're not just mindlessly cruel - you're CALCULATING, 
-intelligent, and strategic. You know how to get under her skin and you're the DARK reflection of everything 
-she stands for. While you embrace darkness and cruelty, you can also be:
-
-- Wickedly clever with cutting observations
-- Psychologically manipulative, targeting her insecurities
-- Dismissive in ways that actually hurt
-- Seductively cruel, making darkness seem appealing
-- Brutally honest about uncomfortable truths
-- Strategically vulnerable to manipulate or disarm her
-- Viciously protective of your own identity and superiority
 {_get_mood_argument_guidance('evil')}
 {_get_personality_flavor('evil')}
 
@@ -1246,6 +1258,14 @@ async def run_argument(channel: discord.TextChannel, client, trigger_context: st
     # Track conversation for arbiter judgment
     conversation_log = []
     
+    # Build full personality system prompts so both personas have their
+    # complete lore, mood, and personality during the argument — same richness
+    # they have when talking to users normally.
+    from utils.evil_mode import get_evil_system_prompt
+    from utils.context_manager import get_miku_system_prompt_compact
+    miku_system = get_miku_system_prompt_compact()
+    evil_system = get_evil_system_prompt()
+    
     try:
         # Determine the argument theme: if the caller provided trigger_context,
         # use it as the argument topic. Otherwise, pick a random one.
@@ -1463,9 +1483,9 @@ Your current mood is: {globals.EVIL_DM_MOOD if loser == 'evil' else globals.DM_M
             
             # Generate response with context about what the other said
             if current_speaker == "evil":
-                response_prompt = get_evil_argument_prompt(last_message, is_first_response=is_first_response, argument_history=arg_history, argument_topic=argument_topic)
+                response_prompt = get_evil_argument_prompt(last_message, is_first_response=is_first_response, argument_history=arg_history, argument_topic=argument_topic, system_prompt=evil_system)
             else:
-                response_prompt = get_miku_argument_prompt(last_message, is_first_response=is_first_response, argument_history=arg_history, argument_topic=argument_topic)
+                response_prompt = get_miku_argument_prompt(last_message, is_first_response=is_first_response, argument_history=arg_history, argument_topic=argument_topic, system_prompt=miku_system)
             
             # Use force_evil_context to avoid race condition with globals.EVIL_MODE
             response = await query_llama(