# The Chai Hut — robots.txt
# Site: https://www.thechaihutyyc.ca/
# Last updated: 2026-07-15

# ---- Default rules for all crawlers ----
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /config/
Disallow: /api/
Disallow: /logs/
Disallow: /*?*
Disallow: /*&*
# Legal pages — keep out of search results
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# NOTE on llms.txt:
# llms.txt is intentionally left crawlable by everyone (no Disallow) so that
# search engines can read the "X-Robots-Tag: noindex" header we serve for it
# (see the /_headers file). That header keeps llms.txt OUT of search results
# (Google, Bing, etc.) while AI/LLM agents can still fetch and use the file.
# A robots.txt "Disallow" is deliberately NOT used here, because a blocked URL
# can never see the noindex header.

# ---- AI / LLM agents: full access, including llms.txt ----
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Claude-User
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: CCBot
User-agent: cohere-ai
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
Allow: /
Allow: /llms.txt

# ---- Google Ads bots ----
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

User-agent: Sogou
Crawl-delay: 10

# ---- Sitemap ----
Sitemap: https://www.thechaihutyyc.ca/sitemap.xml