Fix zero-config demo: default profile groq_cloud + Gemini image keyless fallback

Make demo deployable on Hugging Face Spaces + add local/Groq/demo onboarding

feat: BYOK modal - visitors enter their own Groq key, stored in sessionStorage, auto-deleted on tab close

feat: add groq_cloud profile with Groq LLM + Pollinations image generation (fully free, no credits)

feat: add profiles.py control panel and Gemini backend for prompt expansion and image generation

fix: restore FLUX.1-schnell and Qwen2.5 LLM configurations in local config

fix: update to supported models (zephyr-7b-beta and stable-diffusion-v1-5)

fix: update model IDs to avoid credit depletion and chat model errors

docs: rewrite REPORT.md with details of the developer journey and hardware pivots

fix: relocate frontend build assets to static/ folder to avoid FastAPI /assets conflict

fix: upgrade frontend builder base image to node:20-slim

docs: add HF space config card metadata to README

feat: initial release of Multiverse AI Studio