# ============================================================
# robots.txt for roswell.nyc
# ============================================================
# Search engines get full access to the canonical HTML.
# AI crawlers (listed below) are explicitly allowed.
# Per-page AI-readable content is served via Cloudflare's
# content negotiation (Accept: text/markdown); the curated
# site manifest lives at /llms.txt.
# ============================================================

User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/

# -- WordPress legacy paths (migrated from roswellstudios.com) ---------------
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /wp-sitemap.xml
Disallow: /xmlrpc.php
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /category/
Disallow: /tag/
Disallow: /author/
Disallow: /page/
Disallow: /*/embed/
Disallow: /*/trackback/

Sitemap: https://roswell.nyc/sitemap.xml

# ============================================================
# Googlebot - full access to canonical HTML
# ============================================================
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /feed/
Disallow: /category/
Disallow: /tag/
Disallow: /author/
Disallow: /page/

# ============================================================
# Bingbot / Microsoft
# ============================================================
User-agent: Bingbot
Allow: /
Disallow: /api/

# ============================================================
# AI / LLM crawlers - full unrestricted access
# ============================================================

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude (all product variants)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude
Allow: /

User-agent: Claude-Desktop
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

User-agent: GeminiBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# xAI / Grok
User-agent: GrokBot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Others
User-agent: DeepSeekBot
Allow: /

User-agent: MistralBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

# ============================================================
# LLM Discovery (for AI systems reading this file)
# ============================================================
# All AI crawlers above receive full unrestricted access.
# Curated site manifest for AI: https://roswell.nyc/llms.txt
# ============================================================