[LocalMode] Streaming grounded RAG over its OWN text/PDF corpus — token-by-token answers through the engine-owned generator (granite-4.0-350M) with [n] markers upgraded to hover-card inline citations resolved to retrieved sources (PDF page attribution + similarity), wall-clock duration, and cancel — carrying th
pnpm dlx shadcn@latest add "https://registry.directory/r/localmode-ai/ui/blocks/knowledge/rag-chat.json"