fix(crawler): reap dead jobs alongside done ones

The retention reaper deleted only `state = 'done'` rows, so terminal
`dead` jobs (retries exhausted) accumulated in crawler_jobs forever —
slow unbounded table growth. Both states are end-of-life and never
leased again.

Rename `reap_done` → `reap_terminal` and broaden the filter to
`state IN ('done','dead')`; `pending`/`running` stay untouched. Test
extended to assert old done + old dead both reap while fresh terminal and
old-but-active rows survive.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/Cargo.lock

@@ -1558,7 +1558,7 @@ checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
 
 [[package]]
 name = "mangalord"
-version = "0.93.7"
+version = "0.93.8"
 dependencies = [
  "anyhow",
  "argon2",

backend/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "mangalord"
-version = "0.93.7"
+version = "0.93.8"
 edition = "2021"
 default-run = "mangalord"
 

backend/src/crawler/daemon.rs

@@ -301,9 +301,9 @@ impl CronContext {
                 }
                 Err(e) => tracing::error!(?e, "cron: enqueue_bookmarked_pending failed"),
             }
-            match jobs::reap_done(pool, retention_days).await {
-                Ok(n) => tracing::info!(reaped = n, "cron: done-job reaper finished"),
-                Err(e) => tracing::error!(?e, "cron: done-job reaper failed"),
+            match jobs::reap_terminal(pool, retention_days).await {
+                Ok(n) => tracing::info!(reaped = n, "cron: terminal-job reaper finished"),
+                Err(e) => tracing::error!(?e, "cron: terminal-job reaper failed"),
             }
             match crate::repo::crawl_metrics::reap(pool, metrics_retention_days).await {
                 Ok(n) => tracing::info!(reaped = n, "cron: crawl-metrics reaper finished"),

backend/src/crawler/jobs.rs

@@ -485,16 +485,19 @@ pub async fn reclaim_orphaned(pool: &PgPool) -> sqlx::Result<u64> {
     Ok(result.rows_affected())
 }
 
-/// Delete `done` jobs whose `updated_at` is older than `retention_days`
-/// days. `0` disables the reaper without touching the table. Returns the
-/// number of rows removed.
-pub async fn reap_done(pool: &PgPool, retention_days: u32) -> sqlx::Result<u64> {
+/// Delete **terminal** jobs (`done` or `dead`) whose `updated_at` is older
+/// than `retention_days` days. Both states are end-of-life — `done`
+/// succeeded, `dead` exhausted its retries — and neither is ever leased
+/// again, so reaping only `done` left `dead` rows to accumulate forever.
+/// `pending` / `running` are active and never touched. `0` disables the
+/// reaper without touching the table. Returns the number of rows removed.
+pub async fn reap_terminal(pool: &PgPool, retention_days: u32) -> sqlx::Result<u64> {
     if retention_days == 0 {
         return Ok(0);
     }
     let result = sqlx::query(
         "DELETE FROM crawler_jobs \
-          WHERE state = 'done' \
+          WHERE state IN ('done', 'dead') \
             AND updated_at < now() - ($1::bigint || ' days')::interval",
     )
     .bind(retention_days as i64)

backend/src/repo/crawl_metrics.rs

@@ -187,7 +187,7 @@ pub async fn list_ops(
 }
 
 /// Delete metric rows older than `retention_days`. `0` disables the reaper
-/// (returns 0 without touching the table). Mirrors `jobs::reap_done`.
+/// (returns 0 without touching the table). Mirrors `jobs::reap_terminal`.
 pub async fn reap(pool: &PgPool, retention_days: u32) -> sqlx::Result<u64> {
     if retention_days == 0 {
         return Ok(0);

backend/src/repo/crawler.rs

@@ -903,9 +903,8 @@ pub struct JobHistoryFilter<'a> {
 /// manga/chapter/page context (best-effort) so the table can label rows.
 /// Returns the page slice plus the filtered total for pagination.
 ///
-/// History depth is bounded by the done-job reaper (`reap_done`): completed
-/// jobs older than the retention window are gone. Terminal `dead` jobs
-/// persist until requeued.
+/// History depth is bounded by the terminal-job reaper (`reap_terminal`):
+/// `done` and `dead` jobs older than the retention window are gone.
 pub async fn list_job_history(
     pool: &PgPool,
     filter: JobHistoryFilter<'_>,

backend/tests/crawler_jobs.rs

@@ -718,42 +718,49 @@ async fn release_returns_to_pending_and_undoes_attempt_increment(pool: PgPool) {
 }
 
 #[sqlx::test(migrations = "./migrations")]
-async fn reap_done_deletes_old_rows_keeps_fresh(pool: PgPool) {
-    // Two done rows: one old (updated_at 10 days ago), one fresh.
-    let old_id = match jobs::enqueue(&pool, &chapter_content_payload(Uuid::new_v4()))
-        .await
-        .unwrap()
-    {
-        EnqueueResult::Inserted(id) => id,
-        _ => unreachable!(),
-    };
-    let fresh_id = match jobs::enqueue(&pool, &chapter_content_payload(Uuid::new_v4()))
-        .await
-        .unwrap()
-    {
-        EnqueueResult::Inserted(id) => id,
-        _ => unreachable!(),
-    };
+async fn reap_terminal_deletes_old_done_and_dead_keeps_fresh_and_active(pool: PgPool) {
+    // Helper: enqueue a fresh pending job and return its id.
+    async fn enqueue_one(pool: &PgPool) -> Uuid {
+        match jobs::enqueue(pool, &chapter_content_payload(Uuid::new_v4()))
+            .await
+            .unwrap()
+        {
+            EnqueueResult::Inserted(id) => id,
+            _ => unreachable!(),
+        }
+    }
 
+    let old_done = enqueue_one(&pool).await;
+    let old_dead = enqueue_one(&pool).await;
+    let fresh_done = enqueue_one(&pool).await;
+    let fresh_dead = enqueue_one(&pool).await;
+    let old_pending = enqueue_one(&pool).await;
+
+    // Old terminal rows (10 days) in both terminal states — both must reap.
     sqlx::query("UPDATE crawler_jobs SET state='done', updated_at = now() - interval '10 days' WHERE id = $1")
-        .bind(old_id)
-        .execute(&pool)
-        .await
-        .unwrap();
+        .bind(old_done).execute(&pool).await.unwrap();
+    sqlx::query("UPDATE crawler_jobs SET state='dead', updated_at = now() - interval '10 days' WHERE id = $1")
+        .bind(old_dead).execute(&pool).await.unwrap();
+    // Fresh terminal rows — inside the retention window, kept.
     sqlx::query("UPDATE crawler_jobs SET state='done' WHERE id = $1")
-        .bind(fresh_id)
-        .execute(&pool)
-        .await
-        .unwrap();
+        .bind(fresh_done).execute(&pool).await.unwrap();
+    sqlx::query("UPDATE crawler_jobs SET state='dead' WHERE id = $1")
+        .bind(fresh_dead).execute(&pool).await.unwrap();
+    // Old but still active (pending) — never reaped regardless of age.
+    sqlx::query("UPDATE crawler_jobs SET updated_at = now() - interval '10 days' WHERE id = $1")
+        .bind(old_pending).execute(&pool).await.unwrap();
 
-    let deleted = jobs::reap_done(&pool, 7).await.unwrap();
-    assert_eq!(deleted, 1);
+    let deleted = jobs::reap_terminal(&pool, 7).await.unwrap();
+    assert_eq!(deleted, 2, "both old done and old dead rows are reaped");
 
-    let remaining: Vec<Uuid> = sqlx::query_scalar("SELECT id FROM crawler_jobs ORDER BY id")
+    let mut remaining: Vec<Uuid> = sqlx::query_scalar("SELECT id FROM crawler_jobs")
         .fetch_all(&pool)
         .await
         .unwrap();
-    assert_eq!(remaining, vec![fresh_id], "only fresh row remains");
+    remaining.sort();
+    let mut expected = vec![fresh_done, fresh_dead, old_pending];
+    expected.sort();
+    assert_eq!(remaining, expected, "fresh terminal + active-pending rows survive");
 }
 
 #[sqlx::test(migrations = "./migrations")]
@@ -840,7 +847,7 @@ async fn lease_ties_on_scheduled_at_break_by_created_at(pool: PgPool) {
 }
 
 #[sqlx::test(migrations = "./migrations")]
-async fn reap_done_zero_is_a_no_op(pool: PgPool) {
+async fn reap_terminal_zero_is_a_no_op(pool: PgPool) {
     let id = match jobs::enqueue(&pool, &chapter_content_payload(Uuid::new_v4()))
         .await
         .unwrap()
@@ -854,7 +861,7 @@ async fn reap_done_zero_is_a_no_op(pool: PgPool) {
         .await
         .unwrap();
 
-    let deleted = jobs::reap_done(&pool, 0).await.unwrap();
+    let deleted = jobs::reap_terminal(&pool, 0).await.unwrap();
     assert_eq!(deleted, 0);
     assert_eq!(job_count(&pool).await, 1);
 }

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mangalord-frontend",
-  "version": "0.93.7",
+  "version": "0.93.8",
   "private": true,
   "type": "module",
   "scripts": {