# robots.txt — The Holistic Care (www.theholisticcare.com)
# Managed manually — next-sitemap generateRobotsTxt is set to FALSE to prevent overwriting

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

# Protected app routes (require login — no value to Google)
Disallow: /dashboard
Disallow: /dashboard/
Disallow: /learn/
Disallow: /api/
Disallow: /studio/
Disallow: /admin/

# Auth pages (no indexable content)
Disallow: /login
Disallow: /signup
Disallow: /forgot-password

# Old Odoo internal paths — no content on new site
Disallow: /web/
Disallow: /website/
Disallow: /slides/
Disallow: /forums/
Disallow: /forum/
Disallow: /r/

# Block parameterised shop/blog URLs (faceted filters, sort orders, tags)
# These create duplicate content and waste crawl budget
Disallow: /shop?*
Disallow: /blog?*

# Block old Odoo blog category-numbered paths
Disallow: /blog/uncategorized-8
Disallow: /blog/yoga-7
Disallow: /blog/non-duality-6
Disallow: /blog/mindfulness-4

# AI search crawlers — explicitly allowed for search inclusion (not training)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# GPTBot (OpenAI training) — disallowed; OAI-SearchBot above handles ChatGPT Search
User-agent: GPTBot
Disallow: /

# LLM content files - full site content for AI search, retrieval, and citation
# Markdown format (484 pages)
# https://www.theholisticcare.com/llms-full.txt
# JSON format (484 pages)
# https://www.theholisticcare.com/llms-full.json

# Sitemaps
Sitemap: https://www.theholisticcare.com/sitemap.xml