Update hackathon submission docs and app files

feat: add privacy filtering and execution modes

fix: parse qwen thinking json output

fix: enable qwen thinking with larger token budget

fix: improve qwen json generation

fix: support batch-encoded model inputs

fix: harden codebook and model fallback UX

feat: serve designer React frontend via gradio.Server on ZeroGPU

feat: improve qwen zerogpu ux

feat: improve qwen zerogpu ux

feat: enable oauth-backed model assist

feat: add small model assisted analysis

feat: implement trace field notes mvp