feat: chat uploads, vision turn isolation, and MindSpace agent improvements

Add chat file/image upload UX, attachment proxying, vision thumbnails, and per-turn image scoping so agents only use the current upload. Extend MindSpace asset context, billing token state, OA/scenario verify scripts, and related runtime config. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-11 00:23:01 +08:00
parent e3063ea806
commit 32fb2cdeaf
51 changed files with 4588 additions and 186 deletions
@@ -0,0 +1,73 @@
+import sharp from 'sharp';
+
+export const VISION_THUMB_MAX_SIDE = 1280;
+export const VISION_THUMB_MAX_BYTES = 600 * 1024;
+export const VISION_THUMB_JPEG_QUALITY = 78;
+
+/**
+ * Build a smaller JPEG buffer for vision-model analysis only.
+ * Page generation still uses the full public standard image elsewhere.
+ */
+export async function buildVisionThumbnailBuffer(
+  buffer,
+  mimeType = 'image/jpeg',
+  {
+    maxSide = VISION_THUMB_MAX_SIDE,
+    maxBytes = VISION_THUMB_MAX_BYTES,
+    quality = VISION_THUMB_JPEG_QUALITY,
+  } = {},
+) {
+  if (!Buffer.isBuffer(buffer) || buffer.length === 0) {
+    throw new Error('vision thumb: empty buffer');
+  }
+
+  const metadata = await sharp(buffer, { sequentialRead: true }).metadata();
+  const width = Number(metadata.width ?? 0);
+  const height = Number(metadata.height ?? 0);
+  if (!width || !height) {
+    throw new Error('vision thumb: invalid dimensions');
+  }
+
+  const longest = Math.max(width, height);
+  const resizeWidth = longest > maxSide ? Math.max(1, Math.round((width * maxSide) / longest)) : null;
+  const resizeHeight = longest > maxSide ? Math.max(1, Math.round((height * maxSide) / longest)) : null;
+
+  let pipeline = sharp(buffer, { sequentialRead: true }).rotate();
+  if (resizeWidth && resizeHeight) {
+    pipeline = pipeline.resize({
+      width: resizeWidth,
+      height: resizeHeight,
+      fit: 'inside',
+      withoutEnlargement: true,
+    });
+  }
+
+  let nextQuality = quality;
+  let candidate = await pipeline
+    .flatten({ background: '#ffffff' })
+    .jpeg({ quality: nextQuality, mozjpeg: true })
+    .toBuffer();
+
+  while (candidate.length > maxBytes && nextQuality > 52) {
+    nextQuality = Math.max(52, nextQuality - 8);
+    candidate = await sharp(buffer, { sequentialRead: true })
+      .rotate()
+      .resize({
+        width: resizeWidth ?? width,
+        height: resizeHeight ?? height,
+        fit: 'inside',
+        withoutEnlargement: true,
+      })
+      .flatten({ background: '#ffffff' })
+      .jpeg({ quality: nextQuality, mozjpeg: true })
+      .toBuffer();
+  }
+
+  return candidate;
+}
+
+export const visionThumbInternals = {
+  VISION_THUMB_MAX_SIDE,
+  VISION_THUMB_MAX_BYTES,
+  VISION_THUMB_JPEG_QUALITY,
+};