LLM song-tweak: AI Gateway via Vercel AI SDK, budgeted tune flow

Add a ✨ tune button that lets an LLM inspect the proposed
visualization and tweak the proc-song knobs so the next generation
looks better. Edits only the 7 songbank params (bpm, brightness,
noise, noiseColour, dynamics, transition, arrangement) — never the
Look — then re-synthesizes and re-generates locally for preview.

- ai + @ai-sdk/openai + zod (library per plan) against the Vercel AI
  Gateway (OpenAI-compatible, configurable via
  VITE_AI_GATEWAY_URL/MODEL/API_KEY, localStorage override,
  .env.example).
- Structured output (TweakResultSchema) + clampEdits enforces ranges;
  prompt ≤ ~2.5k tokens, max 2-3 knobs ±0.15 / bpm ±8.
- Budget caps: 3/load + 10/session (sessionStorage), checked before
  network, NO_EDITS refunded, offline/auth/rate-limit mapped.
- Prompt split into src/llm/spec.js (pure, node-testable) + llmTweak.js
  (gateway + digest) to keep `node --test` off the Vite JSON path.
- UI: ⚙️ gateway/model/key dialog (localStorage flow-state:llm),
  confirm(prompt) with hint, diff modal with Apply/Dismiss; Apply
  synthesizes → FeatureTrack → generateLook → Show.useTrack.
- Tests: 7 new LLM cases (clamp, schema, prompt, budget), 18/18 pass.
  Build + lint:scenes green.

Co-Authored-By: Claude <noreply@anthropic.com>

flow-state/.env.example

@@ -0,0 +1,5 @@
+# Vercel AI Gateway — copy to .env.local and fill VITE_AI_API_KEY
+# Get a token at https://vercel.com/dashboard/ai-gateway
+VITE_AI_GATEWAY_URL=https://ai-gateway.vercel.sh/v1
+VITE_AI_MODEL=openai/gpt-4o-mini
+VITE_AI_API_KEY=