- Fixed function name mismatch: generateImage() -> generateManualImage()
- Fixed status div ID mismatch in HTML
- Added /image/view/{filename} endpoint to serve generated images from ComfyUI output
- Implemented proper image preview with DOM element creation instead of innerHTML
- Added robust error handling with onload/onerror event handlers
- Added debug logging to image serving endpoint for troubleshooting
- Images now display directly in the Web UI after generation
Features:
- Real-time streaming chat interface (ChatGPT-like experience)
- Model selection: Text model (fast) or Vision model (image analysis)
- System prompt toggle: Chat with Miku's personality or raw LLM
- Mood selector: Choose from 14 different emotional states
- Full context integration: Uses complete miku_lore.txt, miku_prompt.txt, and miku_lyrics.txt
- Conversation memory: Maintains chat history throughout session
- Image upload support for vision model
- Horizontal scrolling tabs for responsive design
- Clear chat history functionality
- SSE (Server-Sent Events) for streaming responses
- Keyboard shortcuts (Ctrl+Enter to send)
Technical changes:
- Added POST /chat/stream endpoint in api.py with streaming support
- Updated ChatMessage model with mood, conversation_history, and image_data
- Integrated context_manager for proper Miku personality context
- Added Chat with LLM tab to index.html
- Implemented JavaScript streaming client with EventSource-like handling
- Added CSS for chat messages, typing indicators, and animations
- Made tab navigation horizontally scrollable for narrow viewports
- Added /autonomous/join-conversation API endpoint in api.py
- Added 'Detect and Join Conversation' button to Web UI under Autonomous Actions
- Added 'autonomous join-conversation' command to CLI tool (miku-cli.py)
- Updated miku_detect_and_join_conversation_for_server to support force=True parameter
- When force=True: skips time limit, activity checks, and random chance
- Force mode uses last 10 user messages regardless of age
- Manual triggers via Web UI/CLI now work even with old messages
- Moved on_message_event() call to END of message processing in bot.py
- Only track messages for autonomous when NOT addressed to Miku
- Fixed autonomous_engine.py to convert all message-triggered actions to join_conversation
- Prevent inappropriate autonomous actions (general, share_tweet, change_profile_picture) when triggered by user messages
- Ensures Miku responds to user messages FIRST before any autonomous action fires
This fixes the issue where autonomous actions would fire before Miku's response to user messages, and ensures the 'detect and join conversation' safeguard works properly.
Twitter changed their JavaScript response format to include unquoted keys in JSON objects, which breaks twscrape's parser. This fix applies a monkey patch that uses regex to quote the unquoted keys before parsing.
This resolves the issue preventing figurine notifications from being sent for the past several days.
Reference: https://github.com/vladkens/twscrape/issues/284
- Removed parseInt() calls that were causing Discord snowflake IDs to lose precision
- Discord IDs exceed JavaScript's safe integer limit (2^53-1), causing corruption
- Fixed sendBedtime(), triggerAutonomous(), custom prompt, and addServer() functions
- Keep guild_id and channel_id values as strings throughout the frontend
- Backend FastAPI correctly parses string IDs to Python integers without precision loss
- Resolves issue where wrong server ID was sent (e.g., 1429954521576116200 instead of 1429954521576116337)
- Consolidated all .bak.* files from bot/ directory into backups/2025-12-07/
- Moved unused autonomous_wip.py to backups (verified not imported anywhere)
- Relocated old .bot.bak.80825/ backup directory into backups/2025-12-07/old-bot-bak-80825/
- Preserved autonomous_v1_legacy.py as it is still actively used by autonomous.py
- Created new backups/ directory with date-stamped subdirectory for better organization
- Detect animated GIFs and preserve animation frames during upload
- Extract dominant color from first frame for role color syncing
- Generate multi-frame descriptions using existing video analysis pipeline
- Skip face detection/cropping for GIFs to maintain original animation
- Update UI to inform users about GIF support and Nitro requirement
- Add metadata flag to distinguish animated vs static profile pictures
