diff --git a/src/content.js b/src/content.js
index 4ff14b2..188eba0 100644
--- a/src/content.js
+++ b/src/content.js
@@ -68,8 +68,11 @@ const selectPartitionedArticlesMissingContent = db.prepare(`
     SELECT id, url, title, description, source, pub_date_effective,
       ROW_NUMBER() OVER (PARTITION BY source ORDER BY pub_date_effective DESC, id DESC) AS rn
     FROM articles
-    WHERE (content IS NULL OR TRIM(content) = '')
-      AND (content_status IS NULL OR content_status = 'pending')
+    -- content_status is the authority on whether a row has been fetched, and it
+    -- agrees with the content column on all 2.2M rows. Testing TRIM(content) here
+    -- as well meant reading a 4GB blob column just to find out which rows to skip,
+    -- and it stopped the partial index below being usable at all.
+    WHERE (content_status IS NULL OR content_status = 'pending')
       AND (content_retry_after IS NULL OR content_retry_after <= datetime('now'))
       AND (id % ?) = ?
   )
@@ -409,8 +412,7 @@ async function runBackfillWorker({ workerIndex, workerCount, perSource, batchSiz
 function hasPendingContent() {
   return Boolean(db.prepare(`
     SELECT 1 FROM articles
-    WHERE (content IS NULL OR TRIM(content) = '')
-      AND (content_status IS NULL OR content_status = 'pending')
+    WHERE (content_status IS NULL OR content_status = 'pending')
       AND (content_retry_after IS NULL OR content_retry_after <= datetime('now'))
     LIMIT 1
   `).get());
diff --git a/src/db/index.js b/src/db/index.js
index 9ea1cb2..a3751e6 100644
--- a/src/db/index.js
+++ b/src/db/index.js
@@ -54,8 +54,26 @@ db.exec(`
       AND content != ''
       AND is_index_page = 0
       AND has_embedding = 1;
+
+  -- The content backfill picker partitions by source and orders by pub date, and
+  -- without this it built two temp b-trees over every unfetched row: 194 seconds
+  -- per call on a 2.2M row archive, synchronously, which froze the whole process.
+  -- Column order matches PARTITION BY source ORDER BY pub_date_effective DESC, id DESC
+  -- so the window function can just walk it.
+  CREATE INDEX IF NOT EXISTS idx_articles_pending_fetch
+    ON articles(source, pub_date_effective DESC, id DESC)
+    WHERE content_status IS NULL OR content_status = 'pending';
 `);
 
+// Without stats the planner ignores the partial index above and falls back to the
+// content_status index plus a temp b-tree, which is roughly 70% slower. optimize
+// only re-analyses what has actually drifted, so this is cheap after the first run.
+try {
+  db.exec('PRAGMA optimize;');
+} catch (error) {
+  console.error('[db] PRAGMA optimize failed, query plans may be stale:', error.message);
+}
+
 db.exec(`
   CREATE TABLE IF NOT EXISTS article_embedding_store (
     article_id INTEGER NOT NULL,