# Robots.txt for TimberCloud
# https://timbercloud.com/robots.txt

# Allow all search engines to crawl the site
User-agent: *
Allow: /

# Block crawling of authentication and admin areas
Disallow: /api/
Disallow: /login
Disallow: /create-account
Disallow: /reset-password
Disallow: /forgot-password
Disallow: /admin/
Disallow: /dashboard/
Disallow: /session-conflict
Disallow: /onboarding/

# Block crawling of development and testing files
Disallow: /*.json$
# Next.js framework assets MUST stay crawlable — Google's render phase needs
# the JS/CSS bundles and the /_next/data payloads to render pages. The longer
# Allow rules below win over the /*.json$ disallow (longest-match precedence).
Allow: /_next/static/
Allow: /_next/data/
Allow: /_next/image
Allow: /sitemap.xml
Allow: /api/sitemap*.xml
Disallow: /*.xml$
Disallow: /test/
Disallow: /tests/
Disallow: /demo/
Disallow: /node_modules/

# Allow crawling of important assets
Allow: /icons/
Allow: /images/
Allow: /logos/
Allow: /screenshots/
Allow: /manifest.json
Allow: /favicon.ico

# Sitemap location — the index nests the static, marketing (CMS), and blog
# sub-sitemaps, so one declaration covers all real pages with equal footing.
Sitemap: https://timbercloud.com/api/sitemap-index.xml

# Crawl-delay (optional - helps with server load)
Crawl-delay: 1

# Search engines and AI answer engines we explicitly welcome.
#
# IMPORTANT: robots.txt groups do NOT inherit. A crawler obeys exactly one
# group — the most specific match on its own product token — and ignores the
# `User-agent: *` group entirely once it is named here (RFC 9309 §2.2.1).
# So every rule this group needs must be repeated below; it cannot rely on
# the disallows further up the file. Listing all the agents against a single
# rule block keeps that duplication to one place — add new bots to the list,
# never as a separate group with its own copy of the rules.
#
# AI-answer visibility is a growth channel for TimberCloud, so the answer
# engines get the same access as classic search, not a reduced one.
User-agent: Googlebot
User-agent: Bingbot
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Google-Extended
Allow: /
# Rendering assets — Google's render phase needs these to see the page at all.
Allow: /_next/static/
Allow: /_next/data/
Allow: /_next/image
Allow: /api/sitemap*.xml
# Mirrors of the `User-agent: *` disallows above. Keep the two lists in sync.
Disallow: /api/
Disallow: /login
Disallow: /create-account
Disallow: /reset-password
Disallow: /forgot-password
Disallow: /admin/
Disallow: /dashboard/
Disallow: /session-conflict
Disallow: /onboarding/
Crawl-delay: 1

# Block unwanted bots
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /