fix: animation replay + chat uses vision model

fix: SVG animation replaces Canvas+JS (Gradio strips scripts)

fix: Gradio 6.0 compatibility for Chatbot and theme/css

feat: add chatbot & 2D accident animation tabs

feat: add new metrics for accident severity and geographic location

feat: upgrade to LiquidAI/LFM2-VL-3B for balanced inference

fix: switch to Qwen2-VL-7B-Instruct (open model)

feat: upgrade model to Llama-3.2-11B-Vision-Instruct

fix: update parser for new Vehicle 1 format

feat: add time, road type, and detailed vehicle positioning to LFM prompt

fix: add strict format constraints to LFM prompt

feat: update LFM prompt and parser to reproduce static UI format

feat: add api_name to all handlers + JSON API endpoints for custom frontend

fix: use demo.launch() as primary entry point for ZeroGPU detection

fix: wire @spaces.GPU to Gradio event handler for ZeroGPU detection

fix: move @spaces.GPU to top-level of app.py for ZeroGPU detection

refactor: switch to Gradio ZeroGPU with custom frontend + REST API

Simplify sidebar: 'Built by' with LinkedIn only, remove phone placeholder

Apply UI changes to alt_index.html (root landing page)

Move Founder & Contact to sidebar as collapsible widgets

UI update: new header, founder section, contact section

Add automatic lifespan DB fix for persistent volume staleness

Add placeholder image, fix JS loop, sync final DB state

Implement direct static mounted routing for images via FastAPI

Fix frontend photo URL concatenation

Fix photo rendering with robust relative path resolution

Add missing AI dependencies for Vision Model

Update image paths and add /api/logs

Initial MVP deployment with baked-in data

initial commit