test(backend): DB-backed tests for the risky SQL; test isolation; clippy cleanup

All 40 backend tests were pure-function tests — not one line of SQL ran under `cargo test`,
even though the riskiest code in the repo is SQL. Add 12 DB-backed `#[sqlx::test]` tests
(fresh throwaway DB per test, real migrations) pinning the invariants that code is
load-bearing for, each mutation-verified to fail on broken code:

  export_epoch.rs (8): epoch is post-increment on release (a worker born pre-increment is
    inert); epoch strictly monotonic across reopen; a retired-epoch worker's writes are
    no-ops; export_current is EXACTLY the invariant (8-case table); the ViewerOnly
    carry-forward carries a done ZIP forward AND matches nothing when the ZIP is unfinished
    (the af997a8 strand bug); boot recovery doesn't clobber a live ZIP.
  upload_concurrency.rs (4): the atomic quota UPDATE stops two stale-snapshot uploads from
    both committing (sequential AND concurrent-tx via EPQ); the FOR SHARE upload lock
    serializes against release, blocking a photo from committing after the export snapshot.

Deleting FOR SHARE, or the carry-forward's `status='done'`, each makes a test fail.

Test isolation: TRUNCATE now also resets disk_cache and sse_tickets. The stale disk
reading was harmless only while quotas were globally off in e2e (they no longer are — see
the new quota spec), i.e. two holes were masking each other.

clippy: `cargo clippy --all-targets -- -D warnings` now passes (it did not). Deleted the
dead jobs.rs (an unused BackgroundJob sketch) and unused model methods; `#[allow(dead_code)]`
+ comment on the sqlx FromRow field-sets that ARE populated by the DB. No SQL or logic
changed. `cargo test` requires DATABASE_URL by design.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/src/error.rs

@@ -75,10 +75,10 @@ impl IntoResponse for AppError {
         }
 
         let mut resp = (status, axum::Json(body)).into_response();
-        if let Some(secs) = retry_after_secs {
-            if let Ok(val) = axum::http::HeaderValue::from_str(&secs.to_string()) {
-                resp.headers_mut().insert(axum::http::header::RETRY_AFTER, val);
-            }
+        if let Some(secs) = retry_after_secs
+            && let Ok(val) = axum::http::HeaderValue::from_str(&secs.to_string())
+        {
+            resp.headers_mut().insert(axum::http::header::RETRY_AFTER, val);
         }
         resp
     }

backend/src/handlers/admin.rs

@@ -98,6 +98,10 @@ pub async fn get_config(
     Ok(Json(rows.into_iter().collect()))
 }
 
+/// Documents the wire shape of `PATCH /admin/config` (a flat `{key: value}` object).
+/// `patch_config` extracts the `HashMap` directly rather than going through this newtype, so it is
+/// never constructed in Rust — it stays as the serde-derived description of the request body.
+#[allow(dead_code)]
 #[derive(Deserialize)]
 pub struct PatchConfigRequest(pub HashMap<String, String>);
 

backend/src/handlers/test_admin.rs

@@ -85,6 +85,19 @@ pub async fn truncate_all(
     // could serve the previous test's toggles.
     state.config_cache.invalidate();
 
+    // The other two in-memory singletons that TRUNCATE used to leave standing.
+    //
+    // `disk_cache` holds a free-space reading for up to its TTL. TRUNCATE has just deleted every
+    // uploaded file, which materially changes free space — so without this the next test can
+    // compute a storage quota from the PREVIOUS test's disk. That was harmless only while quotas
+    // were globally disabled in e2e (they no longer are: see specs/02-upload/quota.spec.ts, which
+    // steers the per-user limit off `free_disk_bytes`), i.e. two holes were masking each other.
+    state.disk_cache.invalidate();
+
+    // `sse_tickets` maps a ticket to a session token hash. TRUNCATE deletes the sessions, so every
+    // surviving ticket is a dangling reference to a user that no longer exists.
+    state.sse_tickets.clear();
+
     Ok(StatusCode::NO_CONTENT)
 }
 

backend/src/handlers/upload.rs

@@ -168,14 +168,14 @@ pub async fn upload(
     // Validate caption length. Counted in chars (code points) to match the
     // "Zeichen" wording in the error message — `.len()` would be bytes and
     // reject perfectly valid German/emoji captions early.
-    if let Some(ref cap) = caption {
-        if cap.chars().count() > MAX_CAPTION_LENGTH {
-            let _ = tokio::fs::remove_file(&temp_abs).await;
-            return Err(AppError::BadRequest(format!(
-                "Beschreibung ist zu lang. Maximum: {} Zeichen.",
-                MAX_CAPTION_LENGTH
-            )));
-        }
+    if let Some(ref cap) = caption
+        && cap.chars().count() > MAX_CAPTION_LENGTH
+    {
+        let _ = tokio::fs::remove_file(&temp_abs).await;
+        return Err(AppError::BadRequest(format!(
+            "Beschreibung ist zu lang. Maximum: {} Zeichen.",
+            MAX_CAPTION_LENGTH
+        )));
     }
 
     // Determine the file type from its magic bytes and require it to be on the
@@ -555,6 +555,9 @@ pub struct QuotaEstimate {
     pub limit_bytes: Option<i64>,
     pub active_uploaders: i64,
     pub free_disk_bytes: i64,
+    /// The tolerance factor the limit above was computed with. Carried on the snapshot so the
+    /// number is self-describing; no caller reads it back today.
+    #[allow(dead_code)]
     pub tolerance: f64,
 }
 

backend/src/models/comment.rs

@@ -3,6 +3,10 @@ use serde::Serialize;
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `comment`: every field is populated by sqlx from `SELECT *` / `RETURNING *`.
+// `deleted_at` is not read in Rust today (the soft-delete filter lives in SQL), but it is part of
+// the row and stays here so the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Comment {
     pub id: Uuid,
@@ -87,16 +91,8 @@ impl Comment {
         .await
     }
 
-    pub async fn soft_delete(pool: &PgPool, id: Uuid) -> Result<(), sqlx::Error> {
-        sqlx::query("UPDATE comment SET deleted_at = NOW() WHERE id = $1")
-            .bind(id)
-            .execute(pool)
-            .await?;
-        Ok(())
-    }
-
-    /// Event-scoped variant of [`Self::soft_delete`]. Returns `false` if the
-    /// comment doesn't exist or belongs to a different event.
+    /// Event-scoped soft delete. Returns `false` if the comment doesn't exist or belongs to a
+    /// different event.
     /// Executor-generic so the delete and the keepsake regeneration can share one transaction
     /// (see `Upload::soft_delete_in_event` for why that must be atomic).
     pub async fn soft_delete_in_event(

backend/src/models/event.rs

@@ -2,6 +2,11 @@ use chrono::{DateTime, Utc};
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `event`: every field is populated by sqlx from `SELECT *` / `RETURNING *`. Several
+// (`slug`, `cover_image_path`, `export_epoch`, `created_at`) are not read through this struct today
+// — callers that need them query the column directly — but they are part of the row and stay here so
+// the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Event {
     pub id: Uuid,

backend/src/models/hashtag.rs

@@ -1,6 +1,8 @@
-use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `hashtag`, populated by sqlx from `RETURNING *` in `upsert`. Callers only use
+// `id` today; `event_id`/`tag` are the rest of the row and stay part of the struct.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Hashtag {
     pub id: Uuid,
@@ -61,22 +63,6 @@ impl Hashtag {
             .await?;
         Ok(())
     }
-
-    pub async fn tags_for_upload(
-        pool: &PgPool,
-        upload_id: Uuid,
-    ) -> Result<Vec<String>, sqlx::Error> {
-        let rows: Vec<(String,)> = sqlx::query_as(
-            "SELECT h.tag FROM hashtag h
-             JOIN upload_hashtag uh ON uh.hashtag_id = h.id
-             WHERE uh.upload_id = $1
-             ORDER BY h.tag",
-        )
-        .bind(upload_id)
-        .fetch_all(pool)
-        .await?;
-        Ok(rows.into_iter().map(|r| r.0).collect())
-    }
 }
 
 /// Extract `#hashtags` from text (caption or body). Tags are restricted to

backend/src/models/session.rs

@@ -2,6 +2,9 @@ use chrono::{DateTime, Utc};
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `session`, populated by sqlx from `RETURNING *`. Session validation is done in SQL
+// (expiry/last-seen predicates), so no field is read in Rust — the struct is the row's shape.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Session {
     pub id: Uuid,

backend/src/models/upload.rs

@@ -3,6 +3,10 @@ use serde::Serialize;
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `upload`: every field is populated by sqlx from `RETURNING *` in `create`. Callers
+// mostly use `id` and hand the rest to the compression/feed queries, so most fields are never read
+// through this struct — they stay here so it keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Upload {
     pub id: Uuid,
@@ -75,15 +79,6 @@ impl Upload {
         .await
     }
 
-    pub async fn find_by_id(pool: &PgPool, id: Uuid) -> Result<Option<Self>, sqlx::Error> {
-        sqlx::query_as::<_, Self>(
-            "SELECT * FROM upload WHERE id = $1 AND deleted_at IS NULL",
-        )
-        .bind(id)
-        .fetch_optional(pool)
-        .await
-    }
-
     /// Lean lookup for the public media aliases (`get_original`/`get_preview`/
     /// `get_thumbnail`): returns ONLY the file paths + mime for a visible upload —
     /// excluding soft-deleted rows, hidden owners (`uploads_hidden`), and banned owners

backend/src/models/user.rs

@@ -22,6 +22,10 @@ impl UserRole {
     }
 }
 
+// Row shape for `user`: every field is populated by sqlx from `SELECT *` / `RETURNING *`.
+// `uploads_hidden`, `failed_pin_attempts` and `created_at` are enforced/updated in SQL rather than
+// read in Rust, but they are part of the row and stay here so the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct User {
     pub id: Uuid,

backend/src/services/disk.rs

@@ -34,6 +34,17 @@ impl DiskCache {
         }
     }
 
+    /// Drop the cached reading so the next `snapshot()` re-measures the filesystem.
+    ///
+    /// Used by the e2e TRUNCATE endpoint. Truncating deletes every uploaded file, which materially
+    /// changes free space — but the cached reading survives for up to the TTL, so the next test can
+    /// compute a quota from the PREVIOUS test's disk. That matters now that the quota tests steer
+    /// the per-user limit off `free_disk_bytes`: a stale reading makes the limit wrong and the test
+    /// flaky, for reasons that have nothing to do with the code under test.
+    pub fn invalidate(&self) {
+        *self.inner.write().unwrap() = None;
+    }
+
     /// Cached `(total, free)` bytes for the filesystem that holds `media_path`.
     ///
     /// Returns `None` when the mount can't be resolved — callers MUST treat that as
@@ -47,10 +58,11 @@ impl DiskCache {
     /// caller to ask about a different volume (e.g. the exports volume, which is a separate mount)
     /// would have silently got the wrong filesystem's free space.
     pub fn snapshot(&self, path: &Path) -> Option<DiskInfo> {
-        if let Some((cached_path, info, at)) = self.inner.read().unwrap().as_ref() {
-            if cached_path == path && at.elapsed() < TTL {
-                return Some(*info);
-            }
+        if let Some((cached_path, info, at)) = self.inner.read().unwrap().as_ref()
+            && cached_path == path
+            && at.elapsed() < TTL
+        {
+            return Some(*info);
         }
         let info = read_disk_for_path(path)?;
         *self.inner.write().unwrap() = Some((path.to_path_buf(), info, Instant::now()));

backend/src/services/export.rs

@@ -389,6 +389,10 @@ async fn invalidate_missing_files(
 /// start immediately.
 pub const REGEN_DEBOUNCE: Duration = Duration::from_secs(20);
 
+// Export worker entry point: every argument is state the spawned worker is BORN with (notably
+// `epoch`). Bundling them into a struct would be a pure-refactor risk on the epoch logic for no
+// gain, so the arity stands.
+#[allow(clippy::too_many_arguments)]
 pub fn spawn_export_jobs(
     event_id: Uuid,
     event_name: String,

backend/src/services/mod.rs

@@ -2,7 +2,6 @@ pub mod compression;
 pub mod config;
 pub mod disk;
 pub mod export;
-pub mod jobs;
 pub mod maintenance;
 pub mod rate_limiter;
 pub mod sse_tickets;

backend/src/services/rate_limiter.rs

@@ -123,12 +123,58 @@ mod tests {
         assert!(rl.check("k", 1, w), "the slot should expire once the window passes");
     }
 
+    /// `retry_after` is not a "some number in range" — it is the time until the oldest slot
+    /// in the window frees up, and it is surfaced to clients as the backoff they sleep for
+    /// (see `upload-queue.ts`). Asserting only `(1..=60)` spans the entire reachable domain
+    /// of a 60s window, so a hardcoded `Err(1)` would satisfy it while telling every client
+    /// to hammer the server a second later. Pin the actual value.
     #[test]
-    fn retry_after_is_between_one_and_window() {
+    fn retry_after_is_the_remaining_window() {
         let rl = RateLimiter::new();
-        assert!(rl.check_with_retry("k", 1, MIN).is_ok());
-        let retry = rl.check_with_retry("k", 1, MIN).unwrap_err();
-        assert!((1..=60).contains(&retry), "retry_after {retry} out of range");
+
+        // The slot was consumed just now, so essentially the whole window remains.
+        // `as_secs()` truncates the sub-second remainder, so a 30s window reports 29.
+        let w30 = Duration::from_secs(30);
+        assert!(rl.check_with_retry("a", 1, w30).is_ok());
+        let a = rl.check_with_retry("a", 1, w30).unwrap_err();
+        assert_eq!(a, 29, "retry_after must be the remaining window, got {a}");
+
+        // A different window must yield a different retry_after: no single constant can
+        // satisfy both this and the assertion above.
+        let w10 = Duration::from_secs(10);
+        assert!(rl.check_with_retry("b", 1, w10).is_ok());
+        let b = rl.check_with_retry("b", 1, w10).unwrap_err();
+        assert_eq!(b, 9, "retry_after must scale with the window, got {b}");
+    }
+
+    #[test]
+    fn retry_after_counts_down_as_the_window_elapses() {
+        let rl = RateLimiter::new();
+        let w = Duration::from_secs(30);
+        assert!(rl.check_with_retry("k", 1, w).is_ok());
+        let first = rl.check_with_retry("k", 1, w).unwrap_err();
+
+        std::thread::sleep(Duration::from_millis(1200));
+        let second = rl.check_with_retry("k", 1, w).unwrap_err();
+
+        // A client that waits 1.2s must be told to wait ~1.2s less — otherwise the advertised
+        // backoff is a constant, not a deadline.
+        let shaved = first - second;
+        assert!(
+            (1..=2).contains(&shaved),
+            "1.2s of waiting must shorten the advertised backoff by ~1s (got {first} then {second})"
+        );
+    }
+
+    #[test]
+    fn retry_after_floors_at_one_second() {
+        let rl = RateLimiter::new();
+        let w = Duration::from_millis(800);
+        assert!(rl.check_with_retry("k", 1, w).is_ok());
+        let retry = rl.check_with_retry("k", 1, w).unwrap_err();
+        // The sub-second remainder truncates to 0; clients must never be told "retry in 0s"
+        // (that's a busy-loop). The `.max(1)` floor is what prevents it.
+        assert_eq!(retry, 1, "a sub-second remainder must floor to 1, got {retry}");
     }
 
     #[test]
@@ -140,6 +186,59 @@ mod tests {
         assert!(rl.check("k", 1, MIN), "clear() must free the window");
     }
 
+    /// `prune()` is a memory-leak guard: without it a long-lived process keeps one HashMap
+    /// entry per IP that ever connected. Nothing in the public API observes the map size, so
+    /// the only way to catch a no-op body (`fn prune(&self) {}`) is to look at the map — the
+    /// tests module can see the private field.
+    #[test]
+    fn prune_drops_keys_whose_windows_have_fully_expired() {
+        let rl = RateLimiter::new();
+
+        // A key whose only timestamp is older than the 24h ceiling. We can't sleep for a day,
+        // so backdate the Instant directly.
+        let ancient = Instant::now()
+            .checked_sub(Duration::from_secs(25 * 60 * 60))
+            .expect("backdating an Instant by 25h");
+        rl.windows
+            .lock()
+            .unwrap()
+            .insert("stale".to_string(), vec![ancient]);
+
+        // ...alongside a key that is still inside its window.
+        assert!(rl.check("live", 5, MIN));
+        assert_eq!(rl.windows.lock().unwrap().len(), 2);
+
+        rl.prune();
+
+        let map = rl.windows.lock().unwrap();
+        assert!(
+            !map.contains_key("stale"),
+            "prune() must drop keys whose timestamps have all expired"
+        );
+        assert!(
+            map.contains_key("live"),
+            "prune() must keep keys that still have live timestamps"
+        );
+        assert_eq!(map.len(), 1, "exactly one key should survive the prune");
+    }
+
+    #[test]
+    fn prune_does_not_reset_a_live_window() {
+        // The counterpart to the test above: pruning must reclaim memory, never quota. If
+        // prune() dropped live keys, every background sweep would hand attackers a fresh
+        // budget.
+        let rl = RateLimiter::new();
+        assert!(rl.check("k", 1, MIN));
+        assert!(!rl.check("k", 1, MIN));
+
+        rl.prune();
+
+        assert!(
+            !rl.check("k", 1, MIN),
+            "prune() must not clear a window that is still active"
+        );
+    }
+
     #[test]
     fn client_ip_takes_rightmost_forwarded_for_entry() {
         // The right-most entry is the hop our trusted proxy (Caddy) appended.

backend/src/services/sse_tickets.rs

@@ -31,6 +31,13 @@ impl SseTicketStore {
         }
     }
 
+    /// Drop every outstanding ticket. Used by the e2e TRUNCATE endpoint: tickets are bound to a
+    /// session token hash, and TRUNCATE deletes the sessions out from under them, so anything left
+    /// here is a dangling reference to a user that no longer exists.
+    pub fn clear(&self) {
+        self.inner.lock().unwrap().clear();
+    }
+
     /// Mint a new ticket bound to the caller's session (identified by token hash).
     pub fn issue(&self, token_hash: String) -> String {
         let ticket = random_ticket();

backend/tests/common/mod.rs

@@ -0,0 +1,257 @@
+//! Shared fixtures for the DB-backed integration tests.
+//!
+//! Every helper here executes SQL that is **character-for-character identical** to what `src/`
+//! actually runs (see the `// SRC:` markers). That is the whole point: a paraphrased query is a
+//! query nobody runs, and a test that passes against a paraphrase proves nothing about production.
+
+#![allow(dead_code)] // each integration-test crate uses a different subset of these helpers
+
+use sqlx::PgPool;
+use uuid::Uuid;
+
+/// Insert a bare, unreleased event (epoch 0, uploads open).
+pub async fn seed_event(pool: &PgPool, slug: &str) -> Uuid {
+    sqlx::query_scalar("INSERT INTO event (slug, name) VALUES ($1, $2) RETURNING id")
+        .bind(slug)
+        .bind("Hochzeit")
+        .fetch_one(pool)
+        .await
+        .expect("seed event")
+}
+
+/// Insert a guest with a zeroed byte total.
+pub async fn seed_user(pool: &PgPool, event_id: Uuid, name: &str) -> Uuid {
+    sqlx::query_scalar(
+        "INSERT INTO \"user\" (event_id, display_name, recovery_pin_hash)
+         VALUES ($1, $2, 'x') RETURNING id",
+    )
+    .bind(event_id)
+    .bind(name)
+    .fetch_one(pool)
+    .await
+    .expect("seed user")
+}
+
+/// SRC: `handlers/host.rs::release_gallery` — the claim + epoch bump, verbatim.
+/// Returns the POST-increment epoch, exactly as the handler consumes it.
+pub async fn release_gallery(pool: &PgPool, slug: &str) -> Option<i64> {
+    let claimed: Option<(Uuid, String, i64)> = sqlx::query_as(
+        "UPDATE event
+         SET export_released_at = NOW(),
+             uploads_locked_at  = COALESCE(uploads_locked_at, NOW()),
+             export_epoch       = export_epoch + 1
+         WHERE slug = $1 AND export_released_at IS NULL
+         RETURNING id, name, export_epoch",
+    )
+    .bind(slug)
+    .fetch_optional(pool)
+    .await
+    .expect("release_gallery");
+
+    if let Some((event_id, _, epoch)) = claimed {
+        // The handler arms both jobs in the SAME transaction; for a single-connection fixture the
+        // sequencing is equivalent.
+        let mut conn = pool.acquire().await.expect("acquire");
+        enqueue_types_at_epoch(&mut conn, event_id, epoch, &["zip", "html"]).await;
+        Some(epoch)
+    } else {
+        None
+    }
+}
+
+/// SRC: `handlers/host.rs::open_event` — the one statement that retires an entire generation.
+/// Returns rows affected.
+pub async fn open_event(pool: &PgPool, slug: &str) -> u64 {
+    sqlx::query(
+        "UPDATE event
+         SET uploads_locked_at  = NULL,
+             export_released_at = NULL,
+             export_epoch       = export_epoch + 1
+         WHERE slug = $1 AND (uploads_locked_at IS NOT NULL OR export_released_at IS NOT NULL)",
+    )
+    .bind(slug)
+    .execute(pool)
+    .await
+    .expect("open_event")
+    .rows_affected()
+}
+
+/// SRC: `services/export.rs::enqueue_types_at_epoch` — verbatim upsert.
+pub async fn enqueue_types_at_epoch(
+    conn: &mut sqlx::PgConnection,
+    event_id: Uuid,
+    epoch: i64,
+    types: &[&str],
+) {
+    for export_type in types {
+        sqlx::query(
+            "INSERT INTO export_job (event_id, type, status, progress_pct, epoch)
+             VALUES ($1, $2::export_type, 'pending', 0, $3)
+             ON CONFLICT (event_id, type) DO UPDATE
+                 SET status = 'pending', progress_pct = 0, file_path = NULL,
+                     error_message = NULL, completed_at = NULL,
+                     epoch = EXCLUDED.epoch
+             WHERE export_job.status <> 'done' OR export_job.epoch <> EXCLUDED.epoch",
+        )
+        .bind(event_id)
+        .bind(export_type)
+        .bind(epoch)
+        .execute(&mut *conn)
+        .await
+        .expect("enqueue_types_at_epoch");
+    }
+}
+
+/// SRC: `services/export.rs::claim_job` — verbatim. `true` = we won the generation.
+pub async fn claim_job(pool: &PgPool, event_id: Uuid, export_type: &str, epoch: i64) -> bool {
+    sqlx::query(
+        "UPDATE export_job SET status = 'running'
+         WHERE event_id = $1 AND type = $2::export_type
+           AND epoch = $3 AND status = 'pending'",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .bind(epoch)
+    .execute(pool)
+    .await
+    .expect("claim_job")
+    .rows_affected()
+        > 0
+}
+
+/// SRC: `services/export.rs::finalize_job` — verbatim. This IS the publish step.
+pub async fn finalize_job(
+    pool: &PgPool,
+    event_id: Uuid,
+    export_type: &str,
+    epoch: i64,
+    file_path: &str,
+) -> bool {
+    sqlx::query(
+        "UPDATE export_job
+         SET status = 'done', progress_pct = 100, file_path = $3, completed_at = NOW()
+         WHERE event_id = $1 AND type = $2::export_type
+           AND epoch = $4 AND status = 'running'",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .bind(file_path)
+    .bind(epoch)
+    .execute(pool)
+    .await
+    .expect("finalize_job")
+    .rows_affected()
+        > 0
+}
+
+/// SRC: `services/export.rs::update_progress` — verbatim. Doubles as the worker's liveness check:
+/// `false` means "your generation was retired, stop working".
+pub async fn update_progress(
+    pool: &PgPool,
+    event_id: Uuid,
+    export_type: &str,
+    epoch: i64,
+    pct: i16,
+) -> bool {
+    sqlx::query(
+        "UPDATE export_job SET progress_pct = $3
+         WHERE event_id = $1 AND type = $2::export_type
+           AND epoch = $4 AND status = 'running'",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .bind(pct)
+    .bind(epoch)
+    .execute(pool)
+    .await
+    .expect("update_progress")
+    .rows_affected()
+        > 0
+}
+
+/// SRC: `services/export.rs::invalidate_and_arm` — the ViewerOnly ZIP carry-forward, verbatim.
+/// Returns `rows_affected() == 1`, which is what the production code branches on.
+pub async fn carry_zip_forward(pool: &PgPool, event_id: Uuid, epoch: i64) -> bool {
+    sqlx::query(
+        "UPDATE export_job SET epoch = $2
+         WHERE event_id = $1 AND type = 'zip'::export_type
+           AND status = 'done' AND epoch = $2 - 1",
+    )
+    .bind(event_id)
+    .bind(epoch)
+    .execute(pool)
+    .await
+    .expect("carry_zip_forward")
+    .rows_affected()
+        == 1
+}
+
+/// SRC: `services/export.rs::invalidate_and_arm` — the epoch bump, verbatim.
+pub async fn bump_epoch(pool: &PgPool, slug: &str) -> Option<(Uuid, String, i64)> {
+    sqlx::query_as(
+        "UPDATE event SET export_epoch = export_epoch + 1
+         WHERE slug = $1 AND export_released_at IS NOT NULL
+         RETURNING id, name, export_epoch",
+    )
+    .bind(slug)
+    .fetch_optional(pool)
+    .await
+    .expect("bump_epoch")
+}
+
+/// The event's authoritative epoch.
+pub async fn event_epoch(pool: &PgPool, event_id: Uuid) -> i64 {
+    sqlx::query_scalar("SELECT export_epoch FROM event WHERE id = $1")
+        .bind(event_id)
+        .fetch_one(pool)
+        .await
+        .expect("event_epoch")
+}
+
+/// The raw job row, bypassing `export_current` — what the WORKER sees.
+pub async fn job_row(
+    pool: &PgPool,
+    event_id: Uuid,
+    export_type: &str,
+) -> Option<(String, i64, Option<String>)> {
+    sqlx::query_as(
+        "SELECT status::text, epoch, file_path FROM export_job
+          WHERE event_id = $1 AND type = $2::export_type",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .fetch_optional(pool)
+    .await
+    .expect("job_row")
+}
+
+/// Does `export_current` expose this job at all? (The view itself, without the `status` filter —
+/// it is what `handlers/admin.rs::export_status` reports to the host UI.)
+pub async fn in_export_current(pool: &PgPool, event_id: Uuid, export_type: &str) -> bool {
+    sqlx::query_scalar::<_, i64>(
+        "SELECT COUNT(*) FROM export_current
+          WHERE event_id = $1 AND type = $2::export_type",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .fetch_one(pool)
+    .await
+    .expect("in_export_current")
+        > 0
+}
+
+/// THE download predicate. SRC: `handlers/admin.rs::download_export` reads exactly this shape —
+/// `SELECT c.file_path FROM export_current c WHERE ... AND c.status = 'done'`. If this returns
+/// `Some`, a guest can download the keepsake; if `None`, they get a 404.
+pub async fn downloadable(pool: &PgPool, event_id: Uuid, export_type: &str) -> Option<String> {
+    sqlx::query_scalar(
+        "SELECT c.file_path FROM export_current c
+          WHERE c.event_id = $1 AND c.type = $2::export_type AND c.status = 'done'",
+    )
+    .bind(event_id)
+    .bind(export_type)
+    .fetch_optional(pool)
+    .await
+    .expect("downloadable")
+    .flatten()
+}

backend/tests/export_epoch.rs

@@ -0,0 +1,363 @@
+//! DB-backed integration tests for the export epoch state machine (migration 014).
+//!
+//! These run against a REAL Postgres: `#[sqlx::test]` creates a throwaway database per test and
+//! runs `backend/migrations/` into it, so the schema, the enums, the `UNIQUE (event_id, type)`
+//! constraint and the `export_current` view are the production ones — not a mock.
+//!
+//! THE INVARIANT, from migration 014:
+//!
+//!     An export is downloadable IFF
+//!         event.export_released_at IS NOT NULL
+//!     AND export_job.epoch = event.export_epoch
+//!     AND export_job.status = 'done'
+//!
+//! Readiness is DERIVED (the `export_current` view), never stored. Every test below pins one leg of
+//! that invariant with the exact SQL `src/` executes (see `tests/common/mod.rs`).
+
+mod common;
+
+use common::*;
+use sqlx::PgPool;
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 1. Epoch monotonicity
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// Release, reopen and re-release each bump `export_epoch`, and `RETURNING export_epoch` hands the
+/// caller the POST-increment value.
+///
+/// PREVENTS: a worker born with the PRE-increment epoch. It would be inert from the instant it
+/// started — every one of its writes is `epoch`-guarded, so `claim_job`/`finalize_job` would match
+/// nothing, the job row would sit at `pending` 0% forever with no live worker, and the host's
+/// download button would spin and then 404. The keepsake would never be built at all.
+#[sqlx::test]
+async fn release_returns_post_increment_epoch(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    assert_eq!(event_epoch(&pool, event_id).await, 0, "a fresh event starts at epoch 0");
+
+    let released = release_gallery(&pool, "wedding").await.expect("release claims the event");
+    assert_eq!(released, 1, "RETURNING must give the epoch AFTER the +1, not before");
+    assert_eq!(event_epoch(&pool, event_id).await, released, "worker's epoch == event's epoch");
+
+    // The jobs armed by the release carry exactly that epoch — this is what makes the worker's
+    // guarded writes match.
+    for t in ["zip", "html"] {
+        let (status, epoch, _) = job_row(&pool, event_id, t).await.expect("job armed");
+        assert_eq!(status, "pending");
+        assert_eq!(epoch, released, "{t} job must be armed at the epoch the worker was born with");
+    }
+}
+
+/// Epoch is strictly monotonic across the whole release/reopen/re-release cycle, and a second
+/// release attempt while already released is rejected WITHOUT bumping.
+///
+/// PREVENTS: epoch reuse. If a reopen could return the event to an epoch some old `done` row still
+/// carries, a retired keepsake — one that a guest asked to be taken down from — would silently
+/// become downloadable again.
+#[sqlx::test]
+async fn epoch_is_strictly_monotonic_across_reopen(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+
+    assert_eq!(release_gallery(&pool, "wedding").await, Some(1));
+
+    // A duplicate release is a no-op (`WHERE export_released_at IS NULL`) and must NOT bump.
+    assert_eq!(release_gallery(&pool, "wedding").await, None, "already released");
+    assert_eq!(event_epoch(&pool, event_id).await, 1, "a rejected release must not move the epoch");
+
+    // Reopen retires the generation with ONE write.
+    assert_eq!(open_event(&pool, "wedding").await, 1);
+    assert_eq!(event_epoch(&pool, event_id).await, 2, "reopen bumps");
+
+    // And re-releasing bumps again — never back to 1.
+    assert_eq!(release_gallery(&pool, "wedding").await, Some(3), "re-release bumps again");
+    assert_eq!(event_epoch(&pool, event_id).await, 3);
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 2. A retired-epoch worker is inert
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// A worker holding a retired epoch cannot write anything anybody can see: once the rows have been
+/// re-armed at a newer epoch, its `update_progress` and `finalize_job` both match 0 rows, and
+/// `export_current` never exposes its output.
+///
+/// PREVENTS: the classic lost race — a slow worker from BEFORE a takedown finishing afterwards and
+/// publishing an archive that still contains the photo a guest asked to have removed. "Please take
+/// my photo out" is the one request that most needs to reach the keepsake, and the keepsake is the
+/// artifact people keep forever.
+#[sqlx::test]
+async fn retired_epoch_worker_writes_are_no_ops(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let old_epoch = release_gallery(&pool, "wedding").await.unwrap();
+
+    // Worker A is born at epoch 1 and claims the ZIP.
+    assert!(claim_job(&pool, event_id, "zip", old_epoch).await, "worker A wins its claim");
+    assert!(update_progress(&pool, event_id, "zip", old_epoch, 40).await, "still live at 40%");
+
+    // ── A takedown lands mid-export: `invalidate_and_arm(Affects::Both)` bumps and re-arms. ──
+    let (_, _, new_epoch) = bump_epoch(&pool, "wedding").await.expect("bump on a released event");
+    assert_eq!(new_epoch, old_epoch + 1);
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, new_epoch, &["zip", "html"]).await;
+    drop(conn);
+
+    // Worker A is now INERT BY CONSTRUCTION. Every write is guarded on its own birth epoch.
+    assert!(
+        !update_progress(&pool, event_id, "zip", old_epoch, 90).await,
+        "the liveness check must report `false` so worker A stops grinding through the gallery"
+    );
+    assert!(
+        !finalize_job(&pool, event_id, "zip", old_epoch, "exports/Gallery.1.zip").await,
+        "worker A's finalize MUST affect 0 rows — this is the write that would have published a \
+         keepsake still containing the taken-down photo"
+    );
+
+    // The re-armed row is untouched by the loser: still pending at the LIVE epoch, waiting for the
+    // fresh worker. (If worker A had won, this row would read `done` at epoch 1.)
+    let (status, epoch, file_path) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!((status.as_str(), epoch), ("pending", new_epoch));
+    assert_eq!(file_path, None, "the loser's file_path must never be recorded");
+
+    // And nothing is downloadable — not the stale archive, not anything.
+    assert_eq!(downloadable(&pool, event_id, "zip").await, None);
+}
+
+/// The documented, deliberate nuance in `claim_job`: after a bare `open_event` (which writes
+/// NOTHING to `export_job` — that is the point of the design), a worker at the old epoch still WINS
+/// its claim and can still write `done`. That is wasted work, not incorrectness: retirement is
+/// enforced at READ time. `export_current` must refuse to expose the row.
+///
+/// PREVENTS: someone "optimising" `claim_job` into a cross-table `EXISTS (SELECT ... FROM event)`
+/// guard — the exact unsound guard migration 014 removed (under READ COMMITTED, a blocked UPDATE
+/// re-evaluates same-row predicates but answers other-table subqueries from a stale snapshot).
+/// This test pins the read-time enforcement so the write-time guard is never re-added.
+#[sqlx::test]
+async fn reopen_retires_at_read_time_not_write_time(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let epoch = release_gallery(&pool, "wedding").await.unwrap();
+
+    assert!(claim_job(&pool, event_id, "zip", epoch).await);
+
+    // Host reopens uploads. No export_job row is touched.
+    assert_eq!(open_event(&pool, "wedding").await, 1);
+
+    // The in-flight worker's row-local writes still match — it was never told to stop.
+    assert!(
+        finalize_job(&pool, event_id, "zip", epoch, "exports/Gallery.1.zip").await,
+        "documented: the claim/finalize is guarded on the JOB row's epoch, not the event's"
+    );
+    let (status, _, _) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!(status, "done", "the row really does say done");
+
+    // …and yet it is invisible. `export_current` requires the event to be released AND the epochs to
+    // match; the reopen broke both. A worker at a dead epoch writes a row nobody can see.
+    assert!(!in_export_current(&pool, event_id, "zip").await);
+    assert_eq!(
+        downloadable(&pool, event_id, "zip").await,
+        None,
+        "a reopened event must serve NO keepsake, however finished the job row looks"
+    );
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 3. `export_current` exactness (table-driven)
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// The view is the ONE definition of "downloadable". Released + `done` + matching epoch ⇒ present;
+/// break ANY single leg ⇒ absent. Nothing else may make it appear or disappear.
+///
+/// PREVENTS, leg by leg:
+///  * `released` — serving a keepsake for an event whose uploads are still open, i.e. an archive
+///    missing every photo taken after the snapshot.
+///  * `done` — handing out a half-written ZIP (a corrupt keepsake, downloaded once, kept forever).
+///  * `epoch` — the retired-generation download: the 404-forever keepsake, or worse, the archive
+///    still containing content that was taken down.
+#[sqlx::test]
+async fn export_current_is_exactly_the_invariant(pool: PgPool) {
+    // (name, released?, status, job epoch offset from the event epoch, expected visible)
+    let cases: &[(&str, bool, &str, i64, bool)] = &[
+        ("released + done + current epoch", true, "done", 0, true),
+        ("NOT released (done, epoch matches)", false, "done", 0, false),
+        ("NOT done: pending", true, "pending", 0, false),
+        ("NOT done: running", true, "running", 0, false),
+        ("NOT done: failed", true, "failed", 0, false),
+        ("stale epoch (done, released)", true, "done", -1, false),
+        ("future epoch (done, released)", true, "done", 1, false),
+        ("migration-014 retired sentinel epoch -1", true, "done", -2, false),
+    ];
+
+    for (i, (name, released, status, offset, expect_visible)) in cases.iter().enumerate() {
+        let slug = format!("case{i}");
+        let event_id = seed_event(&pool, &slug).await;
+
+        // Get the event to a known epoch (1) either by releasing it, or — for the unreleased case —
+        // by releasing and reopening, which leaves it unreleased at a non-zero epoch.
+        let event_epoch_now = if *released {
+            release_gallery(&pool, &slug).await.unwrap()
+        } else {
+            release_gallery(&pool, &slug).await.unwrap();
+            open_event(&pool, &slug).await;
+            event_epoch(&pool, event_id).await
+        };
+
+        // Plant a single ZIP job row in the exact state under test. `-2` encodes "the sentinel the
+        // migration stamps on retired rows", which must never equal a non-negative event epoch.
+        // (Clear the rows the release armed first — `UNIQUE (event_id, type)`.)
+        sqlx::query("DELETE FROM export_job WHERE event_id = $1")
+            .bind(event_id)
+            .execute(&pool)
+            .await
+            .expect("clear armed jobs");
+
+        let job_epoch = if *offset == -2 { -1 } else { event_epoch_now + offset };
+        sqlx::query(
+            "INSERT INTO export_job (event_id, type, status, progress_pct, epoch, file_path)
+             VALUES ($1, 'zip', $2::export_status, 100, $3, 'exports/Gallery.zip')",
+        )
+        .bind(event_id)
+        .bind(*status)
+        .bind(job_epoch)
+        .execute(&pool)
+        .await
+        .expect("plant job row");
+
+        let visible = downloadable(&pool, event_id, "zip").await.is_some();
+        assert_eq!(
+            visible, *expect_visible,
+            "export_current exactness violated for case: {name} \
+             (released={released}, status={status}, job_epoch={job_epoch}, event_epoch={event_epoch_now})"
+        );
+    }
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 4. The ViewerOnly ZIP carry-forward
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// Branch A — the ZIP is `done` at the outgoing epoch: the carry-forward re-stamps it to the new
+/// epoch (rows_affected = 1), so only the HTML viewer is rebuilt and the finished ZIP stays
+/// downloadable throughout.
+///
+/// PREVENTS: rebuilding a multi-GB archive because someone deleted a comment. The ZIP holds media,
+/// not comments — a needless rebuild would 404 the photo download for minutes to change nothing
+/// inside it.
+#[sqlx::test]
+async fn viewer_only_carries_a_done_zip_forward(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let e1 = release_gallery(&pool, "wedding").await.unwrap();
+
+    // Both halves finish at epoch 1 — the keepsake is live.
+    for t in ["zip", "html"] {
+        assert!(claim_job(&pool, event_id, t, e1).await);
+        assert!(finalize_job(&pool, event_id, t, e1, &format!("exports/{t}.{e1}.zip")).await);
+    }
+    let zip_file = downloadable(&pool, event_id, "zip").await.expect("zip is live");
+
+    // ── A comment is moderated: invalidate_and_arm(Affects::ViewerOnly). ──
+    let (_, _, e2) = bump_epoch(&pool, "wedding").await.unwrap();
+    let carried = carry_zip_forward(&pool, event_id, e2).await;
+    assert!(carried, "a `done` ZIP at epoch-1 MUST be carried forward (rows_affected == 1)");
+
+    // Only the viewer is re-armed…
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, e2, &["html"]).await;
+    drop(conn);
+
+    // …and the ZIP is STILL DOWNLOADABLE, at the new epoch, pointing at the same, unrenamed file.
+    let (status, epoch, _) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!((status.as_str(), epoch), ("done", e2), "the ZIP row rode the epoch bump");
+    assert_eq!(
+        downloadable(&pool, event_id, "zip").await,
+        Some(zip_file),
+        "the carried archive must never stop being served — same file, new epoch"
+    );
+
+    // The viewer, meanwhile, is correctly retired and pending a rebuild.
+    assert_eq!(job_row(&pool, event_id, "html").await.unwrap().0, "pending");
+    assert_eq!(downloadable(&pool, event_id, "html").await, None);
+}
+
+/// Branch B — THE BUG WE JUST FIXED. If the ZIP is still `pending`/`running` when the comment is
+/// moderated (which is MINUTES for a real multi-GB gallery, and deleting a comment right after
+/// release is an utterly ordinary thing to do), the carry-forward matches NOTHING
+/// (rows_affected = 0) — so the caller must NOT assume it carried, and must re-arm the ZIP too.
+///
+/// PREVENTS: the stranded ZIP. Blindly re-arming only the viewer would leave the ZIP row at the
+/// retired epoch; the in-flight worker then finishes and writes `done` at an epoch `export_current`
+/// no longer matches, nothing ever re-arms it, and `GET /export/zip` 404s FOREVER — a keepsake the
+/// couple paid for that simply never appears, short of a reboot.
+#[sqlx::test]
+async fn viewer_only_carry_forward_matches_nothing_when_zip_unfinished(pool: PgPool) {
+    for zip_state in ["pending", "running"] {
+        let slug = format!("wedding-{zip_state}");
+        let event_id = seed_event(&pool, &slug).await;
+        let e1 = release_gallery(&pool, &slug).await.unwrap();
+
+        // The ZIP worker is still going; only the viewer has finished.
+        if zip_state == "running" {
+            assert!(claim_job(&pool, event_id, "zip", e1).await);
+        }
+        assert!(claim_job(&pool, event_id, "html", e1).await);
+        assert!(finalize_job(&pool, event_id, "html", e1, "exports/Memories.1.zip").await);
+
+        // ── The comment is moderated. ──
+        let (_, _, e2) = bump_epoch(&pool, &slug).await.unwrap();
+        let carried = carry_zip_forward(&pool, event_id, e2).await;
+
+        assert!(
+            !carried,
+            "a {zip_state} ZIP has nothing to carry forward — the UPDATE must affect 0 rows \
+             (its `status = 'done'` predicate is the whole precondition)"
+        );
+
+        // The carry-forward's OWN result decides. It didn't match ⇒ rebuild the ZIP as well.
+        let types: &[&str] = if carried { &["html"] } else { &["zip", "html"] };
+        let mut conn = pool.acquire().await.unwrap();
+        enqueue_types_at_epoch(&mut conn, event_id, e2, types).await;
+        drop(conn);
+
+        // THE ASSERTION THAT WOULD HAVE CAUGHT THE BUG: the ZIP must not be stranded at the dead
+        // epoch. It is re-armed at the live one, so a fresh worker will actually build it.
+        let (status, epoch, _) = job_row(&pool, event_id, "zip").await.unwrap();
+        assert_eq!(
+            (status.as_str(), epoch),
+            ("pending", e2),
+            "the unfinished ZIP MUST be re-armed at the new epoch, not left stranded at {e1}"
+        );
+
+        // Even if the old in-flight worker now "finishes", it is inert and cannot resurrect itself.
+        assert!(!finalize_job(&pool, event_id, "zip", e1, "exports/Gallery.1.zip").await);
+        assert_eq!(downloadable(&pool, event_id, "zip").await, None);
+    }
+}
+
+/// The re-arm upsert must never clobber the archive it just carried forward.
+///
+/// `enqueue_types_at_epoch`'s `WHERE export_job.status <> 'done' OR export_job.epoch <> EXCLUDED.epoch`
+/// is the "startup recovery must not clobber a good half" rule, expressed as the readiness predicate
+/// itself. PREVENTS: boot recovery resetting a perfectly good, downloadable ZIP back to `pending`
+/// and making the keepsake 404 while it needlessly rebuilds.
+#[sqlx::test]
+async fn enqueue_preserves_a_done_half_at_the_current_epoch(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let e1 = release_gallery(&pool, "wedding").await.unwrap();
+
+    // The ZIP finished; the HTML worker was killed mid-flight (crash) and sits at `running`.
+    assert!(claim_job(&pool, event_id, "zip", e1).await);
+    assert!(finalize_job(&pool, event_id, "zip", e1, "exports/Gallery.1.zip").await);
+    assert!(claim_job(&pool, event_id, "html", e1).await);
+
+    // Boot recovery re-arms both types at the SAME epoch.
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, e1, &["zip", "html"]).await;
+    drop(conn);
+
+    // The good half survives untouched…
+    let (status, epoch, file_path) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!((status.as_str(), epoch), ("done", e1), "a done half at the live epoch is preserved");
+    assert_eq!(file_path.as_deref(), Some("exports/Gallery.1.zip"), "file_path not nulled");
+    assert!(downloadable(&pool, event_id, "zip").await.is_some());
+
+    // …and only the missing half is re-armed.
+    assert_eq!(job_row(&pool, event_id, "html").await.unwrap().0, "pending");
+}

backend/tests/upload_concurrency.rs

@@ -0,0 +1,268 @@
+//! DB-backed integration tests for the two concurrency guards in the upload commit path
+//! (`handlers/upload.rs`). Both are SQL — a `FOR SHARE` row lock and an atomic compare-and-increment
+//! — and both are load-bearing for things a user can actually lose: a wedding photo, or the disk.
+//!
+//! `#[sqlx::test]` gives each test a fresh database with the real migrations applied.
+
+mod common;
+
+use std::sync::Arc;
+use std::sync::atomic::{AtomicBool, Ordering};
+use std::time::Duration;
+
+use chrono::{DateTime, Utc};
+use common::*;
+use sqlx::PgPool;
+use uuid::Uuid;
+
+/// SRC: `handlers/upload.rs:313-322` — the guarded quota increment, verbatim.
+/// Returns `rows_affected()`; the handler aborts the whole upload tx when this is 0.
+async fn quota_inc(
+    exec: impl sqlx::PgExecutor<'_>,
+    user_id: Uuid,
+    size: i64,
+    limit: i64,
+) -> u64 {
+    sqlx::query(
+        "UPDATE \"user\" SET total_upload_bytes = total_upload_bytes + $2
+         WHERE id = $1 AND total_upload_bytes + $2 <= $3",
+    )
+    .bind(user_id)
+    .bind(size)
+    .bind(limit)
+    .execute(exec)
+    .await
+    .expect("quota_inc")
+    .rows_affected()
+}
+
+async fn total_bytes(pool: &PgPool, user_id: Uuid) -> i64 {
+    sqlx::query_scalar("SELECT total_upload_bytes FROM \"user\" WHERE id = $1")
+        .bind(user_id)
+        .fetch_one(pool)
+        .await
+        .expect("total_bytes")
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 5. The atomic quota increment
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// Two attempts sized off ONE stale snapshot, each of which "fits" on its own, cannot both commit.
+/// The predicate re-reads `total_upload_bytes` inside the UPDATE, so the second matches 0 rows.
+///
+/// PREVENTS: one guest filling the disk. The handler's pre-flight quota check runs BEFORE the body is
+/// streamed — minutes earlier, for a 500 MB video. If the commit trusted that snapshot, a guest could
+/// start N uploads that each individually fit under the limit and land all N, blowing straight through
+/// the quota and (in a 1 GB container) taking the event down for everyone.
+#[sqlx::test]
+async fn quota_two_attempts_from_one_stale_snapshot_cannot_both_commit(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let user_id = seed_user(&pool, event_id, "Gierige Gudrun").await;
+
+    const LIMIT: i64 = 100;
+    const SIZE: i64 = 60;
+
+    // THE STALE SNAPSHOT: the pre-flight check both uploads were admitted on.
+    let snapshot = total_bytes(&pool, user_id).await;
+    assert_eq!(snapshot, 0);
+    // Each upload, judged against that snapshot alone, fits: 0 + 60 <= 100. Twice.
+    assert!(snapshot + SIZE <= LIMIT);
+
+    assert_eq!(quota_inc(&pool, user_id, SIZE, LIMIT).await, 1, "the first upload commits");
+    assert_eq!(
+        quota_inc(&pool, user_id, SIZE, LIMIT).await,
+        0,
+        "the second MUST affect 0 rows — it was admitted on a snapshot that is now a lie \
+         (60 + 60 = 120 > 100). rows_affected() == 0 is what makes the handler abort."
+    );
+
+    assert_eq!(total_bytes(&pool, user_id).await, SIZE, "never 120 — the quota held");
+}
+
+/// The same, but genuinely CONCURRENT: two transactions that both read `total = 0`, then both try to
+/// commit 60 bytes against a 100-byte limit. The second UPDATE blocks on the first's row lock and —
+/// because every predicate is on the ROW BEING UPDATED — Postgres re-evaluates it against the
+/// post-commit row (EPQ) rather than the statement's original snapshot. It matches nothing.
+///
+/// PREVENTS: exactly the same disk-filling overrun, on the path it actually happens — two uploads
+/// in flight at once, which is the normal case at a party.
+#[sqlx::test]
+async fn quota_guard_is_atomic_under_concurrent_transactions(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let user_id = seed_user(&pool, event_id, "Gierige Gudrun").await;
+
+    const LIMIT: i64 = 100;
+    const SIZE: i64 = 60;
+
+    let mut tx1 = pool.begin().await.unwrap();
+    let mut tx2 = pool.begin().await.unwrap();
+
+    // Both transactions read the same snapshot and both would pass a naive `total + size <= limit`
+    // check done in Rust.
+    for tx in [&mut tx1, &mut tx2] {
+        let seen: i64 = sqlx::query_scalar("SELECT total_upload_bytes FROM \"user\" WHERE id = $1")
+            .bind(user_id)
+            .fetch_one(&mut **tx)
+            .await
+            .unwrap();
+        assert_eq!(seen, 0, "both see an empty quota");
+    }
+
+    // tx1 takes the row lock and commits.
+    assert_eq!(quota_inc(&mut *tx1, user_id, SIZE, LIMIT).await, 1);
+    tx1.commit().await.unwrap();
+
+    // tx2's UPDATE was written against the stale snapshot but is evaluated against the row as it
+    // now stands.
+    assert_eq!(
+        quota_inc(&mut *tx2, user_id, SIZE, LIMIT).await,
+        0,
+        "the loser MUST see 0 rows affected — this is the entire quota guarantee"
+    );
+    tx2.rollback().await.unwrap();
+
+    assert_eq!(total_bytes(&pool, user_id).await, SIZE);
+
+    // And an upload that legitimately fits in what's left still succeeds — the guard rejects
+    // overruns, not everything.
+    assert_eq!(quota_inc(&pool, user_id, 40, LIMIT).await, 1, "0 + 60 + 40 == 100, exactly at the limit");
+    assert_eq!(total_bytes(&pool, user_id).await, LIMIT);
+    assert_eq!(quota_inc(&pool, user_id, 1, LIMIT).await, 0, "and one byte more is refused");
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 6. The `FOR SHARE` upload lock vs. the release
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// SRC: `handlers/upload.rs:297-303` — the in-transaction re-check under a row lock, verbatim.
+async fn lock_and_read_event(
+    tx: &mut sqlx::PgConnection,
+    event_id: Uuid,
+) -> (Option<DateTime<Utc>>, Option<DateTime<Utc>>) {
+    sqlx::query_as("SELECT uploads_locked_at, export_released_at FROM event WHERE id = $1 FOR SHARE")
+        .bind(event_id)
+        .fetch_one(tx)
+        .await
+        .expect("FOR SHARE re-check")
+}
+
+/// THE GUARD AGAINST SILENT, PERMANENT PHOTO LOSS.
+///
+/// An upload holding `FOR SHARE` on the event row must BLOCK the `UPDATE event SET
+/// export_released_at = NOW()` in `release_gallery` until it commits. Either the upload commits first
+/// — and the release (hence the export snapshot) is strictly ordered after it, so the keepsake
+/// CONTAINS the photo — or the release commits first and the upload observes the lock and rejects
+/// (reversibly: the client keeps the blob and resumes after a reopen).
+///
+/// PREVENTS: the lost wedding photo. Without this serialization: a guest starts a 500 MB video, the
+/// pre-flight lock check passes, the host releases the gallery, the export workers snapshot the
+/// uploads table, and THEN the upload commits. The photo appears in the live feed but is missing from
+/// the downloaded keepsake, forever — nothing ever regenerates it and nobody ever notices.
+#[sqlx::test]
+async fn for_share_upload_lock_serializes_against_release(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let user_id = seed_user(&pool, event_id, "Fotograf Fritz").await;
+
+    // ── The guest's upload transaction takes the share lock. ──
+    let mut upload_tx = pool.begin().await.unwrap();
+    let (locked, released) = lock_and_read_event(&mut upload_tx, event_id).await;
+    assert!(locked.is_none() && released.is_none(), "uploads are open, so we proceed to commit");
+
+    // ── Concurrently, the host hits "Galerie freigeben". ──
+    let release_done = Arc::new(AtomicBool::new(false));
+    let release_task = {
+        let pool = pool.clone();
+        let release_done = release_done.clone();
+        tokio::spawn(async move {
+            sqlx::query(
+                "UPDATE event
+                 SET export_released_at = NOW(),
+                     uploads_locked_at  = COALESCE(uploads_locked_at, NOW()),
+                     export_epoch       = export_epoch + 1
+                 WHERE id = $1 AND export_released_at IS NULL",
+            )
+            .bind(event_id)
+            .execute(&pool)
+            .await
+            .expect("release");
+            release_done.store(true, Ordering::SeqCst);
+        })
+    };
+
+    // The release MUST be stuck behind our `FOR SHARE` row lock. (`FOR SHARE` conflicts with the
+    // `FOR UPDATE` lock the UPDATE needs, so Postgres makes it wait — this is not a timing race,
+    // it is a lock-conflict guarantee; the sleep only gives it every chance to wrongly proceed.)
+    tokio::time::sleep(Duration::from_millis(750)).await;
+    assert!(
+        !release_done.load(Ordering::SeqCst),
+        "the release MUST block while an upload holds FOR SHARE — if it can slip past, the export \
+         snapshot is taken while a photo is still committing and that photo is lost forever"
+    );
+
+    // The photo commits. It is now unambiguously part of the upload set.
+    let upload_id: Uuid = sqlx::query_scalar(
+        "INSERT INTO upload (event_id, user_id, original_path, mime_type, original_size_bytes)
+         VALUES ($1, $2, 'originals/wedding/x.jpg', 'image/jpeg', 1234) RETURNING id",
+    )
+    .bind(event_id)
+    .bind(user_id)
+    .fetch_one(&mut *upload_tx)
+    .await
+    .unwrap();
+    upload_tx.commit().await.unwrap();
+
+    // Only now can the release proceed.
+    tokio::time::timeout(Duration::from_secs(5), release_task)
+        .await
+        .expect("the release must unblock once the upload commits")
+        .unwrap();
+
+    // THE PAYOFF: the export snapshot — the very query the ZIP worker runs — sees the photo. Order
+    // enforced by the lock: upload commit < release < snapshot.
+    let snapshot: Vec<Uuid> = sqlx::query_scalar(
+        "SELECT u.id FROM upload u
+           JOIN \"user\" usr ON usr.id = u.user_id
+          WHERE u.event_id = $1 AND u.deleted_at IS NULL
+            AND usr.uploads_hidden = FALSE AND usr.is_banned = FALSE",
+    )
+    .bind(event_id)
+    .fetch_all(&pool)
+    .await
+    .unwrap();
+    assert_eq!(snapshot, vec![upload_id], "the released keepsake CONTAINS the in-flight photo");
+}
+
+/// The other side of the same lock: once the release has COMMITTED, the next upload's `FOR SHARE`
+/// re-read sees `export_released_at` set and the handler rejects it with `UploadsLocked`.
+///
+/// PREVENTS: the same lost photo, on the losing side of the race — a photo committing AFTER the
+/// export snapshot would be in the live feed but missing from the keepsake. Rejecting is the correct
+/// outcome, and it is reversible: `UploadsLocked` (not Forbidden) tells the client to keep the blob
+/// and resume when the host reopens.
+#[sqlx::test]
+async fn upload_after_release_commits_sees_the_lock_and_is_rejected(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+
+    // Before the release, the re-check passes.
+    let mut tx = pool.begin().await.unwrap();
+    let (locked, released) = lock_and_read_event(&mut tx, event_id).await;
+    assert!(locked.is_none() && released.is_none());
+    tx.rollback().await.unwrap();
+
+    assert_eq!(release_gallery(&pool, "wedding").await, Some(1));
+
+    // After it, the identical re-check sees the release and the handler bails out.
+    let mut tx = pool.begin().await.unwrap();
+    let (locked, released) = lock_and_read_event(&mut tx, event_id).await;
+    assert!(released.is_some(), "the FOR SHARE re-read MUST observe the committed release");
+    assert!(locked.is_some(), "release locks uploads in the same statement (release ⇒ lock)");
+    tx.rollback().await.unwrap();
+
+    // And a reopen makes it uploadable again — the rejection was reversible, not terminal.
+    assert_eq!(open_event(&pool, "wedding").await, 1);
+    let mut tx = pool.begin().await.unwrap();
+    let (locked, released) = lock_and_read_event(&mut tx, event_id).await;
+    assert!(locked.is_none() && released.is_none(), "the guest can resume their upload");
+    tx.rollback().await.unwrap();
+}