Fix reply-context speaker confusion with structured metadata pipeline

Previously, when a user replied to Miku's message via Discord's reply
feature, Miku's quoted words were embedded directly into the user's
message text using the format:
  [Replying to your message: "Miku's words"] User's response

This caused two problems:
1. The LLM had to parse "your message" to determine the quoted text
   was MIKU's words — fragile and frequently misattributed
2. When stored in episodic memory as [User]: ..., Miku's quoted words
   were permanently mislabeled under the user's speaker prefix

Now reply context flows through as structured metadata:
- bot/bot.py captures the replied-to text WITHOUT embedding it in prompt
- cat_client.py passes it as discord_reply_context in the WebSocket payload
- discord_bridge.py injects it as agent_input['reply_context'] — a
  CLEARLY LABELED note: [The user is replying to what you (Miku) said — ...]
- miku_personality.py + evil_miku_personality.py render it via
  {reply_context} placeholder in the prompt suffix, between memory
  context and conversation history

This keeps Miku's words as a separate context note, never mixed into
the user's HumanMessage. Episodic memory only stores the user's actual
words. The fallback path (when Cat is unavailable) also uses a cleaner
format with explicit speaker labels.

bot/bot.py

@@ -284,8 +284,12 @@ async def on_message(message):
 
         prompt = text  # No cleanup — keep it raw 
         user_id = str(message.author.id)
+        reply_context = None  # Will be passed as structured metadata to Cat pipeline
         
-        # If user is replying to a specific message, add context marker
+        # If user is replying to a specific message, capture the context
+        # WITHOUT embedding it in the prompt text (that caused speaker confusion).
+        # Instead, it's passed as structured metadata — the Cat plugin injects it
+        # into the prompt as a clearly labeled context note, preserving speaker boundaries.
         if message.reference:
             try:
                 replied_msg = await message.channel.fetch_message(message.reference.message_id)
@@ -293,8 +297,7 @@ async def on_message(message):
                 if replied_msg.author == globals.client.user:
                     # Truncate the replied message to keep prompt manageable
                     replied_content = replied_msg.content[:200] + "..." if len(replied_msg.content) > 200 else replied_msg.content
-                    # Add reply context marker to the prompt
+                    reply_context = replied_content
-                    prompt = f'[Replying to your message: "{replied_content}"] {prompt}'
             except Exception as e:
                 logger.error(f"Failed to fetch replied message for context: {e}")
 
@@ -364,6 +367,7 @@ async def on_message(message):
                         author_name=author_name,
                         mood=current_mood,
                         response_type=response_type,
+                        reply_context=reply_context,
                     )
                     if cat_result:
                         response, cat_full_prompt = cat_result
@@ -395,8 +399,11 @@ async def on_message(message):
 
             # Fallback to direct LLM query if Cat didn't respond
             if not response:
+                fallback_prompt = prompt
+                if reply_context:
+                    fallback_prompt = f'[Context: you (Miku) said: {reply_context}]\n[User says:] {prompt}'
                 response = await query_llama(
-                    prompt, 
+                    fallback_prompt, 
                     user_id=str(message.author.id), 
                     guild_id=guild_id, 
                     response_type=response_type,

bot/utils/cat_client.py

@@ -109,6 +109,7 @@ class CatAdapter:
         mood: Optional[str] = None,
         response_type: str = "dm_response",
         media_type: Optional[str] = None,
+        reply_context: Optional[str] = None,
     ) -> Optional[tuple]:
         """
         Send a message through the Cat pipeline via WebSocket and get a response.
@@ -162,6 +163,12 @@ class CatAdapter:
         # Pass media type so discord_bridge can add MEDIA NOTE to the prompt
         if media_type:
             payload["discord_media_type"] = media_type
+        # Pass the message the user is replying to (if any) as structured metadata.
+        # The discord_bridge plugin injects this into the prompt as a clearly-labeled
+        # context note — keeping Miku's words separate from the user's message text
+        # and preventing the speaker confusion that the old embed-in-prompt format caused.
+        if reply_context:
+            payload["discord_reply_context"] = reply_context
         # Pass current Discord activity if it changed recently (30-min decay window)
         activity_label = get_current_activity_fresh()
         if activity_label:

cat-plugins/discord_bridge/discord_bridge.py

@@ -44,6 +44,7 @@ def before_cat_reads_message(user_message_json: dict, cat) -> dict:
     evil_mode = user_message_json.get('discord_evil_mode', False)
     media_type = user_message_json.get('discord_media_type', None)
     activity = user_message_json.get('discord_activity', None)
+    reply_context = user_message_json.get('discord_reply_context', None)
 
     # Also check working memory for backward compatibility
     if not guild_id:
@@ -57,6 +58,7 @@ def before_cat_reads_message(user_message_json: dict, cat) -> dict:
     cat.working_memory['evil_mode'] = evil_mode
     cat.working_memory['media_type'] = media_type
     cat.working_memory['activity'] = activity
+    cat.working_memory['reply_context'] = reply_context
     
     return user_message_json
 
@@ -375,7 +377,21 @@ Please respond in a way that reflects this emotional tone."""
         print(f"   [Discord Bridge] Error building system prefix: {e}")
         system_prefix = cat.working_memory.get('full_system_prefix', '[system prefix not available]')
 
-    full_prompt = f"{system_prefix}\n\n# Context\n\n{episodic_mem}\n\n{declarative_mem}\n\n{tools_output}\n\n# Conversation until now:\nHuman: {user_input}"
+    # Build reply context note if the user is replying to Miku's message.
+    # This injects Miku's quoted words as a SEPARATE clearly-labeled context note
+    # (not embedded in the user's message text). Keeps speaker boundaries intact
+    # and prevents the LLM from misattributing Miku's words to the user.
+    # Uses a colon+space delimiter (no nested quotes) to avoid formatting issues
+    # when the replied message itself contains double-quote characters.
+    reply_context = cat.working_memory.get('reply_context')
+    if reply_context:
+        reply_context_note = f'[The user is replying to what you (Miku) said — you said: {reply_context}]'
+        agent_input['reply_context'] = reply_context_note
+    else:
+        reply_context_note = ''
+        agent_input['reply_context'] = ''
+
+    full_prompt = f"{system_prefix}\n\n# Context\n\n{episodic_mem}\n\n{declarative_mem}\n\n{tools_output}\n\n{reply_context_note}\n\n# Conversation until now:\nHuman: {user_input}"
     cat.working_memory['last_full_prompt'] = full_prompt
     
     return agent_input

cat-plugins/evil_miku_personality/evil_miku_personality.py

@@ -119,6 +119,8 @@ def agent_prompt_suffix(suffix, cat):
 
 {{tools_output}}
 
+{{reply_context}}
+
 [Current mood: {mood_name.upper()} — respond accordingly]
 
 # Conversation until now:

cat-plugins/miku_personality/miku_personality.py

@@ -91,6 +91,8 @@ def agent_prompt_suffix(suffix, cat):
 
 {tools_output}
 
+{reply_context}
+
 # Conversation until now:
 (Note: In the conversation below, "Human" = the person you're talking to, "AI" = you, Miku. Pay attention to who said what.)"""