feat(ui): Record-sign tab — multi-frame burst capture for full ASL words

feat(backend): /recognize accepts frames list + body-size cap

feat(vlm): add recognize_sign_from_frames for multi-image VLM input

feat(prompts): NVIDIA-pattern single-frame + multi-frame VLM prompts

refactor: extract closed vocabulary into signbridge.vocab module

feat: SignBridge initial scaffold + tests