feat: AI job filter — score jobs 0-10 with Claude Haiku before applying

- lib/filter.mjs: batch scoring engine (10 jobs/call, Claude Haiku)
- job_filter.mjs: standalone CLI with --dry-run and --stats flags
- Threshold configurable globally + per-search in search_config.json (filter_min_score, default 5)
- Job profiles (gtm/ae) passed as context via settings.filter.job_profiles
- Filtered jobs get status='filtered' with filter_score + filter_reason
- Filter errors pass jobs through (never block applications)
- status.mjs: added 'AI filtered' line to report

status.mjs

@@ -111,6 +111,7 @@ function buildStatus() {
     queue: {
       total: queue.length,
       new: byStatus['new'] || 0,
+      filtered: byStatus['filtered'] || 0,
       applied: byStatus['applied'] || 0,
       failed: byStatus['failed'] || 0,
       needs_answer: byStatus['needs_answer'] || 0,
@@ -209,6 +210,7 @@ function formatReport(s) {
   }
 
   lines.push(
+    `  🚫 AI filtered:         ${q.filtered || 0}`,
     `  ✅ Applied:             ${q.applied}`,
     `  🔁 Already applied:     ${q.already_applied || 0}`,
     `  💬 Needs your answer:   ${q.needs_answer}`,