Fix AMP deprecation warnings

Detect ZeroGPU from Spaces environment

Force local ZeroGPU inference path on Space

Suppress asyncio fd shutdown noise in Space logs

Remove prelaunch asyncio loop from Space entrypoint

Register CORS before Gradio app startup

Use Blocks launch entrypoint for Space runtime

Align pydantic pin with Gradio 6

Use Gradio Server mode for Space entrypoint

Disable Gradio SSR on Space mount

Avoid Gradio node port collision on Spaces

Fix Gradio entrypoint and switch explainability to Gemini

Serve frontend API routes via Gradio Server

Let Hugging Face set Gradio server port

Use Gradio launch on Hugging Face Space

Mount Gradio app at Space root

Fix ZeroGPU model loading lifecycle

Fix ZeroGPU startup and local GPU inference path

Mount FastAPI routes into Gradio space app

Pin huggingface-hub below v1 for Gradio compatibility

Prepare Hugging Face Space deployment

Lazy load SSTGNN optional dependencies

Keep Space alive when model weights are unavailable

Implement ZeroGPU Space runtime

fix gradio video input for hf runtime

lazy-load gradio modules for hf startup

switch hf space to gradio sdk

align project with CLAUDE spec and hf space deploy

feat(fingerprint): improve CLIP attribution accuracy and add 4th detector

fix(video): cap frames at 60, pass tmp_path to coherence, keep temp alive through inference

feat: update generator labels and enhance detection response structure

feat: Enhance generator detection and attribution mechanisms

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