style(ui): add parent-friendly theme selector

chore: remove dead modal_app_gemma.py, gitignore working artifacts

feat(asr): add optional Nemotron voice-note input

chore(modal): drop warmup ping, document cold-start trade-off

perf(modal): bump per-server max_model_len to 8k/4k

perf(agent,modal): aggressive summarization + per-server max_model_len

perf(modal): bake weights, eager-load, drop max-model-len, AOT cache

perf(modal): cold-start on demand with eager-mode and warmup ping

Fabella Phase 3: chat UI, HF Auth, bucket JSON history

Fabella Phase 2: add read aloud and redesign frontend

Fabella Phase 1: Gradio app with mock + real model paths