# BreakReady — www.breakreadyapp.com
#
# robots.txt is a request, not a control. Well-behaved crawlers honour it;
# a scraper written to copy this site will ignore it entirely. It is here to
# handle the compliant majority and to keep private surfaces out of search
# indexes. The camp catalogue is protected by /api/camps and RLS, not by this
# file. See LICENSE and /terms for the part that has legal weight.


# ---------------------------------------------------------------------------
# AI TRAINING CRAWLERS — blocked
#
# These collect pages to train models. Nothing comes back the other way: no
# referral, no citation, no visitor. The camp catalogue took months to build
# by hand and there is no reason to donate it to a training set.
# ---------------------------------------------------------------------------

User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Scrapy
User-agent: magpie-crawler
Disallow: /


# ---------------------------------------------------------------------------
# ANSWER ENGINES — deliberately ALLOWED
#
# These fetch a page because a person just asked a question it might answer,
# and they cite the source. A parent typing "camps in Carlsbad over fall break"
# into ChatGPT or Perplexity is exactly the visitor /camps exists for, and
# blocking these would cut off a discovery channel to prevent a copy that the
# training-crawler block above already covers.
#
# This is a judgement call, not a default. Flip these to Disallow if the
# catalogue ever starts showing up reproduced somewhere it shouldn't.
# ---------------------------------------------------------------------------

User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-User
User-agent: YouBot
Disallow: /admin
Disallow: /api/
Allow: /api/camps
Allow: /api/breaks
Disallow: /family
Disallow: /kid-planner
Disallow: /logistics
Disallow: /notifications
Disallow: /reassign
Disallow: /schedule-update-form
Disallow: /share
Disallow: /summer-ahead
Disallow: /fall-ahead
Disallow: /carpool
Disallow: /pushtest
Disallow: /camps_demo_2026


# ---------------------------------------------------------------------------
# EVERYONE ELSE, INCLUDING GOOGLE AND BING
#
# /camps and /for-camps are the SEO surfaces and stay open. Everything token-
# gated stays out of the index: those URLs carry a family's identity, and a
# token that lands in search results is a token anyone can use.
#
# /api/ is closed with two deliberate exceptions. /camps renders its list from
# a client-side fetch, so a crawler blocked from /api/camps would index the
# page as an empty shell — closing the whole prefix would quietly wreck the
# ranking of the one page built to rank. Allow beats Disallow on longest match
# in both Google and Bing.
# ---------------------------------------------------------------------------

User-agent: *
Disallow: /admin
Disallow: /api/
Allow: /api/camps
Allow: /api/breaks
Disallow: /family
Disallow: /kid-planner
Disallow: /logistics
Disallow: /notifications
Disallow: /reassign
Disallow: /schedule-update-form
Disallow: /share
Disallow: /summer-ahead
Disallow: /fall-ahead
Disallow: /carpool
Disallow: /pushtest
Disallow: /camps_demo_2026