# 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

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: /

# END Cloudflare Managed Content

# WikiSure — robots policy
# Purpose: keep public product/evidence surfaces crawlable while avoiding
# route-name disclosure for private app, admin, research, and internal API areas.
# robots.txt is not access control; sensitive routes must enforce auth in app code.

User-agent: *
Allow: /
Allow: /build-info
Allow: /api-docs
Allow: /api/resolve
Allow: /api/evidence/
Allow: /api/public/build-info
Allow: /upload
Allow: /llms.txt
Allow: /sitemap.xml

# Private application and research workspaces. Use broad prefixes so robots.txt
# does not become a route inventory for recon.
Disallow: /api/
Disallow: /auth
Disallow: /reset-password
Disallow: /new
Disallow: /edit/
Disallow: /bulk
Disallow: /audit
Disallow: /unsubscribe
Disallow: /research-workspace/
Disallow: /wikisure/
Disallow: /definitions/dashboard
Disallow: /lovable/

# Product-journey proof pages such as /findings, /governance and /report are
# reachable from the public product tour and self-declare noindex where needed.
# Do not list hidden route names here; add real auth in the route instead.

Sitemap: https://wikisure.org/sitemap.xml