2 Commits

Author	SHA1	Message	Date
yuanzonghao	9cedfa66e4	feat: prefetch, vision split, provider adapter, UI polish ... Engine - Split /api/vision out from /api/interact so client can drive prefetch + cache lookup independently of click interpretation - Image client switched to chat-completions+modalities API (OpenRouter/ provider style), supporting markdown image URL responses - annotateClick now resizes to 768w before composite to keep vision payloads small and avoid CDN timeouts - Prompts updated to mention "JSON" in user messages (required by Gemini's strict JSON mode) - Shared fetchWithRetry helper: 2 retries for chat/image, 0 for vision (with 60s hard timeout) Client - Parallel prefetch of all three choice branches on each new frame - Effect deliberately excludes phase from deps so user-click doesn't abort in-flight prefetches - Cache hit/miss/free-form fallback handled in handleClick - PlayCanvas reads img naturalWidth/Height and adapts container to whatever aspect AI returns (no more cropped third choice) - max-width raised to 560px, max-height calc(100dvh - 200px) Misc - README env-path corrected to apps/web/.env.local - users.md: BGM/TTS idea note - .env.example moved into apps/web alongside next config Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-12 19:38:03 +08:00
yuanzonghao	cbd95bbea2	Initial commit: AI-driven visual novel scaffold ... - Monorepo (pnpm workspace): apps/web + packages/{types,ai-client,engine} - Next.js 16 web app with three-stage AI orchestration - Three independently configurable providers: text LLM, image generator, vision model - Warm minimalist editorial UI design - One-click Vercel deploy ready Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-09 13:29:58 +08:00