Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion src/routes/robots[.]txt.ts
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,17 @@ import { SITE_URL } from "@/lib/metadata";
export function buildRobotsTxt() {
const sitemapUrl = new URL("sitemap.xml", SITE_URL).toString();

return ["User-agent: *", "Allow: /", `Sitemap: ${sitemapUrl}`, ""].join("\n");
return [
// Content Signals declare our preferences for how AI systems and search
// engines may use this content. See https://contentsignals.org/ and
// https://datatracker.ietf.org/doc/draft-romm-aipref-contentsignals/
"Content-Signal: search=yes, ai-input=yes, ai-train=yes",
"",
"User-agent: *",
"Allow: /",
`Sitemap: ${sitemapUrl}`,
"",
].join("\n");
}

export const Route = createFileRoute("/robots.txt")({
Expand Down
37 changes: 36 additions & 1 deletion src/start.ts
Original file line number Diff line number Diff line change
Expand Up @@ -132,8 +132,43 @@ const llmMiddleware = createMiddleware().server(({ next, request }) => {
return next();
});

/**
* Links advertised to agents via the `Link` response header (RFC 8288).
*
* Reference: https://www.rfc-editor.org/rfc/rfc8288
* https://www.iana.org/assignments/link-relations/link-relations.xhtml
*/
const AGENT_LINK_HEADER = [
'</docs/sitemap.xml>; rel="sitemap"; type="application/xml"',
'</docs/llms.txt>; rel="describedby"; type="text/plain"',
'</docs/llms-full.txt>; rel="alternate"; type="text/plain"; title="LLM-friendly full docs"',
'</docs>; rel="service-doc"; type="text/html"',
'<https://superwall.com>; rel="canonical"; type="text/html"',
].join(", ");

function shouldAnnotateResponse(request: Request, response: Response): boolean {
if (request.method !== "GET" && request.method !== "HEAD") return false;
const contentType = response.headers.get("Content-Type");
if (!contentType) return false;
return contentType.toLowerCase().includes("text/html");
}

const agentDiscoveryMiddleware = createMiddleware().server(async ({ next, request }) => {
const result = await next();

if (shouldAnnotateResponse(request, result.response)) {
const existing = result.response.headers.get("Link");
result.response.headers.set(
"Link",
existing ? `${existing}, ${AGENT_LINK_HEADER}` : AGENT_LINK_HEADER,
);
}

return result;
});

export const startInstance = createStart(() => {
return {
requestMiddleware: [legacyRedirectMiddleware, llmMiddleware],
requestMiddleware: [agentDiscoveryMiddleware, legacyRedirectMiddleware, llmMiddleware],
};
});
Loading