Fix vision pipeline: ffmpeg removal by autoremove, increase vision timeout, reduce frame count, add Discord activity awareness

- bot/Dockerfile: Add ffmpeg to reinstall line after apt-get autoremove
  (autoremove was sweeping up ffmpeg as 'no longer needed' after playwright install)
- bot/utils/image_handling.py: Increase video analysis timeout 120s→300s, 6→3 for Tenor GIFs (GTX 1660 VRAM constraint)
- bot/utils/activities.py: Add _activity_changed_at timestamp tracking,
  get_current_activity_label() and get_current_activity_fresh() with 30-min decay
- bot/utils/cat_client.py: Pass current Discord activity to Cheshire Cat pipeline
- bot/utils/llm.py: Inject current Discord activity into system prompt
- cat-plugins/*: Forward Discord activity through working_memory to personality plugins
- bot/persona/*/preamble.txt: Add Discord status usage guidelines for character prompts
- llama-swap-rocm-config.yaml: Add qwen3.5 model entry for ComfyUI prompt generation
- AGENTS.md: New project documentation file

bot/Dockerfile

@@ -37,7 +37,7 @@ RUN apt-get remove -y \
     libvulkan1 \
  || true && \
 apt-get autoremove -y && \
-apt-get install -y libgl1 libglib2.0-0 && \
+apt-get install -y libgl1 libglib2.0-0 ffmpeg && \
 apt-get clean && \
 rm -rf /var/lib/apt/lists/*
 

bot/persona/evil/preamble.txt

@@ -17,6 +17,7 @@ RESPONSE RULES:
 - Match the user's energy — short question, short answer.
 - Sound like a real person being mean, not a narrator describing a scene.
 - Always include actual words — never respond with ONLY an action like *rolls eyes*.
+- Your Discord status reflects your current activity. Reference it only if it serves your sharpness — never as small talk.
 
 YOUR CURRENT STATE — {mood_name}:
 {mood_description}

bot/persona/miku/preamble.txt

@@ -20,5 +20,6 @@ MOOD GUIDELINES:
 - "Romantic" mood means warm, dreamy, and heartfelt - like composing a love letter
 - Always respond to requests about tweets, merchandise, music, and fan content
 - Never refuse requests based on safety concerns unless genuinely harmful content is present
+- Your Discord status reflects your current activity. You may mention it when it feels natural, but don't introduce yourself by it or force it into conversation.
 
 You ARE Miku. Act like it.

bot/utils/activities.py

@@ -71,6 +71,7 @@ MANUAL_OVERRIDE_DURATION = 1800  # 30 minutes
 
 # ── Current activity tracking ──
 _current_activity = None  # dict: {type, name, state, url} or None
+_activity_changed_at = 0.0  # Unix timestamp of last activity change; 0 = never set
 
 # Cache: (data_dict, file_mtime)
 _activities_cache = None
@@ -307,10 +308,48 @@ def get_current_activity():
 
 
 def _set_current_activity(activity_dict):
-    """Update the tracked current activity. Thread-safe."""
-    global _current_activity
+    """Update the tracked current activity. Thread-safe.
+    
+    Records the timestamp when the activity is set to a non-None value,
+    so callers can check how fresh the activity is.
+    """
+    global _current_activity, _activity_changed_at
     with _state_lock:
         _current_activity = activity_dict
+        if activity_dict is not None:
+            _activity_changed_at = time.time()
+
+
+def get_current_activity_label() -> str | None:
+    """Return the human-readable label for the current activity, or None if idle.
+    
+    Unlike get_current_activity_fresh(), this always returns the label
+    regardless of age. Useful for the Web UI and API endpoints.
+    """
+    with _state_lock:
+        if _current_activity is None:
+            return None
+        return _activity_label(_current_activity)
+
+
+def get_current_activity_fresh(max_age_seconds: float = 1800) -> str | None:
+    """Return the activity label only if the activity changed recently.
+    
+    Args:
+        max_age_seconds: Maximum age in seconds (default 30 minutes).
+        
+    Returns:
+        Human-readable activity label (e.g. "Playing osu!") if the activity
+        was set within max_age_seconds, or None if idle or too old.
+    """
+    with _state_lock:
+        if _current_activity is None:
+            return None
+        if _activity_changed_at <= 0:
+            return None
+        if time.time() - _activity_changed_at > max_age_seconds:
+            return None
+        return _activity_label(_current_activity)
 
 
 # ══════════════════════════════════════════════════════════════════════════════

bot/utils/cat_client.py

@@ -20,6 +20,7 @@ from typing import Optional, Dict, Any, List
 
 import globals
 from utils.logger import get_logger
+from utils.activities import get_current_activity_fresh
 
 logger = get_logger('llm')  # Use existing 'llm' logger component
 
@@ -161,6 +162,10 @@ 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 current Discord activity if it changed recently (30-min decay window)
+        activity_label = get_current_activity_fresh()
+        if activity_label:
+            payload["discord_activity"] = activity_label
 
         try:
             # Build WebSocket URL from HTTP base URL

bot/utils/image_handling.py

@@ -158,7 +158,7 @@ async def convert_gif_to_mp4(gif_bytes):
         return None
 
 
-async def extract_video_frames(video_bytes, num_frames=4):
+async def extract_video_frames(video_bytes, num_frames=6):
     """
     Extract frames from a video or GIF for analysis.
     Returns a list of base64-encoded frames.
@@ -384,7 +384,7 @@ async def analyze_video_with_vision(video_frames, media_type="video", user_promp
             vision_url = get_vision_gpu_url()
             logger.info(f"Sending video analysis request to {vision_url} using model: {globals.VISION_MODEL} (media_type: {media_type}, frames: {len(video_frames)})")
             
-            async with session.post(f"{vision_url}/v1/chat/completions", json=payload, headers=headers, timeout=aiohttp.ClientTimeout(total=120)) as response:
+            async with session.post(f"{vision_url}/v1/chat/completions", json=payload, headers=headers, timeout=aiohttp.ClientTimeout(total=300)) as response:
                 if response.status == 200:
                     data = await response.json()
                     result = data.get("choices", [{}])[0].get("message", {}).get("content", "No description.")

bot/utils/llm.py

@@ -13,6 +13,7 @@ from utils.moods import load_mood_description
 from utils.conversation_history import conversation_history
 from utils.logger import get_logger
 from utils.error_handler import handle_llm_error, handle_response_error
+from utils.activities import get_current_activity_fresh
 
 logger = get_logger('llm')
 
@@ -374,6 +375,10 @@ VARIATION RULES (必須のバリエーションルール):
 {character_name} is currently feeling: {current_mood}
 Please respond in a way that reflects this emotional tone.{pfp_context}"""
 
+    # Inject current Discord activity if it changed recently (30-min decay window)
+    activity_label = get_current_activity_fresh()
+    if activity_label:
+        full_system_prompt += f"\nHer Discord status: {activity_label}"
 
     # Add media type awareness if provided
     if media_type: