# =====================================================
# Hotel Bergsonne Allgaeu - robots.txt
# https://bergsonne-allgaeu.de
#
# Policy: maximum AI discoverability — every AI and search crawler is allowed.
#
# DECIDED 12.09.2026 (reinstated same day): the "Content-Signal:" lines
# (contentsignals.org) are BACK. Removing them was based on a wrong diagnosis:
# Lighthouse SEO 100 was achieved by removing the single invalid "Agentmap:"
# line — Content-Signal lines are flagged as unknown directives but do NOT
# invalidate the file. Without them Cloudflare Bot Access Control drops to
# 2/3 and the agent-readiness grade falls from Stufe 5 to Stufe 1.
# They must stay. Both Lighthouse 100 and Content Signals work together.
# =====================================================

Sitemap: https://bergsonne-allgaeu.de/sitemap.xml
Sitemap: https://bergsonne-allgaeu.de/image-sitemap.xml

# Agent Resource Discovery (ard.dev): the catalog of every machine-readable
# interface of this site is discoverable through the RFC 8288 Link header on /,
# https://bergsonne-allgaeu.de/.well-known/ard.json and the DNS TXT record
# _catalog._agents.bergsonne-allgaeu.de. No robots.txt directive is used for it:
# Lighthouse flags a non-standard "Agentmap:" line as an unknown directive.

# --- Classic search + social ---
User-agent: Googlebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: LinkedInBot
User-agent: Pinterestbot
Allow: /
Allow: /.well-known/
Disallow: /admin/
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Disallow: /tv/
Disallow: /lio/
Disallow: /maxibar/
Disallow: /update/
Disallow: /_/

# --- AI crawlers: training, grounding, and user-triggered fetch ---
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Meta-ExternalAgent
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: CCBot
User-agent: AI2Bot
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: Diffbot
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: ImagesiftBot
User-agent: PanguBot
Allow: /
Allow: /.well-known/
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /webmcp.json
Allow: /api/openapi
Allow: /api/booking
Allow: /api/booking-mcp
Disallow: /admin/
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Disallow: /tv/
Disallow: /lio/
Disallow: /maxibar/
Disallow: /update/
Disallow: /_/
Disallow: /api/

# --- Site-audit tool ---
User-agent: Seobility
Disallow: /llms.txt
Disallow: /llms-full.txt
Disallow: /api/
Disallow: /webmcp.json

# --- Everything else ---
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Allow: /.well-known/
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /webmcp.json
Allow: /api/openapi
Allow: /api/booking
Allow: /api/booking-mcp
Disallow: /admin/
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Disallow: /tv/
Disallow: /lio/
Disallow: /maxibar/
Disallow: /update/
Disallow: /_/
Disallow: /api/