final: add loading indicator and force direct URL for perfect mobile compatibility

fix: use direct space URL and mobile user agent to fix persistent white screen

fix: resolve mobile white screen by ensuring JS is enabled and using stable embed URL

fix: update decommissioned Groq model to llama-3.3-70b-versatile

feat: switch AI backend to Groq for ultra-fast medical responses

fix: explicit model ID for Gemini 1.5 Flash

fix: switch to Gemini 1.5 Flash for higher rate limits and add error handling

fix: simplify app to single server and self-contained manifest to fix port conflict

fix: disable example caching and use messages type to resolve HF port conflict

refactor: update to modern google-genai library and fix deprecation warnings

fix: pin both gradio and huggingface_hub to resolve import error

fix: pin gradio version to resolve huggingface_hub import error

fix: add missing dependencies for FastAPI and PWA support

fix: use stable embed URL and enable JS to fix blank screen

fix: update APK upload path to recursive search

fix: force yes to all prompts in cloud build

fix: add --yes flag to handle interactive prompts in CI

fix: restore flutter and java setup in workflow

feat: add cloud build for Android APK

feat: add PWA support and medical icons

Update app with full PWA functionality

Robust deployment: lazy data loading and package structure

Fix Hugging Face color validation: slate -> indigo

Fix configuration for Hugging Face Spaces

Add Hugging Face Space metadata to README

Update for Hugging Face Spaces deployment

Switch to Gemini 3 Flash model

Update repo name to mediagent in README

Fix Gradio 6.0 compatibility and theme placement

Initial commit: Medical AI Agent with Gemini and OpenMed datasets