# One Bag Travel — https://onebag.travel
#
# Crawling is open to everyone, AI crawlers included. What a crawler may DO with
# the content afterwards is stated separately, with Content Signals
# (https://contentsignals.org), because robots.txt only governs access:
#
#   search=yes    index the site and link back to it
#   ai-input=yes  quote or ground an answer in it, with a link back
#   ai-train=no   do not use it to train or fine-tune a model
#
# Content Signals are a statement of preference, not a technical control.
#
# Machine-readable entry points for agents:
#   /llms.txt                             site overview
#   /llms-full.txt                        full text of the guides
#   /.well-known/api-catalog              JSON data APIs (RFC 9727)
#   /.well-known/mcp.json                 MCP server card
#   /.well-known/agent-skills/index.json  Agent Skills index
# Page markdown: request any page with `Accept: text/markdown`, or append .md.

Sitemap: https://onebag.travel/sitemap.xml

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /manage/
Disallow: */preview
Allow: /

# --- AI search and answer engines: crawl, cite, link back ---------------------
# Named explicitly so the policy is unambiguous. A robots.txt parser obeys the
# single most specific matching group, so each group repeats the rules above.

User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Google-CloudVertexBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /manage/
Disallow: */preview
Allow: /

# --- Model-training crawlers: allowed to crawl, asked not to train ------------

User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: CCBot
User-agent: Bytespider
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Timpibot
User-agent: omgili
User-agent: omgilibot
User-agent: ImagesiftBot
User-agent: AI2Bot
User-agent: PanguBot
User-agent: Webzio-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /manage/
Disallow: */preview
Allow: /