Update app.py

Update app.py

Update app.py

Update app.py

feat: add camera auto-open signal handler to trigger vision modal from LLM output

style: fix comment formatting in app.py

feat: update capture_camera_image to trigger frontend camera modal via marker string

refactor: replace file-based vision uploads with base64 encoded data processing for improved compatibility

feat: add interactive webcam modal for photo capture and file uploads

refactor: remove unused imports from app.py

feat: add warning icon to privacy disclaimer in app UI

docs: update Aiko-chan description to include new search and vision capabilities

feat: add camera button styling and update camera icon to frame emoji

feat: enhance service warmups with real-data validation and add VLM and SearXNG initialization steps

refactor: relocate audio and perception logic to core module and remove legacy ui components

refactor: optimize chat text animation timing and improve VRM lip-syncing by replacing 'aa' viseme and adjusting audio smoothing

chore: remove debug print statements for Gradio version and Chatbot signature

Remove temp

Add temp

feat: implement asynchronous network warmup on login to improve serverless responsiveness

fix: prevent Gradio component resets by using gr.update() in voice processing error paths

style: update UI title to include colon separator for consistent branding

fix: remove redundant line break in app description UI

style: bold the security warning message in the application UI

feat: add privacy disclaimer to app landing page

docs: update disclaimer to include privacy warning regarding personal information and passwords

refactor: scope memory management and system prompts to individual user_id sessions throughout the chat pipeline

perf: update audio duration estimation constant for improved speech synthesis timing

feat: update recording button text content based on active state

fix: update audio b64 component visibility and selector logic for reliable element access

refactor: remove microphone permission warm-up logic from application startup

feat: replace standard Gradio microphone component with custom JS MediaRecorder and base64 transmission for audio input

feat: add client-side audio permission prompt on app load

refactor: clean up whitespace and formatting in listen.py

refactor: replace browser-side JS recording logic with Python state handler and visibility adjustment

refactor: adjust text-to-speech duration coefficients for improved timing accuracy

feat: implement dynamic scroll helper to ensure chatbot auto-scrolls correctly within nested Gradio containers

refactor: overhaul speech cleaning, deduplicate tool annotations, and update typewriter protocol to separate notes from response text

refactor: improve audio event handling with debouncing, fix VRM emotion persistence, and update tool annotation UI logic.

fix: adjust estimated duration multiplier for better timing accuracy

fix: adjust audio duration estimation multiplier to 0.07

refactor: unify avatar state management across thinking, speaking, and idle modes with improved event bridging and UI transitions.

feat: implement audio playback state bridge to synchronize iframe speaking status

Add text to slower speed

style: adjust right margin of aiko-chat-overlay to 96px

Edit message text

Please provide the specific changes made to `app.py` so I can generate an accurate summary for you.

refactor: update application entry point and configuration settings in app.py

feat: implement info modal overlay and refine shell layout styling

refactor: remove info panel styling from CSS and its corresponding initialization in app.py