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/styles.css

@@ -4410,3 +4410,32 @@ span.chat-tab > button {
   color: var(--muted);
   font-variant-numeric: tabular-nums;
 }
+
+.media-badge {
+  position: absolute;
+  top: 6px;
+  left: 6px;
+  font-size: 11px;
+  font-weight: 600;
+  padding: 1px 6px;
+  border-radius: 4px;
+  background: var(--bg0);
+  color: var(--accent);
+}
+.media-model {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 12px;
+  max-height: 100%;
+}
+.media-model img {
+  max-height: calc(100% - 50px);
+  max-width: 100%;
+  object-fit: contain;
+}
+.media-model > .icon {
+  width: 64px;
+  height: 64px;
+  color: var(--accent);
+}