fix(ai): read AI switches, modules and consent afresh inside background jobs

A background job opens one wide event for its whole run, and the per-request
memo cached the operator switches, module availability, module preferences,
provider presence and consent kinds on it. The nightly status passes loop
over every candidate inside that one event, so a switch turned off mid-run
did not stop the remaining users, and the wire re-check read the same cached
answer.

memoizePerRequest takes a freshInBackground option; every input that decides
whether AI work may run sets it, so a background caller reads them on every
call while a request still reads them once.

src/lib/modules/operator-availability.ts

@@ -104,13 +104,17 @@ async function loadAvailabilityBlob(): Promise<unknown> {
  * all-available so the modules stay visible on first boot.
  */
 export async function getOperatorModuleAvailability(): Promise<OperatorModuleAvailability> {
-  return memoizePerRequest("operator-module-availability", async () => {
-    const [blob, switches] = await Promise.all([
-      loadAvailabilityBlob(),
-      getAssistantFlags(),
-    ]);
-    return resolveOperatorAvailability(blob, switches.coach);
-  });
+  return memoizePerRequest(
+    "operator-module-availability",
+    async () => {
+      const [blob, switches] = await Promise.all([
+        loadAvailabilityBlob(),
+        getAssistantFlags(),
+      ]);
+      return resolveOperatorAvailability(blob, switches.coach);
+    },
+    { freshInBackground: true },
+  );
 }
 
 /** A module key whose operator layer the blob owns (every key but the Coach). */