fix(docs): extract only main content from API HTML to reduce redundancy

- Extract only <main> element content, skipping sidebar navigation
- Remove breadcrumb div to avoid repeated navigation paths
- Reduces llms-full.txt from ~3.7MB to ~2.4MB with cleaner content

Co-Authored-By: Claude Opus 4.5 <[email protected]>

Author: critesjosh

docs/scripts/append_api_docs_to_llms.js

@@ -35,10 +35,17 @@ const API_DIRS = [
 
 /**
  * Extract text content from HTML, stripping tags and normalizing whitespace.
+ * Only extracts content from <main> element to avoid redundant navigation.
  */
 function htmlToText(html) {
+  // Extract only the <main> content to avoid sidebar/navigation redundancy
+  const mainMatch = html.match(/<main[^>]*>([\s\S]*?)<\/main>/i);
+  const content = mainMatch ? mainMatch[1] : html;
+
   return (
-    html
+    content
+      // Remove the breadcrumb div (first div with navigation links)
+      .replace(/<div><a[^>]*>aztec-nr<\/a>[\s\S]*?<\/div>/i, "")
       // Remove script and style elements entirely
       .replace(/<script[^>]*>[\s\S]*?<\/script>/gi, "")
       .replace(/<style[^>]*>[\s\S]*?<\/style>/gi, "")