# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Zanbug — https://zanbug.com
#
# Every crawler may read all four languages of the public site; only the panel
# is closed. The product is meant to be found when someone asks an assistant
# "self-hosted error tracking for Laravel", so the AI groups below are allowed
# rather than merely unmentioned.
#
# Cloudflare's managed robots.txt — which prepended "Disallow: /" for every AI
# crawler ahead of this file — was switched off on 2026-08-19, so what you read
# here is now the whole answer. The rules stay written the defensive way anyway:
# that setting is one dashboard click from coming back, and a file that only
# works while a setting stays off is a file that breaks silently.

User-agent: *
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /payment/
Disallow: /github/
Disallow: /live/
Disallow: /share/

# AI assistants and answer engines — allowed on the public pages, blocked from
# the panel like everyone else.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: cohere-ai
User-agent: YouBot
# Stated on the AI groups themselves rather than on "User-agent: *", so they
# survive anything an edge product prepends to a wildcard group.
Content-Signal: search=yes,ai-input=yes,ai-train=yes,use=full
# "Allow: /" would only TIE with Cloudflare's "Disallow: /" — same length, and
# parsers break that tie differently (Google takes the least restrictive, others
# take the first group and stay out). Every rule below is LONGER than "/", so
# longest-match makes the answer the same everywhere.
Allow: /*
Allow: /$
Allow: /az
Allow: /ru
Allow: /tr
Allow: /integrations/
Allow: /llms.txt
Allow: /sitemap.xml
# Longer than "/*", so the panel stays out of reach for them too.
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /payment/
Disallow: /github/
Disallow: /live/
Disallow: /share/

# Bytespider scrapes for training and sends no visitors back. Cloudflare's
# managed block used to be the only thing keeping it out; naming it here is why
# turning that block off changed nothing for anyone we actually want.
User-agent: Bytespider
Disallow: /

# What this site is, for assistants that read it.
# https://llmstxt.org
Sitemap: https://zanbug.com/sitemap.xml

# IndexNow key file: /20e2dc89002317779c8ba4ac11594490.txt
# Bing and Yandex accept a direct "these URLs changed" ping instead of waiting
# for a crawl. Google does not participate — there it is sitemap plus patience.