# robots.txt — merci-michel.com
# Crawl rules per RFC 9309 (https://www.rfc-editor.org/rfc/rfc9309).
# Crawlers may access the whole site; only the internal generator tool and the raw
# template partials are excluded.
#
# Content-Signal (https://contentsignals.org) declares how the listed crawlers may
# USE this content: search = search indexing (allowed); ai-input = use as live AI
# input such as answers/grounding (allowed); ai-train = AI model training (not
# allowed). These are usage preferences, separate from the crawl rules above.

Sitemap: https://www.merci-michel.com/sitemap.xml

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /generator
Disallow: /shared/

# AI assistants, AI search, and training crawlers — explicitly welcomed,
# with the same two exclusions as everyone else.
# (Mirrors App::AI_CRAWLER_PATTERN in server/App.php — keep in sync when adding crawlers.
#  Not 1:1: policy-only tokens like Applebot-Extended have no live-UA match in that regex.)
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Claude-User
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /generator
Disallow: /shared/