# https://www.stacksync.com/robots.txt
#
# Default policy: allow crawl of everything except infrastructure paths.
# Query-param variants are deliberately CRAWLABLE: every page emits a
# query-stripped canonical (BaseLayout), which lets Google consolidate
# ?utm_/?ref= URLs instead of leaving them stuck in "Blocked by robots.txt".
# Dead Webflow pagination params ({hex}_page=) are 301-stripped by
# src/middleware.ts on on-demand routes, which include the blog index,
# category and author listings where Webflow paginated. Prerendered pages
# ignore the query and carry the same canonical. (Unpublished drafts live in
# src/_drafts/ and never build, so they need no Disallow.)
#
# Per-pair planning worksheets (/integrations/{pair}/planning.csv) are linked
# with rel="nofollow" and answer with X-Robots-Tag: noindex. They are not
# disallowed here, so crawlers that do fetch one can read the noindex.
#
# AI / LLM crawlers are explicitly allowed — stacksync wants to be cited
# in AI Overviews, ChatGPT search, Perplexity, Claude, Bing Copilot, etc.
# A crawler obeys only the most specific group that names it (RFC 9309), so
# the named group repeats every rule of the * group.

User-agent: *
Allow: /
Allow: /api/og.png
Disallow: /api/
Allow: /_astro/

# AI search & training crawlers — explicit allow, same rules as *
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bingbot
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: MistralAI-User
User-agent: Amazonbot
User-agent: DuckAssistBot
User-agent: cohere-ai
User-agent: YouBot
Allow: /
Allow: /api/og.png
Disallow: /api/
Allow: /_astro/

# Sitemap discovery — single master index points to all per-section sitemaps
Sitemap: https://www.stacksync.com/sitemap.xml