# robots.txt for centripetal.ai
User-agent: *
Allow: /

# Disallow admin/CMS areas
Disallow: /admin/
Disallow: /cpresources/
Disallow: /actions/

# Tracking-parameter URLs (Wistia + HubSpot) generate thousands of duplicate
# crawl URLs — the bulk of GSC's "Crawled - currently not indexed" bucket
# (~12k as of 2026-07-21). Match the param ANYWHERE in the query string: the
# old "/*?param=" rules only caught it as the FIRST param and missed the far
# more common "&param=" variants. Video playback is unaffected (loads via JS
# from *.wistia.com, not via these crawled URLs).
Disallow: /*wchannelid
Disallow: /*wmediaid
Disallow: /*wtime
Disallow: /*__hstc
Disallow: /*__hsfp
Disallow: /*__hssc
Disallow: /*doing_wp_cron
# HubSpot email-link + referral tracking params (2026-07-28) — close the
# remaining gaps not caught by the analytics-cookie params above.
Disallow: /*_hsenc
Disallow: /*_hsmi
Disallow: /*snoball_referral

# NOTE: /download is deliberately NOT disallowed here. The page serves
# noindex/nofollow (via SEOmatic) and is excluded from the sitemap; Google
# must be able to crawl it to see the noindex and drop it from the index.
# The installer files themselves are password-gated server-side (404 to
# crawlers), so nothing sensitive is crawlable anyway.

# Explicitly allow LLM crawler files
Allow: /llms.txt
Allow: /llms-full.txt

# Sitemaps (generated by SEOMatic plugin — one per Multi-Site).
# The plugin emits a separate sitemap index per site; each must be listed
# so search engines can discover and process them independently.
Sitemap: https://www.centripetal.ai/sitemap.xml
Sitemap: https://www.centripetal.ai/ja/sitemap.xml
Sitemap: https://www.centripetal.ai/es-latam/sitemap.xml