# robots.txt — Arkalyans — www.arkalyans.fr (production)
# Gate 3 lifted 2026-09-20. Previous version (sandbox, Disallow: /) is kept at
# site/prod-robots-before-gates-20260920.bak.
#
# sandbox.arkalyans.fr keeps its own robots.txt with Disallow: / — do not copy
# this file into the sandbox tree.

Sitemap: https://www.arkalyans.fr/sitemap.xml

# ---------------------------------------------------------------------------
# Every crawler: the whole public site is open.
# Server-side trees (cron, data, includes, _migration_backup, vendor) are denied
# by .htaccess itself, which is the real control; they are listed here too so a
# crawler does not waste budget on them.
# ---------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /cron/
Disallow: /data/
Disallow: /includes/
Disallow: /vendor/
Disallow: /_migration_backup/
Disallow: /api/
# Autres proprietes hebergees dans le meme dossier : jamais explorees via www.
Disallow: /sandbox/
Disallow: /gameswealth/
Disallow: /doc/

# ---------------------------------------------------------------------------
# AI RETRIEVAL crawlers — explicitly allowed. These are what put the site in
# ChatGPT Search, Claude and Perplexity answers. Blocking them removes it.
# ---------------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

# ---------------------------------------------------------------------------
# AI TRAINING crawlers — currently allowed (§C.3: "Allow par défaut" in prod).
# Business decision, not a technical one: switch Allow -> Disallow here to opt
# out of model training without affecting the retrieval crawlers above.
# ---------------------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /