fix(ingestion): drain the Grants.gov backlog + source-filtered review queue

ingest-grants spent its 200-detail budget on hits.slice(0, 200) — the
same head of the search results every night; the backlog never drained.
Now new opportunities fill the budget first (serverListGrantSourceUrls
partition), remaining budget refreshes known ones; search cap raised to
2,000. Full eligible pool turns out to be 565 federal opportunities —
drained in two passes, 366 newly embedded.

Review queue gains a source badge column and All/Foundations/Federal
RFPs filter (?source=) — foundation easy-wins otherwise bury posted-RFP
matches, which score lower by design (no precedent, national pools) but
are the deadline-driven sends. Immediate proof: DOJ OVW FY2026 DV
program (closes 9/8) matched five NH domestic-violence orgs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

packages/outreach-core/src/grants/queries/index.server.ts

@@ -1,3 +1,4 @@
 export * from './list-open-grants.server.js';
 export * from './list-grants-needing-embedding.server.js';
 export * from './list-eligible-grants-for-org.server.js';
+export * from './list-grant-source-urls.server.js';

packages/outreach-core/src/grants/queries/list-grant-source-urls.server.ts

@@ -0,0 +1,20 @@
+import { eq } from 'drizzle-orm';
+
+import type { NpOutreachDatabase, NpOutreachTransaction } from '#~/db/db.js';
+import { schema } from '#~/db/db.js';
+
+/**
+ * All source URLs already ingested for one source — lets ingestion spend
+ * its per-run detail-fetch budget on NEW opportunities first instead of
+ * re-fetching the same head of the search results every night.
+ */
+export async function serverListGrantSourceUrls(
+  db: NpOutreachDatabase | NpOutreachTransaction,
+  source: (typeof schema.grants.$inferSelect)['source'],
+): Promise<Set<string>> {
+  const rows = await db
+    .select({ sourceUrl: schema.grants.sourceUrl })
+    .from(schema.grants)
+    .where(eq(schema.grants.source, source));
+  return new Set(rows.map((r) => r.sourceUrl));
+}

packages/outreach-core/src/matches/queries/list-pending-review-matches.server.ts

@@ -1,4 +1,4 @@
-import { desc, eq } from 'drizzle-orm';
+import { and, desc, eq } from 'drizzle-orm';
 
 import type { NpOutreachDatabase, NpOutreachTransaction } from '#~/db/db.js';
 import { schema } from '#~/db/db.js';
@@ -14,6 +14,7 @@ export interface PendingReviewMatch {
   orgName: string;
   grantTitle: string;
   funder: string;
+  source: string;
   totalScore: number;
   easyWin: boolean;
   isHero: boolean;
@@ -22,6 +23,7 @@ export interface PendingReviewMatch {
 
 export async function serverListPendingReviewMatches(
   db: NpOutreachDatabase | NpOutreachTransaction,
+  { source }: { source?: string } = {},
 ): Promise<PendingReviewMatch[]> {
   return db
     .select({
@@ -29,6 +31,7 @@ export async function serverListPendingReviewMatches(
       orgName: schema.orgs.name,
       grantTitle: schema.grants.title,
       funder: schema.grants.funder,
+      source: schema.grants.source,
       totalScore: schema.matches.totalScore,
       easyWin: schema.matches.easyWin,
       isHero: schema.matches.isHero,
@@ -37,7 +40,14 @@ export async function serverListPendingReviewMatches(
     .from(schema.matches)
     .innerJoin(schema.orgs, eq(schema.matches.orgId, schema.orgs.id))
     .innerJoin(schema.grants, eq(schema.matches.grantId, schema.grants.id))
-    .where(eq(schema.matches.reviewStatus, 'pending'))
+    .where(
+      source == null
+        ? eq(schema.matches.reviewStatus, 'pending')
+        : and(
+            eq(schema.matches.reviewStatus, 'pending'),
+            eq(schema.grants.source, source as never),
+          ),
+    )
     // Reviewers see the best candidates first: heroes, then easy wins,
     // then raw score. Capped — nightly re-scoring generates thousands of
     // pending pairs and the queue is worked top-down, not exhaustively.