rspace-online/backlog/tasks/task-4 - Phase-3-AI-Integration-Shapes.md

id	title	status	assignee	created_date	labels	dependencies	priority
task-4	Phase 3: AI Integration Shapes	To Do		2026-01-02 15:54	migration shapes ai		medium

Description

Port AI-powered shapes using existing MCP servers and APIs:

1. folk-image-gen - Image generation (fal.ai Flux)

   • Prompt input, image history thread
   • Loading states, error handling
   • Uses: mcp__fal-ai__fal_generate_image

2. folk-video-gen - Video generation (WAN 2.1)

   • Image-to-video, text-to-video
   • Duration control, queue polling
   • Uses: mcp__fal-ai__fal_generate_video

3. folk-prompt - LLM prompt executor

   • Agent binding, multiple personalities
   • Output streaming
   • Uses: mcp__gemini__gemini_generate or direct Anthropic API

4. folk-transcription - Audio transcription (Whisper)

   • Real-time transcription, pause/resume
   • Speaker diarization
   • Uses: Web Speech API fallback + Whisper API

Simplifications:

• Use MCP tools directly instead of custom API clients
• Simplify loading states to CSS classes
• Remove complex React hooks, use async/await patterns

Acceptance Criteria

• #1 folk-image-gen with fal.ai integration
• #2 folk-video-gen with video generation
• #3 folk-prompt with LLM streaming
• #4 folk-transcription with Whisper