# CatalogHub — https://cataloghub.hopshq.com
#
# The Sitemap directive must be an absolute URL. It was previously "/sitemap.xml",
# which is not valid in robots.txt and is ignored, so the sitemap was never
# discovered. If the site moves to its own domain, update the absolute URLs in
# this file alongside VITE_SITE_URL.

User-agent: *
Allow: /

# Application surfaces. These sit behind authentication and hold supplier
# pricing, so there is nothing to index and no reason to spend crawl budget on
# them. The SPA shell served for these paths also carries noindex.
Disallow: /admin/
Disallow: /restaurant/
Disallow: /supplier/
Disallow: /reseller/
Disallow: /account-picker
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password

# Single-use token links. Disallowed rather than merely noindexed: keeping them
# out of the crawl is what stops a live invite or upload token reaching an index
# in the first place.
Disallow: /catalog-upload/
Disallow: /customer-invite-verify/
Disallow: /invitation-verify/
Disallow: /magic-link-verify/
Disallow: /reseller-invite-verify/
Disallow: /reseller-signup/
Disallow: /system-admin-invite-verify/

# Raw prerender artifacts. The same content is served at the canonical paths
# ("/suppliers", not "/prerendered/suppliers.html"); keep the duplicates out of
# the crawl so only the canonical URLs get indexed.
Disallow: /prerendered/

# AI and answer-engine crawlers.
#
# Already covered by User-agent: * above; named explicitly because being cited
# in AI answers is a deliberate goal here, and an explicit Allow makes that
# intent legible to whoever audits this file next. None of these crawlers
# execute JavaScript, which is why the public pages are prerendered to static
# HTML at build time — otherwise there is nothing here for them to read.

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

Sitemap: https://cataloghub.hopshq.com/sitemap.xml

# Machine-readable discovery. Non-standard directives, so commented out —
# crawlers ignore unrecognised keys, and /llms.txt is the canonical index of
# these resources.
# agent manifest: https://cataloghub.hopshq.com/.well-known/agent.json
# llms.txt:       https://cataloghub.hopshq.com/llms.txt
# OpenAPI:        https://cataloghub.hopshq.com/openapi.json
# MCP descriptor: https://cataloghub.hopshq.com/mcp