From 9cbc525cf5f70b65764a7241f8b33dfa37e65cc7 Mon Sep 17 00:00:00 2001
From: rafapolo <rafael@extrapolo.com>
Date: Mon, 14 Sep 2026 20:12:05 +0200
Subject: [PATCH] fix: dedupe digest against all previously-sent jobs, not just
 this run

---
 daily.ts | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/daily.ts b/daily.ts
index 86a7545..3e7bc87 100644
--- a/daily.ts
+++ b/daily.ts
@@ -85,6 +85,22 @@ const normCompany = (company: string) =>
     .toLowerCase();
 const seenExact = new Set<string>();
 const seenTitleOnly = new Set<string>();
+
+// Seed both sets from everything already sent (any past day), keyed the same
+// way — not just today's batch. Without this, a job re-dedupes only against
+// jobs sent in the *same run*: LinkedIn reposts the same opening under a new
+// job ID every few weeks (Optiml, LocalBini, hexagonab, nicollcurtin, etc. —
+// confirmed repeats in sent.txt across different days), each repost lands
+// under a fresh link that passes the `sent.has(link)` check untouched, and it
+// got renotified as if new. `all` (the full CSV) still has every past row, so
+// each previously-sent link resolves back to a title+company to seed with.
+for (const r of all) {
+  if (!sent.has(r.link)) continue;
+  const t = normTitle(r.title);
+  seenExact.add(`${t}|${normCompany(r.company)}`);
+  if (t.split(" ").filter(Boolean).length >= 5) seenTitleOnly.add(t);
+}
+
 const matched = preDedupe.filter((r) => {
   const t = normTitle(r.title);
   const exactKey = `${t}|${normCompany(r.company)}`;