generate_3d: 3D models with fal.ai (image, text, or image steered by text)

- New tool: image-to-3D (project file or an image attached to the chat,
  optional back/left/right views) or text-to-3D; image + prompt refines the
  image with the prompt first (the 3D models take no text with an image).
  Styles textured / geometry / lowpoly, optional PBR, face count. Runs through
  fal.ai's queue API with progress, saves GLB + preview, books the cost
  (published prices, overridable per model). Request bodies for the Hunyuan3D,
  Tripo and Trellis families; defaults [images] model_3d / model_3d_text.
- Chat card: "Open in the 3D view"; media overview: kind "model" (also
  STL/3MF/OBJ written by agents) with previews.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

web/src/whatsnew.ts

@@ -3,6 +3,10 @@
  * under "unreleased"; scripts/release.sh renames the key to the release version.
  */
 export const WHATS_NEW: Record<string, { en: string[]; de: string[] }> = {
+  unreleased: {
+    en: ["3D models with fal.ai: from an image (also pasted into the chat), a text prompt or both – open them in the 3D view"],
+    de: ["3D-Modelle mit fal.ai: aus einem Bild (auch eingefügt), einem Text oder beidem – öffnen in der 3D-Ansicht"],
+  },
   "202611-00023": {
     en: ["Tokens and cost under every answer; the total cost of chats with opencode Go is shown correctly again"],
     de: ["Tokens und Kosten unter jeder Antwort; der Gesamtpreis von Chats mit opencode Go stimmt wieder"],