# SunsetWalk llms.txt - Last updated: 2026-02-26
# Purpose: Declare how AI/LLM crawlers may use and access the content of this website.
# This does NOT replace robots.txt, but works alongside it.

# ------------------------------
# GLOBAL POLICY
# ------------------------------
# Allow AI crawlers to access ONLY publicly indexable pages.
# Do NOT allow scraping of admin routes, search results, filters, or gated content.
# Follow robots.txt exclusions.
policy: allow
disallowed_paths:
  - /wp-admin/
  - /wp-login.php
  - /?s=
  - /search/
  - /page/
  - /*?filter=
  - /*?sorting=
  - /*?orderby=
  - /*?event_*
  - /*?gallery_*
  - /*?offer_*
  - /event_type/
  - /event_organizer/
  - /event_location/
  - /category/
  - /?attachment_id=

# ------------------------------
# CRAWLER-SPECIFIC DECLARATIONS
# ------------------------------
# OpenAI (ChatGPT, GPT-5)
agent: OpenAI
policy: allow

# Google Gemini / Google AI
agent: Google-Extended
policy: allow

# Anthropic (Claude)
agent: anthropic-ai
policy: allow

# Perplexity
agent: PerplexityAI
policy: allow

# Meta AI
agent: MetaAI
policy: allow

# Apple
agent: Applebot-Extended
policy: allow

# You.com
agent: YouBot
policy: allow

# CCBot (Common Crawl)
agent: CCBot
policy: disallow   # optional — CC crawls aggressively; block if bandwidth is a concern

# ------------------------------
# SITEMAP REFERENCE (for all LLMs)
# ------------------------------
sitemaps:
  - https://www.sunsetwalk.com/sitemap_index.xml

# ------------------------------
# ATTRIBUTION & LICENSE
# ------------------------------
# All content is copyrighted by Promenade at Sunset Walk.
# AI crawlers may access and train on publicly available content,
# but attribution back to the source URL is required when generating outputs.
require_attribution: true

# ------------------------------
# RATE LIMITING
# ------------------------------
# Respect crawl patterns defined in robots.txt.
# Please limit requests to avoid bandwidth spikes.
crawl_delay_seconds: 2