castle-search: resolve Google links lazily, in Chrome, not eagerly over plain HTTPHEADmaster

The Node-side resolver sent one curl-like request per result with no
cookies, JS or browser; Google answers that with its 'Verifying your
request' countdown after a handful, and the testing itself triggered it.
A click or direct navigation in Chrome redirects at once (measured).

Search now leaves Google links wrapped and prints the breadcrumb Google
shows for each. castle_cdp_resolve follows one wrapped link in a Chrome tab
when the agent picks it, accepts only google.com/goto?url=<token>, and
reports the verification page instead of waiting it out.

1 files changed, 45 insertions, 2 deletions

diff --git a/castle-search/src/search.ts b/castle-search/src/search.ts
index c64735d..b5effb8 100644
--- a/castle-search/src/search.ts
+++ b/castle-search/src/search.ts
@@ -8,7 +8,8 @@
  * first search and closed by an idempotent `session_shutdown`.
  */
 
-import { resolveGoogleLinks } from "./resolve.ts";
+import { isGoogleGoto } from "./google-links.ts";
+import { GoogleVerificationError } from "./errors.ts";
 import { BrowserConnection, PageSession, raceAbort } from "./cdp.ts";
 import {
   type CdpTarget,
@@ -332,7 +333,7 @@ export const search = async (
       }
 
       return {
-        results: await resolveGoogleLinks(probe.results.slice(0, request.numResults), signal),
+        results: probe.results.slice(0, request.numResults),
         searchUrl,
         finalUrl: probe.url || searchUrl,
         endpoint,
@@ -350,3 +351,45 @@ export const search = async (
     release();
   }
 };
+
+export type ResolveOutcome = { from: string; to: string; endpoint: string };
+
+/**
+ * Follows one Google `/goto` link in Chrome and reports where it lands.
+ *
+ * Lazy by design: search leaves the links wrapped, and the caller resolves only
+ * the ones it means to open. One tab, one navigation, closed afterwards — the
+ * pattern of a person clicking a result, which Google serves directly.
+ *
+ * If Google answers with its "Verifying your request" page instead, the tab is
+ * still on google.com when the page loads. That is reported as such. The
+ * countdown is not waited out and nothing is clicked.
+ */
+export const resolveLink = async (url: string, signal: AbortSignal): Promise<ResolveOutcome> => {
+  if (!isGoogleGoto(url)) {
+    throw new Error(
+      "castle_cdp_resolve only follows Google result links of the form https://www.google.com/goto?url=… " +
+        "as printed by castle_cdp_search. Results from other engines already carry their real URL.",
+    );
+  }
+  const release = await acquire(signal);
+  try {
+    const conn = await ensureConnection(signal);
+    const endpoint = describeCdpTarget(conn.target);
+    const page = await PageSession.open(conn, signal);
+    try {
+      await page.navigate(url, signal);
+      const landed = await page.evaluate<string>("location.href", signal);
+      if (!landed || isGoogleHost(landed)) {
+        throw new GoogleVerificationError(landed || url);
+      }
+      return { from: url, to: landed, endpoint };
+    } finally {
+      await page.close();
+    }
+  } finally {
+    release();
+  }
+};
+
+const isGoogleHost = (url: string): boolean => /^https?:\/\/([a-z0-9-]+\.)*google\.(?:com?\.)?[a-z]{2,3}\//.test(url);