# Zesty Dessert Café — robots.txt
# https://www.zestydessertcafe.ca

# ===== Default rules for all crawlers =====
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Legal pages — keep crawlable for compliance lookups but not promoted
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# llms.txt is intended for AI agents only.
# Search engines should not index it.
Disallow: /llms.txt
Noindex: /llms.txt

# ===== AI / LLM crawlers — explicitly allow site + llms.txt =====
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: Bytespider
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ===== Google Ads crawlers — full access =====
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ===== Crawl-delay for heavy bots =====
User-agent: Baiduspider
Crawl-delay: 10

# ===== Sitemap =====
Sitemap: https://www.zestydessertcafe.ca/sitemap.xml