# WormGPT Robots.txt
# Last Updated: 2026-05-27
# Version: 4.1.0 - Allow crawling so noindex tags can be seen

User-agent: *
Allow: /

# Block only truly private/admin areas. App routes that should not be indexed
# (e.g. /chat, /agent-ide, /api, /profile, /payment-*, /dashboard, /admin,
# /training, /discount-pricing) are served with an X-Robots-Tag: noindex
# header — Google MUST be able to crawl them to see that tag, otherwise they
# get reported as "Indexed, though blocked by robots.txt".
Disallow: /admin
Disallow: /investors

# Block query parameter variants (but not the base paths)
Disallow: /*?lang=
Disallow: /*?mode=
Disallow: /*?ref=
Disallow: /*?utm_

# Block legacy static HTML duplicates (handled by Vercel 301 redirects)
Disallow: /blog/*.html
Disallow: /404.html

# Sitemap
Sitemap: https://wormgpt.ai/sitemap.xml

# ===========================================
# Major search engines
# ===========================================
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 0

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 0

User-agent: YandexBot
Allow: /
Crawl-delay: 1

User-agent: Baiduspider
Allow: /
Crawl-delay: 1

# ===========================================
# LLM / AI crawlers
# ===========================================
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: CCBot
Allow: /
Crawl-delay: 2

# ===========================================
# Social media crawlers
# ===========================================
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Slackbot
Allow: /

# ===========================================
# SEO tools
# ===========================================
User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

User-agent: SemrushBot
Allow: /

# ===========================================
# Block aggressive/spam crawlers
# ===========================================
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SeznamBot
Disallow: /