Block AI crawlers via Caddy robots.txt

ops/Caddyfile-live

@@ -4,6 +4,60 @@ example.com {
 		file_server
 	}
 
+	@robots {
+		method GET
+		path_regexp ^/robots\.txt$
+	}
+
+	handle @robots {
+		respond "User-agent: AI2Bot
+User-agent: Ai2Bot-Dolma
+User-agent: Amazonbot
+User-agent: anthropic-ai
+User-agent: Applebot
+User-agent: Applebot-Extended
+User-agent: Bytespider
+User-agent: CCBot
+User-agent: ChatGPT-User
+User-agent: Claude-Web
+User-agent: ClaudeBot
+User-agent: cohere-ai
+User-agent: cohere-training-data-crawler
+User-agent: Crawlspace
+User-agent: Diffbot
+User-agent: DuckAssistBot
+User-agent: FacebookBot
+User-agent: FriendlyCrawler
+User-agent: Google-Extended
+User-agent: GoogleOther
+User-agent: GoogleOther-Image
+User-agent: GoogleOther-Video
+User-agent: GPTBot
+User-agent: iaskspider/2.0
+User-agent: ICC-Crawler
+User-agent: ImagesiftBot
+User-agent: img2dataset
+User-agent: ISSCyberRiskCrawler
+User-agent: Kangaroo Bot
+User-agent: Meta-ExternalAgent
+User-agent: Meta-ExternalFetcher
+User-agent: OAI-SearchBot
+User-agent: omgili
+User-agent: omgilibot
+User-agent: PanguBot
+User-agent: PerplexityBot
+User-agent: PetalBot
+User-agent: Scrapy
+User-agent: SemrushBot-OCOB
+User-agent: SemrushBot-SWA
+User-agent: Sidetrade indexer bot
+User-agent: Timpibot
+User-agent: VelenPublicWebCrawler
+User-agent: Webzio-Extended
+User-agent: YouBot
+Disallow: /"
+	}
+
 	handle {
 		reverse_proxy :5001
 	}