Implement hybrid approach for AI news

- Update ainews script to detect OpenAI URLs and mark as NEEDS_WEB_FETCH
- Update TOOLS.md with content availability table and hybrid workflow
- Update all 4 AI news cron jobs (10:05, 14:05, 18:05, 22:05) with hybrid instructions
  - Simon/Raschka: use ainews articles (fivefilters works)
  - OpenAI: use web_fetch tool (JS-heavy site)

bin/ainews

@@ -20,8 +20,12 @@ Commands:
   items --all [max]        All items including seen
   article <url>            Fetch article content via fivefilters proxy
   articles <url1,url2,...> Fetch multiple articles + mark as seen
+                           (OpenAI URLs print NEEDS_WEB_FETCH - use web_fetch tool)
   seen                     Show seen count and recent entries
   reset                    Clear seen history
+
+Note: OpenAI's site is JS-rendered, fivefilters can't extract it.
+      For OpenAI articles, use the web_fetch tool directly.
 EOF
 }
 
@@ -122,7 +126,13 @@ case "${1:-}" in
     for url in "${URLS[@]}"; do
       title=$(echo "$url" | grep -oP '[^/]+$' | sed 's/-/ /g; s/\..*//; s/.*/\u&/')
       echo "=== ${title} ==="
-      fetch_single_article "$url"
+      # OpenAI is JS-heavy, fivefilters can't extract it - needs web_fetch tool
+      if [[ "$url" == *"openai.com"* ]]; then
+        echo "NEEDS_WEB_FETCH: $url"
+        echo "(OpenAI's site is JS-rendered - use web_fetch tool instead)"
+      else
+        fetch_single_article "$url"
+      fi
       echo ""
       echo ""
       mark_seen "$url"