# As a condition of accessing this website, you agree to abide by the following
# content signals:
#
# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.
#
# The content signals and their meanings are:
#
# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
#
# Policy (SNOW-1102): allow conventional search indexing and real-time AI
# retrieval/grounding/citation; disallow crawlers used primarily for model
# training or bulk training-data collection. This file is the sole robots.txt
# source of truth once Cloudflare Managed robots.txt is disabled (operators can
# only wholesale-disable that feature, not scope it to www-only).

# Default: searchable; AI input/RAG allowed; training disallowed; reference use.
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /

# Search / discovery / real-time retrieval (explicit allow; also covered by *).
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

# Training / bulk AI-data crawlers (absorbed from Cloudflare Managed + SNOW-1102).
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Sitemaps (canonical www host — do not use apex; apex 301s to www).
Sitemap: https://www.snow.day/sitemap.xml
Sitemap: https://www.snow.day/server-sitemap.xml