fix(portals): depth-track div extraction so nested job descriptions aren't truncated (#204)

The jobindex and linkedin detail parsers matched description containers with a non-greedy regex that stops at the first inner </div>, so any posting whose description contains nested divs was silently truncated (jobindex dropped later sections; linkedin dropped everything after the first block). Replaces the regex with a depth-tracked extractDivContent scanner that walks div open/close markers to the matching close. Verified: truncation bug reproduced against real markup fixtures, depth arithmetic correct (no off-by-one/infinite-loop), 28 tests pass network-free, no regression on non-nested divs. Malformed-HTML over-grabs rather than truncates - the safer failure, cleaned by downstream stripTags/decode.

By @oscarbol09.

.agents/skills/jobindex-search/cli/src/commands/detail.ts

@@ -1,6 +1,6 @@
 import { defineCommand, option } from "@bunli/core"
 import { z } from "zod"
-import { htmlFetch, writeError } from "../helpers.js"
+import { htmlFetch, writeError, extractDivContent } from "../helpers.js"
 
 const BASE_URL = "https://www.jobindex.dk"
 
@@ -180,9 +180,9 @@ function parseDetailPage(html: string, url: string, id: string): DetailResult {
   let description: string | null = null
 
   // Try job-text class first
-  const jobTextMatch = html.match(/class="job-text"[^>]*>([\s\S]*?)<\/div>\s*(?:<div|<\/div>)/i)
-  if (jobTextMatch) {
-    description = decodeHtmlEntities(stripTags(jobTextMatch[1])).replace(/\s+/g, " ").trim() || null
+  const jobTextHtml = extractDivContent(html, "job-text")
+  if (jobTextHtml) {
+    description = decodeHtmlEntities(stripTags(jobTextHtml)).replace(/\s+/g, " ").trim() || null
   }
 
   // Fallback: try og:description meta tag for a brief description

.agents/skills/jobindex-search/cli/src/helpers.ts

@@ -307,6 +307,33 @@ export function parseJobCards(html: string): JobCard[] {
   return results
 }
 
+export function extractDivContent(html: string, className: string): string | null {
+  const escaped = className.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')
+  const openRe = new RegExp(`<div[^>]*class="[^"]*${escaped}[^"]*"[^>]*>`, 'i')
+  const open = openRe.exec(html)
+  if (!open) return null
+
+  let i = open.index + open[0].length
+  let depth = 1
+
+  while (depth > 0 && i < html.length) {
+    const nextOpen = html.indexOf('<div', i)
+    const nextClose = html.indexOf('</div>', i)
+
+    if (nextClose === -1) return null
+
+    if (nextOpen !== -1 && nextOpen < nextClose) {
+      depth++
+      i = nextOpen + 4
+    } else {
+      depth--
+      i = nextClose + 6
+    }
+  }
+
+  return html.slice(open.index + open[0].length, i - 6)
+}
+
 export function parseHitCount(html: string): number {
   const match = html.match(/af <strong>([\d.]+)<\/strong>/)
   if (!match) return 0