Merge pull request #1003 from heygen-com/feat/capture-pipeline-improvements-v2

feat(capture): pipeline improvements — contact sheets, design styles, snapshot

Author: ukimsanov

packages/cli/package.json

@@ -38,7 +38,7 @@
     "postcss": "^8.5.8",
     "prettier": "^3.8.1",
     "puppeteer-core": "^24.39.1",
-    "sharp": "^0.34.0"
+    "sharp": "^0.34.5"
   },
   "devDependencies": {
     "@clack/prompts": "^1.1.0",

packages/cli/src/capture/agentPromptGenerator.ts

@@ -10,12 +10,35 @@
  * website-to-hyperframes skill — this file points agents there.
  */
 
-import { writeFileSync } from "node:fs";
+import { writeFileSync, readdirSync, existsSync } from "node:fs";
 import { join } from "node:path";
 import type { DesignTokens } from "./types.js";
 import type { AnimationCatalog } from "./animationCataloger.js";
 import type { CatalogedAsset } from "./assetCataloger.js";
 
+/**
+ * Infer a human-readable role hint from a hex color based on luminance and saturation.
+ * Not a substitute for DESIGN.md — just helps orient agents scanning the brand summary.
+ */
+function inferColorRole(hex: string): string {
+  const r = parseInt(hex.slice(1, 3), 16) / 255;
+  const g = parseInt(hex.slice(3, 5), 16) / 255;
+  const b = parseInt(hex.slice(5, 7), 16) / 255;
+  if (isNaN(r) || isNaN(g) || isNaN(b)) return "color";
+
+  const max = Math.max(r, g, b);
+  const min = Math.min(r, g, b);
+  const luminance = 0.2126 * r + 0.7152 * g + 0.0722 * b;
+  const saturation = max === 0 ? 0 : (max - min) / max;
+
+  if (luminance < 0.04) return "bg-dark";
+  if (luminance > 0.9) return "bg-light";
+  if (saturation > 0.4 && luminance > 0.05 && luminance < 0.7) return "accent";
+  if (luminance < 0.2) return "surface-dark";
+  if (luminance > 0.7) return "surface-light";
+  return "neutral";
+}
+
 export function generateAgentPrompt(
   outputDir: string,
   url: string,
@@ -25,25 +48,28 @@ export function generateAgentPrompt(
   hasLottie?: boolean,
   hasShaders?: boolean,
   _catalogedAssets?: CatalogedAsset[], // reserved for future asset inventory
-  detectedLibraries?: string[],
+  _detectedLibraries?: string[],
 ): void {
-  const prompt = buildPrompt(url, tokens, hasScreenshot, hasLottie, hasShaders, detectedLibraries);
+  const prompt = buildPrompt(outputDir, url, tokens, hasScreenshot, hasLottie, hasShaders);
   writeFileSync(join(outputDir, "AGENTS.md"), prompt, "utf-8");
   writeFileSync(join(outputDir, "CLAUDE.md"), prompt, "utf-8");
   writeFileSync(join(outputDir, ".cursorrules"), prompt, "utf-8");
 }
 
 function buildPrompt(
+  outputDir: string,
   url: string,
   tokens: DesignTokens,
   hasScreenshot: boolean,
   hasLottie?: boolean,
   hasShaders?: boolean,
-  detectedLibraries?: string[],
 ): string {
   const title = tokens.title || new URL(url).hostname.replace(/^www\./, "");
 
-  const colorSummary = tokens.colors.slice(0, 10).join(", ");
+  const colorSummary = tokens.colors
+    .slice(0, 10)
+    .map((hex) => `${hex} (${inferColorRole(hex)})`)
+    .join(", ");
   const fontSummary =
     tokens.fonts
       .map(
@@ -58,17 +84,66 @@ function buildPrompt(
       .join(", ") || "none detected";
 
   // Build the data inventory table rows
+  // Helper: find all contact sheet pages for a given base name. Matches the
+  // exact base file plus paginated variants only (e.g. `contact-sheet.jpg`,
+  // `contact-sheet-2.jpg`, `contact-sheet-3.jpg`). The "-NNN" suffix is digits
+  // only, so unrelated files that happen to share the prefix (notably the
+  // `contact-sheet-svgs.jpg` SVG fallback sheet in assets/) don't get mixed in.
+  function contactSheetRows(dir: string, baseFile: string, label: string): string[] {
+    const fullDir = join(outputDir, dir);
+    if (!existsSync(fullDir)) return [];
+    const baseName = baseFile.replace(/\.jpg$/, "");
+    // Escape regex metacharacters in baseName so future callers can pass
+    // filenames containing `.`, `+`, `(`, etc. without the regex breaking.
+    const escapedBase = baseName.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+    const paginatedRe = new RegExp(`^${escapedBase}(?:-(\\d+))?\\.jpg$`);
+    // Sort by the numeric page suffix so `contact-sheet-10.jpg` lands after
+    // `contact-sheet-2.jpg`, not before (default string sort orders them
+    // lexicographically and breaks at 10+ pages). Unpaginated `contact-sheet.jpg`
+    // gets page 0 so it sorts first if it co-exists with paginated files.
+    const all = readdirSync(fullDir)
+      .filter((f) => paginatedRe.test(f))
+      .map((f) => ({ name: f, page: parseInt(f.match(paginatedRe)?.[1] ?? "0", 10) }))
+      .sort((a, b) => a.page - b.page)
+      .map((entry) => entry.name);
+    if (all.length === 0) return [];
+    if (all.length === 1) {
+      return [`| \`${dir}/${all[0]}\` | ${label} |`];
+    }
+    return all.map((f, i) => `| \`${dir}/${f}\` | ${label} — page ${i + 1} of ${all.length} |`);
+  }
+
   const tableRows: string[] = [];
   if (hasScreenshot) {
+    const screenshotRows = contactSheetRows(
+      "screenshots",
+      "contact-sheet.jpg",
+      "**View this first.** All scroll screenshots in labeled grid — see the entire page at a glance",
+    );
+    if (screenshotRows.length > 0) {
+      tableRows.push(...screenshotRows);
+    } else {
+      tableRows.push(
+        "| `screenshots/contact-sheet.jpg` | **View this first.** All scroll screenshots in one labeled grid. |",
+      );
+    }
     tableRows.push(
-      "| `screenshots/scroll-*.png` | Viewport screenshots of the full page. Start with `scroll-000.png` (hero). |",
+      "| `screenshots/scroll-*.png` | Individual viewport screenshots if you need detail on a specific section. |",
     );
   }
   tableRows.push(
-    "| `extracted/asset-descriptions.md` | One-line description of every downloaded asset. **Read this first.** |",
+    `| \`extracted/tokens.json\` | Design tokens: ${tokens.colors.length} colors, ${tokens.fonts.length} fonts, ${tokens.headings?.length ?? 0} headings, ${tokens.ctas?.length ?? 0} CTAs |`,
   );
+  // design-styles.json is written from a try/catch in capture/index.ts and
+  // gets skipped when the live-DOM style extraction fails. Only list it in the
+  // agent prompt when it actually exists, so the agent isn't pointed at a 404.
+  if (existsSync(join(outputDir, "extracted", "design-styles.json"))) {
+    tableRows.push(
+      "| `extracted/design-styles.json` | Computed styles from live DOM: typography hierarchy, button/card/nav styles, spacing scale, border-radius, box shadows. Primary data source for DESIGN.md. |",
+    );
+  }
   tableRows.push(
-    `| \`extracted/tokens.json\` | Design tokens: ${tokens.colors.length} colors, ${tokens.fonts.length} fonts, ${tokens.headings?.length ?? 0} headings, ${tokens.ctas?.length ?? 0} CTAs |`,
+    "| `extracted/asset-descriptions.md` | One-line description of every downloaded asset. Read this for asset selection — only open individual files for safe-zone checking. |",
   );
   tableRows.push(
     "| `extracted/visible-text.txt` | Page text in DOM order, prefixed with HTML tag (`[h1]`, `[p]`, `[a]`). Use as context — rephrase freely. |",
@@ -81,20 +156,41 @@ function buildPrompt(
   if (hasShaders) {
     tableRows.push("| `extracted/shaders.json` | WebGL shader source (GLSL). |");
   }
-  if (detectedLibraries && detectedLibraries.length > 0) {
-    tableRows.push(
-      `| \`extracted/detected-libraries.json\` | Libraries: ${detectedLibraries.join(", ")} |`,
-    );
+
+  // Asset contact sheets — dynamically list all pages
+  const assetSheetRows = contactSheetRows(
+    "assets",
+    "contact-sheet.jpg",
+    "Downloaded images in labeled grid — view before opening individual files",
+  );
+  if (assetSheetRows.length > 0) {
+    tableRows.push(...assetSheetRows);
+  } else {
+    tableRows.push("| `assets/contact-sheet.jpg` | All downloaded images in one labeled grid. |");
   }
-  tableRows.push("| `assets/` | Downloaded images, SVGs, and font files. |");
+
+  // SVG contact sheets — check both assets/svgs/ and assets/ root fallback
+  const svgSubdirRows = contactSheetRows(
+    "assets/svgs",
+    "contact-sheet.jpg",
+    "SVGs rendered as thumbnails in labeled grid",
+  );
+  const svgRootRows = contactSheetRows(
+    "assets",
+    "contact-sheet-svgs.jpg",
+    "SVGs rendered as thumbnails in labeled grid",
+  );
+  const svgRows = svgSubdirRows.length > 0 ? svgSubdirRows : svgRootRows;
+  if (svgRows.length > 0) {
+    tableRows.push(...svgRows);
+  }
+
+  tableRows.push("| `assets/` | Individual downloaded images, SVGs, and font files. |");
 
   // Brand summary — just the essentials
   const brandLines: string[] = [];
   brandLines.push(`- **Colors**: ${colorSummary || "see tokens.json"}`);
   brandLines.push(`- **Fonts**: ${fontSummary}`);
-  if (detectedLibraries && detectedLibraries.length > 0) {
-    brandLines.push(`- **Built with**: ${detectedLibraries.join(", ")}`);
-  }
 
   return `# ${title}
 

packages/cli/src/capture/assetDownloader.ts

@@ -24,11 +24,21 @@ export async function downloadAssets(
 
   // 1. ALL inline SVGs — save as files (logos get priority naming)
   mkdirSync(join(outputDir, "assets", "svgs"), { recursive: true });
+  const usedSvgNames = new Set<string>();
   for (let i = 0; i < tokens.svgs.length && i < 30; i++) {
     const svg = tokens.svgs[i]!;
     if (!svg.outerHTML || svg.outerHTML.length < 50) continue;
     const label = svg.label?.replace(/[^a-zA-Z0-9-_ ]/g, "").trim();
-    const name = label ? slugify(label) + ".svg" : svg.isLogo ? `logo-${i}.svg` : `icon-${i}.svg`;
+    let slug = label ? slugify(label) : svg.isLogo ? `logo-${i}` : `icon-${i}`;
+    // Deduplicate — two SVGs with same aria-label get suffixed
+    let finalSlug = slug;
+    let suffix = 2;
+    while (usedSvgNames.has(finalSlug)) {
+      finalSlug = `${slug}-${suffix}`;
+      suffix++;
+    }
+    usedSvgNames.add(finalSlug);
+    const name = `${finalSlug}.svg`;
     const localPath = `assets/svgs/${name}`;
     try {
       writeFileSync(join(outputDir, localPath), svg.outerHTML, "utf-8");
@@ -86,55 +96,49 @@ export async function downloadAssets(
     }
   }
 
-  // Download all images (no arbitrary cap) — Claude Code needs to see every asset to use them creatively.
-  // The 10KB minimum size filter handles tracking pixels and tiny icons.
+  // Download all images — use catalog context for human-readable filenames.
   // Pre-filter to deduplicate before downloading.
-  const toDownload: { url: string; isPoster: boolean; normalized: string }[] = [];
+  const toDownload: {
+    url: string;
+    isPoster: boolean;
+    normalized: string;
+    catalog?: CatalogedAsset;
+  }[] = [];
   for (const { url, isPoster } of imageUrls) {
     const normalized = normalizeUrl(url);
     if (downloadedUrls.has(normalized)) continue;
-    downloadedUrls.add(normalized); // Reserve to prevent duplicates in parallel batches
-    toDownload.push({ url, isPoster, normalized });
+    downloadedUrls.add(normalized);
+    const catalog = catalogedAssets?.find((a) => normalizeUrl(a.url) === normalized);
+    toDownload.push({ url, isPoster, normalized, catalog });
   }
 
   // Download in parallel batches of 5
   const BATCH_SIZE = 5;
   let imgIdx = 0;
+  const usedNames = new Set<string>();
   for (let i = 0; i < toDownload.length; i += BATCH_SIZE) {
     const batch = toDownload.slice(i, i + BATCH_SIZE);
     const results = await Promise.allSettled(
-      batch.map(async ({ url, isPoster }) => {
+      batch.map(async ({ url, isPoster, catalog }) => {
         const parsedUrl = new URL(url);
         const pathExt = extname(parsedUrl.pathname);
         const ext = pathExt && pathExt.length <= 5 ? pathExt : ".jpg";
         const buffer = await fetchBuffer(url);
         if (!buffer) return null;
-        // SVGs are inherently small — don't apply the 10KB minimum to them
         const isSvg = ext === ".svg" || url.includes(".svg");
         const minSize = isSvg ? 200 : 10000;
         if (buffer.length < minSize) return null;
-        return { url, isPoster, parsedUrl, ext, buffer };
+        return { url, isPoster, parsedUrl, ext, buffer, catalog };
       }),
     );
     for (const result of results) {
       if (result.status !== "fulfilled" || !result.value) continue;
-      const { url, isPoster, parsedUrl, ext, buffer } = result.value;
+      const { url, isPoster, parsedUrl, ext, buffer, catalog } = result.value;
       try {
-        const prefix = isPoster ? "poster" : "image";
-        const rawName =
-          parsedUrl.pathname
-            .split("/")
-            .pop()
-            ?.replace(/\.[^.]+$/, "") || "";
-        const isMeaningful =
-          rawName.length > 2 &&
-          rawName.length < 50 &&
-          !/^[a-f0-9]{8,}$/i.test(rawName) &&
-          !/^\d+$/.test(rawName) &&
-          !rawName.includes("_next") &&
-          !rawName.includes("?");
-        const slug = isMeaningful ? slugify(rawName) : `${prefix}-${imgIdx}`;
+        // Generate human-readable name from catalog context
+        const slug = deriveAssetName(parsedUrl, catalog, isPoster, imgIdx, usedNames);
         const name = `${slug}${ext}`;
+        usedNames.add(slug);
         const localPath = `assets/${name}`;
         writeFileSync(join(outputDir, localPath), buffer);
         assets.push({ url, localPath, type: "image" });
@@ -303,3 +307,77 @@ function slugify(text: string): string {
     .replace(/^-|-$/g, "")
     .slice(0, 40);
 }
+
+/**
+ * Derive a human-readable filename from catalog context.
+ * Priority: alt text > nearest heading > meaningful URL path > fallback index.
+ */
+function deriveAssetName(
+  parsedUrl: URL,
+  catalog: CatalogedAsset | undefined,
+  isPoster: boolean,
+  idx: number,
+  usedNames: Set<string>,
+): string {
+  const candidates: string[] = [];
+
+  // 1. Alt text / description from catalog
+  if (catalog?.description) {
+    const desc = catalog.description.replace(/[^a-zA-Z0-9 -]/g, "").trim();
+    if (desc.length > 3 && desc.length < 80) candidates.push(desc);
+  }
+
+  // 2. Nearest heading context
+  if (catalog?.nearestHeading) {
+    const heading = catalog.nearestHeading.replace(/[^a-zA-Z0-9 -]/g, "").trim();
+    if (heading.length > 3 && heading.length < 60) candidates.push(heading);
+  }
+
+  // 3. Meaningful URL path segment
+  const rawName =
+    parsedUrl.pathname
+      .split("/")
+      .pop()
+      ?.replace(/\.[^.]+$/, "") || "";
+  const isMeaningful =
+    rawName.length > 2 &&
+    rawName.length < 50 &&
+    !/^[a-f0-9]{8,}$/i.test(rawName) &&
+    !/^\d+$/.test(rawName) &&
+    !rawName.includes("_next") &&
+    !rawName.includes("?");
+  if (isMeaningful) candidates.push(rawName);
+
+  // 4. Section classes as context
+  if (catalog?.sectionClasses) {
+    const classes = catalog.sectionClasses
+      .split(/\s+/)
+      .filter((c) => c.length > 3 && c.length < 30 && !/^(w-|h-|p-|m-|flex|grid|block)/.test(c))
+      .slice(0, 2)
+      .join("-");
+    if (classes.length > 3) candidates.push(classes);
+  }
+
+  // Pick the best candidate
+  const prefix = isPoster ? "poster" : catalog?.aboveFold ? "hero" : "image";
+  let slug = "";
+
+  for (const c of candidates) {
+    slug = slugify(c);
+    if (slug.length > 3 && !usedNames.has(slug)) break;
+  }
+
+  if (!slug || slug.length <= 3 || usedNames.has(slug)) {
+    slug = `${prefix}-${idx}`;
+  }
+
+  // Deduplicate
+  let final = slug;
+  let suffix = 2;
+  while (usedNames.has(final)) {
+    final = `${slug}-${suffix}`;
+    suffix++;
+  }
+
+  return final;
+}