feat: add metadata extraction and synthetic keyword detection for images and videos

feat: update frontend to proxy requests to Hugging Face Space API and configure environment variables

fix: add PYTHONPATH environment variable and ensure src is importable in app.py

refactor: clean up model roster comments and remove broken model references

fix: update Dockerfile dependencies, remove audio processing, and replace models

feat: enhance model capabilities and update dependencies

Use CPU-only PyTorch wheels in Docker build for HF Space stability

Refresh Gemini candidate order to current Gemini 3 model codes

Update model stack, add audio stream extraction, and harden inference wiring

fix(space): set PYTHONPATH and prefer Gemini 3.1 with 2.5 fallback

fix(docker): replace removed libgl1-mesa-glx with libgl1

fix(space): correct HF frontmatter emoji

Initial commit

initial commit