Update ui/css.py

refactor: adjust mouth clamping, jaw rotation, and viseme mappings while removing redundant mesh double-sided rendering logic

fix: mitigate VRM chin mesh artifacts by clamping mouth weight, adjusting jaw rotation, forcing double-sided rendering, and refining viseme defaults

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

style: decrease max-height of aiko-info-card to 74vh

fix: reduce max-height of info card to 76vh to prevent overflow

style: increase max-height of aiko-info-card to 80vh

style: reduce max-height of aiko-info-card to 72vh

style: increase maximum width of aiko-info-card to 160vw

style: increase max width of aiko-info-card to 600px

fix: increase max-height of info card to 90vh to improve content visibility

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

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

refactor: standardize ASR endpoint to /transcribe and update MiniCPM-V dependency and video decoding logic

feat: migrate ASR backend to Modal Nemotron endpoint with language support

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

feat: implement parallel multi-chunk synthesis and WAV concatenation for long TTS responses

refactor: increase llama context window, remove redundant output format parameter, and add error logging to MioTTS requests

docs: fix whitespace and formatting in listen.py module docstring

fix: escape raw string for VRM UI and correct module import path for ASR functionality

fix: improve markdown cleanup by stripping bold tags, bullet points, and horizontal rules

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

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

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.

refactor: remove unused _interpqueues import from vrm module

fix: prevent premature status reset and preserve existing expressions during UI state transitions

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

style: adjust aiko-chat-overlay positioning and increase send button margin

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

style: increase top and right margins for chat overlay positioning

style: increase right margin of flex container to 24px

style: uncomment status container styles in VRM UI

feat: implement info modal overlay and refine shell layout styling

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

style: comment out status element in vrm UI stylesheet

Delay typewriter

style: update UI layout for status indicators and info panel dimensions

feat: expand layout constraints and introduce styled information panel for improved UI responsiveness

refactor: standardize input layout styles and fix CSS overrides for chatbot components

style: adjust chat window bottom spacing and width proportions

style: update aiko-input-row layout parameters and z-index

refactor: replace character-based clip-path reveal with sentence-by-sentence text animation and enhance TTS text cleaning.

chore: update default MIOTTS preset to Aiko and adjust input row right margin positioning

fix: adjust input row right offset to prevent send button overflow

chore: update input row spacing and change default MioTTS preset to Asuka

chore: adjust camera and orbit control focus position for better alignment