# 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

User-agent: *
Allow: /

# Private or session-only surfaces. Nothing here renders without an account,
# so a crawler that follows these links only ever reaches the login form --
# which is what would get indexed under the puzzle's name. Each is listed in
# both shapes because every public page also exists under a locale prefix
# (/fr/history is the same private page as /history).
Disallow: /users/
Disallow: /settings
Disallow: /admin
Disallow: /history
Disallow: /friends
Disallow: /challenges
Disallow: /api/
Disallow: /r/
Disallow: /*/users/
Disallow: /*/settings
Disallow: /*/history
Disallow: /*/friends
Disallow: /*/challenges

# The scroll is public, but the query strings behind it are the same feed
# sliced differently -- one indexed address is what we want, not fifty.
#
# The scroll moved to "/", and the rule deliberately did NOT move with it: a
# `Disallow: /?` would match every query string on the apex, which is where
# `?ref=` and `?src=` land -- i.e. every campaign and affiliate link the
# product has. The canonical on "/" is what dedupes those instead, which is
# the weaker instrument and the only correct one here.
Disallow: /create?
Disallow: /*/create?

# One line, and it points at an *index*: the shards it names live under
# /sitemaps/ and are deliberately not listed here. A sitemap index is the
# supported way to declare more than one file, and a robots.txt naming forty
# shards would be a second list of them -- one that goes stale the day a game
# type is added, silently, while the index stays right by construction.
Sitemap: https://ohwa.it/sitemap.xml

# The site plan a person reads, and the one page every game type is one click
# from: https://ohwa.it/sitemap (and /fr/sitemap, /de/sitemap, ... for the other
# fourteen). Not a `Sitemap:` line -- that directive means an XML sitemap, and
# pointing it at an HTML page is how a crawler is told the whole index is
# malformed. It is a comment for the same reason the two files below are, and it
# is linked from the footer of every page, which is the declaration that counts.

# Written for an assistant rather than for a crawler: what this product is and
# where each game is played (/llms.txt), and the full rules of every game type
# (/llms-full.txt). There is no directive for these, so they are named here as
# a comment -- robots.txt is the one file every reader already fetches, and a
# pointer costs nothing to anything that does not understand it.
# https://ohwa.it/llms.txt
# https://ohwa.it/llms-full.txt