User-agent: *
Allow: /

# Block admin panel from indexing
Disallow: /admin
Disallow: /admin/
Disallow: /api/

# Sitemap
Sitemap: https://current-cruises.com/sitemap.xml

# LLM context files
# https://llmstxt.org
# llms.txt:      https://current-cruises.com/llms.txt
# llms-full.txt: https://current-cruises.com/llms-full.txt

# ── AI crawlers ──────────────────────────────────────────────────────────────
# Split by what the crawler gives back, not by who runs it.
#
# 1. Answer engines that fetch when a real person asks a question and reply
#    with a citation and a link. That is free distribution — a guest asking an
#    assistant about Amsterdam canal tours should find us. They get the site.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-User
User-agent: Applebot
Allow: /
Disallow: /api/

# 2. Training and bulk-dataset crawlers. They take content into a model or a
#    dataset with no attribution and no visit back, so they get the commercial
#    surface only — who we are, what we sell, prices, FAQ. Knowing that is how
#    an assistant recommends us from memory, and we are happy to be known for
#    it. The researched Amsterdam corpus is not part of the deal: no /facts,
#    no /discover, no llms-full.txt.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Scrapy
Allow: /
Disallow: /facts
Disallow: /facts/
Disallow: /discover
Disallow: /discover/
Disallow: /llms-full.txt
Disallow: /api/

# Search crawlers (Googlebot, Bingbot, …) are covered by the * group above and
# keep full access — /discover pages need to stay indexable to rank at all.
# Everything here is voluntary compliance; the enforced half lives in
# src/lib/public-api-guard.ts and the edge bot rules.