From 0c595a787ec8e0c74ed6ba200acce25b672255f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Felix=20F=C3=B6rtsch?= <mail@felixfoertsch.de>
Date: Wed, 15 Apr 2026 19:42:23 +0200
Subject: [PATCH] =?UTF-8?q?library:=20batch=20audio-codec=20lookup=20?=
 =?UTF-8?q?=E2=80=94=20per-row=20subquery=20was=20O(page=C3=97streams)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The scalar subquery I added in 7d30e6c ran one aggregate scan of
media_streams per row. On a real library (33k items / 212k streams)
a single page took 500+ seconds synchronously, blocking the event
loop and timing out every other request — Library AND Pipeline both
stopped loading.

Swap it for a single batched `GROUP_CONCAT ... WHERE item_id IN (?...)`
query over the current page's ids (max 25), then merge back into rows.

v2026.04.15.10

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 package.json       |  2 +-
 server/api/scan.ts | 24 +++++++++++++++++++-----
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/package.json b/package.json
index c09a96b..f7d3292 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "netfelix-audio-fix",
-	"version": "2026.04.15.9",
+	"version": "2026.04.15.10",
 	"scripts": {
 		"dev:server": "NODE_ENV=development bun --hot server/index.tsx",
 		"dev:client": "vite",
diff --git a/server/api/scan.ts b/server/api/scan.ts
index c58f152..cb89b74 100644
--- a/server/api/scan.ts
+++ b/server/api/scan.ts
@@ -163,11 +163,7 @@ app.get("/items", (c) => {
 			`
 			SELECT id, jellyfin_id, name, type, series_name, season_number, episode_number,
 			       scan_status, original_language, orig_lang_source, container, file_size, file_path,
-			       last_scanned_at, ingest_source,
-			       (SELECT GROUP_CONCAT(DISTINCT LOWER(codec))
-			        FROM media_streams
-			        WHERE item_id = media_items.id AND type = 'Audio' AND codec IS NOT NULL
-			       ) AS audio_codecs
+			       last_scanned_at, ingest_source
 			FROM media_items
 			${where.sql}
 			ORDER BY COALESCE(last_scanned_at, created_at) DESC, id DESC
@@ -192,6 +188,24 @@ app.get("/items", (c) => {
 		ingest_source: string | null;
 		audio_codecs: string | null;
 	}>;
+
+	// Audio codecs per item, batched into one query for the current page.
+	// A per-row scalar subquery over media_streams was O(page × streams)
+	// and could block the event loop for minutes on large libraries.
+	if (rows.length > 0) {
+		const placeholders = rows.map(() => "?").join(",");
+		const codecRows = db
+			.prepare(
+				`SELECT item_id, GROUP_CONCAT(DISTINCT LOWER(codec)) AS codecs
+				 FROM media_streams
+				 WHERE item_id IN (${placeholders}) AND type = 'Audio' AND codec IS NOT NULL
+				 GROUP BY item_id`,
+			)
+			.all(...rows.map((r) => r.id)) as { item_id: number; codecs: string | null }[];
+		const byItem = new Map(codecRows.map((r) => [r.item_id, r.codecs]));
+		for (const row of rows) row.audio_codecs = byItem.get(row.id) ?? null;
+	}
+
 	const total = (db.prepare(`SELECT COUNT(*) as n FROM media_items ${where.sql}`).get(...where.args) as { n: number }).n;
 	return c.json({ rows, total, hasMore: query.offset + rows.length < total, query });
 });