Merge branch 'fix/reject-zero-quota-tolerance'

Zero is inside the documented 0–1 range and catastrophic. The per-user limit is
`free_disk * tolerance / active_uploaders`, so a tolerance of 0 makes every limit 0 and
refuses EVERY upload -- mid-event, with "Du hast dein Upload-Limit für dieses Event
erreicht", an error naming the wrong cause entirely. An admin reaching for an off-switch
wants `storage_quota_enabled`; the rejection now says so.

Rejecting the value rather than raising the floor. A floor of 0.01 was the obvious fix
and it is wrong: very small tolerances are legitimate -- they are how a large disk is
throttled down to a sensible per-guest ceiling, and how the quota specs steer it
(tolerance = target * active / free lands around 1e-5 on the 174 GB volume this suite
runs on). A floor would forbid real configurations, and would have broken the entire
storage-quota describe block, to prevent one typo. Verified: those four tests still pass.

Tests: the rejection, that the stored value is untouched (validation fully precedes any
write), and the mirror -- 0.00001 still round-trips -- so the guard can't quietly become
a floor later.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

.claude/settings.json

@@ -0,0 +1,9 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(cargo check *)",
+      "Bash(cargo clippy *)",
+      "Bash(git --no-pager diff *)"
+    ]
+  }
+}

.env.example

@@ -16,6 +16,13 @@ DATABASE_URL=postgres://eventsnap:CHANGE_ME_use_a_strong_password@db:5432/events
 POSTGRES_USER=eventsnap
 POSTGRES_PASSWORD=CHANGE_ME_use_a_strong_password
 POSTGRES_DB=eventsnap
+# Connection pool size. Default 10. For a busy event (~100 guests polling the feed
+# + SSE + uploads at once) raise to ~30 so requests don't queue on a pool permit.
+# PAIRED WITH THE DB CONTAINER'S MEMORY LIMIT: 30 backends plus Postgres 16's default
+# shared_buffers is already snug in the 1G that docker-compose.yml allots the `db`
+# service. If you raise this, raise `db.deploy.resources.limits.memory` with it — an
+# OOM in Postgres doesn't degrade one feature, it takes the whole event down.
+DATABASE_MAX_CONNECTIONS=30
 
 # ── Authentication ────────────────────────────────────────────────────────────
 # Generate with: openssl rand -hex 64
@@ -24,7 +31,11 @@ SESSION_EXPIRY_DAYS=30
 
 # Admin dashboard password (bcrypt hash).
 # Generate with: htpasswd -bnBC 12 "" yourpassword | tr -d ':\n'
-ADMIN_PASSWORD_HASH=$2y$12$placeholder_replace_me
+# IMPORTANT: keep the SINGLE QUOTES. A bcrypt hash is full of `$` (e.g. $2b$12$…$…),
+# and both Docker Compose's env_file interpolation and dotenvy's variable substitution
+# would otherwise eat the `$…` segments (reading them as unset vars) and corrupt the
+# hash — every admin login then 401s. Single quotes make both read it literally.
+ADMIN_PASSWORD_HASH='$2y$12$placeholder_replace_me'
 
 # ── Event ─────────────────────────────────────────────────────────────────────
 EVENT_NAME=Max & Maria's Wedding
@@ -36,19 +47,43 @@ MEDIA_PATH=/media
 # /media is publicly served, so exports here would be downloadable without auth.
 EXPORT_PATH=/exports
 
-# ── Upload limits ─────────────────────────────────────────────────────────────
-DEFAULT_MAX_IMAGE_SIZE_MB=20
-DEFAULT_MAX_VIDEO_SIZE_MB=500
-
-# ── Rate limiting ─────────────────────────────────────────────────────────────
-DEFAULT_UPLOAD_RATE_PER_HOUR=10
-DEFAULT_FEED_RATE_PER_MIN=60
-DEFAULT_EXPORT_RATE_PER_DAY=3
-
-# ── Capacity ──────────────────────────────────────────────────────────────────
-DEFAULT_ESTIMATED_GUEST_COUNT=100
-# Fraction of total storage that triggers the "low storage" warning (0.0–1.0)
-DEFAULT_QUOTA_TOLERANCE=0.75
+# ── Runtime settings (upload limits, rate limits, capacity) ───────────────────
+# NOTE: These are NOT environment variables. Upload size caps, rate limits, guest
+# count and quota tolerance are stored in the database `config` table (seeded once
+# at first boot) and changed at runtime from the ADMIN DASHBOARD — the backend does
+# not read them from .env. Setting them here has no effect. Current seeded defaults:
+#   upload rate      100 / hour / guest   (raised from 10 by migration 015)
+#   feed rate         60 / minute
+#   export rate        3 / day
+#   max image size    20 MB
+#   max video size   500 MB
+#   estimated guests 100
+#   quota tolerance  0.75  (see below — NOT a warning threshold)
+# Adjust these in the admin UI before the event if needed.
+#
+# quota_tolerance is the MULTIPLIER IN THE PER-USER QUOTA FORMULA, not the point at
+# which anything warns you:
+#
+#     per_user_limit = floor(free_disk * quota_tolerance / active_uploaders)
+#
+# It is recomputed against LIVE free space on every upload, so it self-throttles: guests
+# converge on a fixed point at tolerance/(1+tolerance) of the free space you started
+# with — 43% at 0.75, i.e. ~30 GB of a fresh 70 GB.
+#
+# Raising it therefore AUTHORISES GUESTS TO FILL MORE OF THE DISK. Setting 0.95 in the
+# belief that it means "warn me later" moves the fixed point to ~49% and eats the
+# headroom the keepsake needs — and the keepsake needs a lot, because Gallery.zip and
+# Memories.zip are each roughly a second copy of every original (both store media
+# uncompressed). Budget for media + 2x media, or move exports to their own volume.
+#
+# 0.75 is the tested default. Lower it if the box is tight; raise it only if you have
+# provisioned export headroom separately.
 
 # ── Workers ───────────────────────────────────────────────────────────────────
+# Number of parallel image/video compression workers. Default 2. This is the main
+# throughput bottleneck: with 2 workers a burst of uploads can take ~5s to appear.
+# For a large event (100+ guests) 4 is a good target — but each worker can run an
+# ffmpeg transcode, so if you raise this ALSO raise the app container's memory limit
+# in docker-compose.yml (`app.deploy.resources.limits.memory`) from 1G to ~2G, or a
+# burst of large videos can OOM the box and take Postgres down with it.
 COMPRESSION_WORKER_CONCURRENCY=2

.github/workflows/e2e.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   e2e:
-    name: Playwright E2E (chromium-desktop)
+    name: Playwright E2E (chromium + webkit)
     runs-on: ubuntu-latest
     timeout-minutes: 30
     steps:
@@ -25,7 +25,7 @@ jobs:
 
       - name: Install Playwright browsers
         working-directory: ./e2e
-        run: npx playwright install --with-deps chromium
+        run: npx playwright install --with-deps chromium webkit
 
       - name: Bring up the test stack
         working-directory: ./e2e
@@ -54,6 +54,22 @@ jobs:
         working-directory: ./e2e
         run: npm run test:e2e -- --project=chromium-mobile
 
+      # iOS Safari is the app's stated primary user (a wedding guest opening a QR link), and
+      # WebKit is the ONLY engine here that reproduces two of its behaviours:
+      #   - it enforces X-Frame-Options on the download iframe, so a site-wide `DENY` makes the
+      #     keepsake download silently do nothing. Blink hands attachments to the download
+      #     manager first and never notices. That shipped once already.
+      #   - it abandons a <video> load without a 206 response to its Range probe.
+      # Both regressions are invisible to every Chromium project, so running WebKit is what
+      # actually gates them on a PR rather than on someone remembering to test locally.
+      #
+      # The project is scoped in playwright.config.ts to the journeys a guest walks
+      # (01-auth, 02-upload, 03-feed, 06-export); four IndexedDB-blob tests skip themselves
+      # there — see helpers/webkit.ts for why that is the harness and not the app.
+      - name: Run E2E tests (webkit / iOS)
+        working-directory: ./e2e
+        run: npm run test:e2e -- --project=webkit-iphone
+
       - name: Upload Playwright report
         if: failure()
         uses: actions/upload-artifact@v4

.gitignore

@@ -29,3 +29,6 @@ e2e/.env.test
 # OS
 .DS_Store
 Thumbs.db
+
+# Claude Code personal (per-user) settings — shared settings.json IS committed
+.claude/settings.local.json

Caddyfile

@@ -9,34 +9,63 @@
 	header {
 		Strict-Transport-Security "max-age=31536000; includeSubDomains"
 		X-Content-Type-Options "nosniff"
-		X-Frame-Options "DENY"
 		Referrer-Policy "strict-origin-when-cross-origin"
 	}
 
+	# X-Frame-Options: DENY everywhere EXCEPT the keepsake download endpoints, which
+	# are navigated in a HIDDEN, SAME-ORIGIN iframe so a 404/429 can't unload the PWA
+	# (see frontend/src/routes/export/+page.svelte). WebKit enforces XFO *before*
+	# honouring Content-Disposition, so a blanket DENY makes the download silently do
+	# nothing on iOS Safari — the app's primary platform. SAMEORIGIN still blocks
+	# cross-origin framing.
+	#
+	# Split into two disjoint matchers rather than an override: Caddy applies the
+	# FIRST header directive outermost, so it wins on write — a later, more specific
+	# `header` would be silently ignored.
+	@framable path /api/v1/export/zip /api/v1/export/html
+	@not_framable not path /api/v1/export/zip /api/v1/export/html
+	header @framable X-Frame-Options "SAMEORIGIN"
+	header @not_framable X-Frame-Options "DENY"
+
 	# SvelteKit frontend — static assets with long-lived cache (content-hashed filenames)
 	@hashed_assets path_regexp hashed /_app/immutable/.*\.[a-f0-9]{8,}\.(js|css|woff2)$
 	header @hashed_assets Cache-Control "public, max-age=31536000, immutable"
 
-	# Preview/thumbnail images. These are now served by the app through a
-	# visibility-checked alias (/api/v1/upload/{id}/{preview,thumbnail}) so moderation
-	# can revoke access; direct /media/previews|thumbnails is 404-blocked at the app.
+	# Preview/thumbnail images. These are served by the app through a visibility-checked
+	# alias (/api/v1/upload/{id}/{preview,thumbnail}) so moderation can revoke access;
+	# the app serves no /media route at all, so there is no direct path to the bytes.
 	# Privately cacheable for a short window (the app sets the same header; this is the
 	# edge carve-out from the blanket no-store below). Kept short so a moderated image
 	# stops being served to a direct-URL holder promptly.
 	@media_api path /api/v1/upload/*/preview /api/v1/upload/*/thumbnail
 	header @media_api Cache-Control "private, max-age=300"
 
-	# API — never cache, EXCEPT the gated image routes above.
+	# API and health — never cache, EXCEPT the gated image routes above. A cached health
+	# response would report the last known state rather than the current one.
 	@api {
-		path /api/*
+		path /api/* /health
 		not path /api/v1/upload/*/preview /api/v1/upload/*/thumbnail
 	}
 	header @api Cache-Control "no-store"
 
-	# Route API and media requests to the Rust backend
+	# Route API and media requests to the Rust backend.
+	#
+	# The app serves no /media route at all (see the note in backend/src/main.rs) — media
+	# bytes are reachable only through the visibility-checked /api/v1/upload aliases, so
+	# /media/* forwards to a plain 404. The proxy line is kept deliberately: it means the
+	# edge faithfully hands /media to the app, so if a future change ever re-introduces a
+	# static media route the e2e gating specs see it here exactly as production would,
+	# instead of being masked by the SvelteKit 404 page.
 	reverse_proxy /api/* app:3000
 	reverse_proxy /media/* app:3000
 
+	# The backend registers /health on its ROOT router, not under /api/v1, so it needs its
+	# own line — without it the catch-all below hands /health to SvelteKit, which has no
+	# such route and returns its 404 page. That made the documented post-deploy check
+	# (`curl -fsS https://DOMAIN/health`) fail 100% of the time on a perfectly healthy
+	# stack. e2e/Caddyfile.test has always carried this line; production never did.
+	reverse_proxy /health app:3000
+
 	# Everything else goes to SvelteKit frontend
 	reverse_proxy frontend:3001
 }

PROJECT.md

@@ -709,7 +709,7 @@ CREATE TABLE config (
 INSERT INTO config (key, value) VALUES
     ('max_image_size_mb',       '20'),
     ('max_video_size_mb',       '500'),
-    ('upload_rate_per_hour',    '10'),
+    ('upload_rate_per_hour',    '100'),  -- raised from 10 in migration 015 (guests upload bursts of 10-20)
     ('feed_rate_per_min',       '60'),
     ('export_rate_per_day',     '3'),
     ('quota_tolerance',         '0.75'),
@@ -1133,16 +1133,19 @@ eventsnap/
 
 ### Backup Strategy
 
-```bash
-# Daily (e.g. as a separate Compose service or cron on the VPS)
-pg_dump $DATABASE_URL | gzip > /media/backups/db_$(date +%Y-%m-%d).sql.gz
+Three artefacts in three places: the database, the `media_data` volume
+(originals + derivatives), and the **separate** `exports_data` volume. See
+[README.md](README.md#backup) for the exact commands.
 
-# Weekly: rsync /media volume to Hetzner Storage Box
-rsync -az /opt/eventsnap/media/ \
-  user@u123456.your-storagebox.de:backup/eventsnap/
-```
+Everything runs through `docker compose` / `docker run`, because `DATABASE_URL`
+and the `/media` and `/exports` paths only exist inside the compose network —
+they are not host paths, and `DATABASE_URL` is never exported into an operator's
+shell.
 
-The `/media` volume contains originals, previews, thumbnails, generated exports, and DB backups — a single volume to back up.
+Export archives are deliberately outside `MEDIA_PATH` (`EXPORT_PATH=/exports`): a
+keepsake contains every photo in the event, and keeping it off the media tree is
+what stops it being reachable except through the ticket-gated handler. A backup
+of the media volume alone silently loses every generated keepsake.
 
 ---
 

README.md

@@ -34,7 +34,6 @@ A guest scans the QR code on their way in, types their name, and is immediately
 ### Planned (v1.x)
 
 - Individual file download button
-- Low-disk alert (< 10 GB free)
 - Event banner / cover image
 - Chunked resumable upload for large videos
 - Host-curated story highlights
@@ -115,6 +114,65 @@ Caddy automatically obtains a Let's Encrypt certificate on first start. The app
 > docker compose -f docker-compose.yml -f docker-compose.dev.yml up
 > ```
 
+### Updating an existing deployment
+
+> **`docker compose up -d` alone will NOT deploy your changes.** `app` and `frontend` are
+> `build:` services with no published image tag, and Compose has no source-change detection:
+> if an image with that name already exists it is reused. After a `git pull` the command
+> reports `Container … Running`, changes nothing, and **exits 0** — so a deploy that shipped
+> nothing looks exactly like a successful one. `--build` is what makes it real.
+
+```bash
+cd /path/to/eventsnap
+
+# 1. Back up first — migrations run automatically on boot and are not reversible in place.
+#    (See "Backup" below; the database dump is the one that matters here.)
+
+# 2. Fetch the new code.
+git pull
+
+# 3. Rebuild and restart the application services. --build is NOT optional.
+docker compose up -d --build
+
+# 4. Apply any Caddyfile change. Step 3 does NOT do this — see the warning below.
+docker compose up -d --force-recreate caddy
+
+# 5. Confirm the app came back up. Anything other than "ok" means check the logs.
+curl -fsS https://DOMAIN/health && echo
+
+# 6. Confirm a NEW image was actually built. Note the IMAGE ID before you start and
+#    compare — it must have changed. (Ignore the CREATED column; it reports the base
+#    layer's age, not this build's.) An unchanged ID means step 3 ran without --build
+#    and you are still serving the old code.
+docker compose images app frontend
+```
+
+Migrations are applied by the backend on startup, so step 3 covers them. If `app` stays
+unhealthy afterwards, `docker compose logs app` will name the failing migration — and note
+that a migration applied by a *newer* build is not removed by checking out an older commit,
+so rolling back code without restoring the database snapshot from step 1 leaves the schema
+ahead of the binary and the app refusing to boot.
+
+> **Why step 4 exists.** `--build` only rebuilds services that have a `build:` section, and
+> `caddy` is a pinned upstream image. Compose decides whether to recreate a container from its
+> *config hash*, which covers the mount **specification** (`./Caddyfile:/etc/caddy/Caddyfile:ro`)
+> but **not the file's contents** — so a `git pull` that changes `./Caddyfile` produces no
+> delta, Compose reports `Running`, and Caddy keeps serving its old config indefinitely. Exit
+> code 0 throughout.
+>
+> That is not hypothetical: the fix that made the keepsake download work on iOS
+> (`137c4ee`) touched the Caddyfile and four e2e files and nothing else, so **all** of its
+> production effect lives in that one file. Without step 4 you deploy it, watch both image IDs
+> change, and iOS downloads stay broken.
+>
+> `--force-recreate` rather than `restart` or `caddy reload`: the bind mount is resolved to an
+> **inode** when the container is created, and `git pull` replaces the file instead of editing
+> it in place, so the container can still be bound to the old, now-unlinked inode. A restart
+> then re-reads the stale content. Recreating the container re-resolves the path.
+
+`db` is never touched, and recreating `caddy` does not disturb the `caddy_data` volume, so the
+TLS certificate and all data volumes survive.
+
 ### Generate required secrets
 
 ```bash
@@ -162,23 +220,176 @@ See [.env.example](.env.example) for the full list with descriptions and default
 └────────┘
 ```
 
-- `/api/*` and `/media/*` → Rust backend
+- `/api/*` → Rust backend
 - Everything else → SvelteKit frontend (`adapter-node`)
-- Named volumes: `postgres_data`, `media_data`, `caddy_data`
+- Named volumes: `postgres_data`, `media_data`, `exports_data`, `caddy_data`
+
+Media is **not** served as static files. Every image goes through a
+visibility-checked alias (`/api/v1/upload/{id}/{preview,display,thumbnail,original}`)
+so a host takedown or a ban actually revokes access to the bytes.
+
+---
+
+## Sizing the disk
+
+`postgres_data`, `media_data` and `exports_data` are all Docker named volumes under
+`/var/lib/docker/volumes`, so **they share one filesystem**. Filling it does not
+degrade one subsystem — Postgres stops being able to write and the whole event goes
+down.
+
+Uploads are self-limiting. `per_user_limit = free_disk × quota_tolerance ÷
+active_uploaders` is recomputed against live free space on every upload, so guests
+converge on a fixed point at `tolerance / (1 + tolerance)` of the free space you
+started with — **43%** at the default 0.75. On an 80 GB box with ~70 GB free after
+the OS and images, media settles at ~30 GB and stops.
+
+**The keepsake is what the 80 GB baseline does not cover.** `Gallery.zip` and
+`Memories.zip` are built concurrently and each is roughly a second copy of every
+original: both write their media `Compression::Stored`, and `Memories.zip` streams the
+untouched original for every video and for every image at or under 5 MB. So a release
+wants room for **two more copies of the gallery** on top of the gallery itself.
+
+| Stage | Used | Free (80 GB box) |
+|---|---|---|
+| Fresh box (OS + images) | ~10 GB | ~70 GB |
+| Guests reach the quota fixed point | ~40 GB | ~40 GB |
+| Host releases → both archives | ~100 GB | **ENOSPC** |
+
+Two ways to size for it:
+
+- **Provision ~3× your expected media** on one volume (media + two archives), or
+- **give `exports_data` its own volume** so a full export cannot reach Postgres, and
+  size that one at ~2× expected media.
+
+This is no longer silent. The export refuses up front with the two numbers rather than
+hitting ENOSPC halfway through a multi-GB write, a rebuild reclaims the superseded
+generation before it starts (so peak is one generation, not two), and the host
+dashboard warns as soon as the keepsake would not fit — which is the only point at
+which anyone can still do something about it.
 
 ---
 
 ## Backup
 
-```bash
-# Database snapshot
-pg_dump $DATABASE_URL | gzip > /media/backups/db_$(date +%Y-%m-%d).sql.gz
+There are **three** things to back up, and they live in three different places.
+`DATABASE_URL` and the container paths (`/media`, `/exports`) are meaningful only
+*inside* the compose network — they are not host paths, and `DATABASE_URL` is
+never exported into an operator's shell — so every command below runs through
+`docker compose` from the repo directory.
 
-# Weekly offsite sync (Hetzner Storage Box or similar)
-rsync -az /opt/eventsnap/media/ user@storagebox.example.com:backup/eventsnap/
+```bash
+# 1. Database snapshot. Runs pg_dump inside the db container (the app image has no
+#    postgres client), reading credentials from the compose environment.
+#    --clean --if-exists makes the dump SELF-CLEANING: without it the restore below
+#    aborts on the first "already exists" against a database that has ever booted,
+#    which is every database you would actually want to restore over.
+mkdir -p ./backups
+docker compose exec -T db \
+  sh -c 'pg_dump --clean --if-exists -U "$POSTGRES_USER" "$POSTGRES_DB"' \
+  | gzip > ./backups/db_$(date +%Y-%m-%d).sql.gz
+
+# 2. Uploaded media (originals + derivatives) out of the named volume.
+#    NOTE the mountpoint is /src, not /media: if the volume is ever empty, Docker
+#    pre-populates a fresh mount from the image's own directory, and alpine ships a
+#    /media containing cdrom/floppy/usb. Mounting somewhere the image has nothing
+#    avoids silently tarring (and polluting the volume with) those.
+docker run --rm \
+  -v eventsnap_media_data:/src:ro -v "$PWD/backups":/backup \
+  alpine tar czf /backup/media_$(date +%Y-%m-%d).tar.gz -C /src .
+
+# 3. Export archives — a SEPARATE volume (see the security note below).
+docker run --rm \
+  -v eventsnap_exports_data:/src:ro -v "$PWD/backups":/backup \
+  alpine tar czf /backup/exports_$(date +%Y-%m-%d).tar.gz -C /src .
+
+# Offsite sync of the three artefacts above.
+rsync -az ./backups/ user@storagebox.example.com:backup/eventsnap/
 ```
 
-The `/media` volume holds originals, previews, thumbnails, exports, and DB backups — a single path to back up.
+Volume names are prefixed with the compose project name — `eventsnap_` if you run
+from a directory called `eventsnap`. Confirm yours with `docker volume ls`.
+
+> **Exports are deliberately NOT under `/media`.** They live on their own
+> `exports_data` volume (`EXPORT_PATH=/exports`) because a keepsake archive
+> contains every photo in the event; keeping it outside the media tree is what
+> stops it being reachable except through the ticket-gated download handler.
+> Backing up only the media volume therefore loses every generated keepsake.
+
+### When to run it
+
+**A nightly cron is the wrong shape for this app.** Every irreplaceable byte is
+created inside one eight-hour window, and nobody can retake a wedding. Run the three
+commands above:
+
+1. **The night of the event**, once uploads have stopped. This is the backup that
+   matters; everything else is a formality.
+2. **After the host releases the gallery**, so the generated keepsake is captured too.
+3. Weekly thereafter, until the event is archived and torn down.
+
+Take the DB dump and the media tarball **back to back**, without uploads in flight
+between them. Upload rows reference files by path — a database from 22:00 and a media
+volume from 23:00 gives you rows pointing at files the dump doesn't know about, and
+rows whose files aren't in the tarball. Locking uploads from the host dashboard first
+(**Uploads sperren**) makes the pair genuinely consistent.
+
+---
+
+## Restore
+
+An untested backup is not a backup. Run this once against a scratch host **before**
+the event — it is roughly ten minutes, and it is the only way to find out that your
+tarball is empty or your dump is truncated while that is still a small problem.
+
+```bash
+# 0. Stop the app FIRST. Migrations run on boot and a live pool will fight the
+#    restore — a booting app against a half-restored schema can leave the migration
+#    table and the schema disagreeing, which is its own recovery problem.
+#    Leave `db` running: the dump is restored through it.
+docker compose stop app caddy
+
+# 1. Database. The dump carries its own DROPs (step 1 of Backup), so this replaces
+#    rather than collides. A dump taken WITHOUT --clean --if-exists will abort here
+#    on the first "already exists" — restore that one into a fresh empty database
+#    instead.
+gunzip -c ./backups/db_2026-07-29.sql.gz \
+  | docker compose exec -T db \
+      sh -c 'psql -U "$POSTGRES_USER" -d "$POSTGRES_DB" --set ON_ERROR_STOP=1'
+
+# 2. Media. NOTE the `--numeric-owner` and the chown: the app runs as a
+#    NON-ROOT user (uid 100, gid 101 — `addgroup -S app && adduser -S app`), and a
+#    restore that lands root-owned files makes every upload fail with EACCES deep in
+#    the write path, surfacing to the guest as a generic 500 with nothing in the UI
+#    to suggest permissions. The explicit chown is what guarantees it — BusyBox tar
+#    (which is what `alpine` ships) has no --same-owner, and restores ownership only
+#    because it runs as root here.
+docker run --rm \
+  -v eventsnap_media_data:/dst -v "$PWD/backups":/backup:ro \
+  alpine sh -c 'tar xzf /backup/media_2026-07-29.tar.gz -C /dst \
+                    --numeric-owner && chown -R 100:101 /dst'
+
+# 3. Exports. Same volume-name caveat, same ownership rules.
+docker run --rm \
+  -v eventsnap_exports_data:/dst -v "$PWD/backups":/backup:ro \
+  alpine sh -c 'tar xzf /backup/exports_2026-07-29.tar.gz -C /dst \
+                    --numeric-owner && chown -R 100:101 /dst'
+
+# 4. Back up. Migrations run, then export recovery re-arms any keepsake whose file
+#    didn't come back with the volume.
+docker compose up -d app caddy
+docker compose logs -f app        # watch for "migrations applied"
+
+# 5. Verify — all three, not just the first.
+curl -fsS https://DOMAIN/health && echo            # → ok
+#   … then sign in as host and confirm the feed renders images (proves the media
+#   volume restored AND is readable by uid 100), and that the keepsake downloads.
+```
+
+If the media volume restored but images 404 while the feed lists them, the paths are
+there and the bytes aren't — check `docker compose exec app ls -ln /media/originals`
+and confirm both the files and the `100:101` ownership.
+
+The restore is deliberately **not** automated. It is rare, destructive, and the one
+operation where a script that half-works is worse than a checklist someone reads.
 
 ---
 
@@ -254,7 +465,7 @@ Open:
 - [ ] SSE delta-fetch on foreground reconnect (scaffolded in [sse.ts](frontend/src/lib/sse.ts), not wired)
 - [ ] Live diashow / slideshow mode — see [docs/CONCEPT_DIASHOW.md](docs/CONCEPT_DIASHOW.md)
 - [ ] Individual file download button per post
-- [ ] Low-disk alert (< 10 GB free)
+- [x] Low-disk alert — host dashboard warns below 10 GB free, or whenever the keepsake would not fit
 - [ ] Event banner / cover image
 - [ ] Chunked resumable upload for files > 100 MB
 - [ ] Shared Tailwind config between main app and export-viewer

backend/migrations/015_raise_upload_rate.down.sql

@@ -0,0 +1,3 @@
+-- Revert the default upload rate to 10/hour for installs still on the raised
+-- default (preserves any explicit admin override at another value).
+UPDATE config SET value = '10' WHERE key = 'upload_rate_per_hour' AND value = '100';

backend/migrations/015_raise_upload_rate.up.sql

@@ -0,0 +1,10 @@
+-- Raise the default per-guest upload rate from 10/hour to 100/hour.
+--
+-- Rationale: guests routinely upload a burst of 10-20 photos at once (phone
+-- multi-select). At the old default of 10/hour a real guest's first burst was
+-- throttled — surfaced by the 2026-07-18 load test. 100/hour comfortably covers
+-- several bursts across an event while still bounding abuse.
+--
+-- Only bump installs still on the old default; an admin who deliberately set a
+-- different value keeps it (migration 005 seeded 10; this UPDATE is scoped to '10').
+UPDATE config SET value = '100' WHERE key = 'upload_rate_per_hour' AND value = '10';

backend/migrations/016_display_derivative.down.sql

@@ -0,0 +1,28 @@
+-- Drop the view (frees the column dependency), remove the column, then restore the
+-- pre-016 view definition (matches migration 011).
+DROP VIEW IF EXISTS v_feed;
+ALTER TABLE upload DROP COLUMN display_path;
+
+CREATE VIEW v_feed AS
+SELECT
+    u.id,
+    u.event_id,
+    u.user_id,
+    usr.display_name             AS uploader_name,
+    usr.is_banned,
+    usr.uploads_hidden,
+    u.preview_path,
+    u.thumbnail_path,
+    u.mime_type,
+    u.caption,
+    u.created_at,
+    COUNT(DISTINCT l.user_id)    AS like_count,
+    COUNT(DISTINCT c.id)         AS comment_count
+FROM upload u
+JOIN "user" usr ON u.user_id = usr.id
+LEFT JOIN "like" l  ON l.upload_id = u.id
+LEFT JOIN comment c ON c.upload_id = u.id AND c.deleted_at IS NULL
+WHERE u.deleted_at IS NULL
+  AND usr.uploads_hidden = FALSE
+  AND usr.is_banned = FALSE
+GROUP BY u.id, usr.display_name, usr.is_banned, usr.uploads_hidden;

backend/migrations/016_display_derivative.up.sql

@@ -0,0 +1,34 @@
+-- Display derivative: a big-screen-quality image (~2048px long edge) for the diashow.
+-- The 800px `preview_path` is sized for phone feeds (data saver); upscaled on a projector
+-- it looks soft. The diashow uses `display_path` instead — bounded in size (safe to decode
+-- on weak kiosk hardware) yet sharp on 1080p/4K. NULL until the compression worker (or the
+-- one-time backfill) generates it; consumers fall back to the original when absent.
+ALTER TABLE upload ADD COLUMN display_path TEXT;
+
+-- Recreate (not CREATE OR REPLACE, which only allows appending columns at the end) so the
+-- new column can sit alongside preview_path/thumbnail_path.
+DROP VIEW IF EXISTS v_feed;
+CREATE VIEW v_feed AS
+SELECT
+    u.id,
+    u.event_id,
+    u.user_id,
+    usr.display_name             AS uploader_name,
+    usr.is_banned,
+    usr.uploads_hidden,
+    u.preview_path,
+    u.thumbnail_path,
+    u.display_path,
+    u.mime_type,
+    u.caption,
+    u.created_at,
+    COUNT(DISTINCT l.user_id)    AS like_count,
+    COUNT(DISTINCT c.id)         AS comment_count
+FROM upload u
+JOIN "user" usr ON u.user_id = usr.id
+LEFT JOIN "like" l  ON l.upload_id = u.id
+LEFT JOIN comment c ON c.upload_id = u.id AND c.deleted_at IS NULL
+WHERE u.deleted_at IS NULL
+  AND usr.uploads_hidden = FALSE
+  AND usr.is_banned = FALSE
+GROUP BY u.id, usr.display_name, usr.is_banned, usr.uploads_hidden;

backend/migrations/017_join_ip_rate.down.sql

@@ -0,0 +1 @@
+DELETE FROM config WHERE key IN ('join_ip_rate_per_min', 'admin_login_rate_enabled');

backend/migrations/017_join_ip_rate.up.sql

@@ -0,0 +1,18 @@
+-- Per-IP flood ceiling for /join, and the `admin_login_rate_enabled` toggle that
+-- every prior migration forgot to seed.
+--
+-- Rationale: /join was throttled at 5 requests per 60s keyed on the client IP. At a
+-- venue every guest is behind one NAT, so the whole party shared a single bucket —
+-- 12 guests scanning the QR code within a few seconds meant 5 got in and 7 were
+-- turned away. The handler now keys the real anti-spam bucket per (ip, name), the
+-- same shape as `recover:{ip}:{name}`, and keeps only a loose per-IP ceiling to bound
+-- raw volume. 60/min comfortably covers a whole wedding arriving at once while still
+-- capping a flood from a single source.
+--
+-- `admin_login_rate_enabled` is read by auth::handlers::admin_login with a code
+-- default of `true`, but no migration ever inserted it, so it was invisible to the
+-- admin config UI and to the e2e reseed. Seed it explicitly.
+INSERT INTO config (key, value) VALUES
+    ('join_ip_rate_per_min',     '60'),
+    ('admin_login_rate_enabled', 'true')
+ON CONFLICT (key) DO NOTHING;

backend/migrations/018_derivatives_rev.down.sql

@@ -0,0 +1,2 @@
+DROP INDEX IF EXISTS idx_upload_derivatives_rev;
+ALTER TABLE upload DROP COLUMN IF EXISTS derivatives_rev;

backend/migrations/018_derivatives_rev.up.sql

@@ -0,0 +1,18 @@
+-- Track which revision of the derivative pipeline produced an upload's preview/display.
+--
+-- Rev 1 applies the EXIF orientation tag. Everything generated before it decoded the raw
+-- sensor pixels and re-encoded to JPEG (which writes no EXIF), so every portrait phone photo
+-- was stored sideways in the feed preview, the diashow display and the keepsake — while the
+-- untouched original still rendered upright.
+--
+-- Existing rows default to 0 so the startup backfill can find and re-generate them exactly
+-- once; bump the constant in services/compression.rs if the pipeline ever changes again.
+ALTER TABLE upload ADD COLUMN IF NOT EXISTS derivatives_rev SMALLINT NOT NULL DEFAULT 0;
+
+-- Only image derivatives are affected — video thumbnails are extracted by ffmpeg, which
+-- already honours the rotation matrix. Mark them current so the backfill skips them.
+UPDATE upload SET derivatives_rev = 1 WHERE mime_type NOT LIKE 'image/%';
+
+CREATE INDEX IF NOT EXISTS idx_upload_derivatives_rev
+    ON upload (derivatives_rev)
+    WHERE deleted_at IS NULL;

backend/migrations/019_recover_ip_rate.down.sql

@@ -0,0 +1 @@
+DELETE FROM config WHERE key = 'recover_ip_rate_per_min';

backend/migrations/019_recover_ip_rate.up.sql

@@ -0,0 +1,19 @@
+-- Per-IP flood ceiling for /recover, mirroring the one migration 017 added for /join.
+--
+-- Rationale: /recover is keyed `recover:{ip}:{name}` at 5 per 15 minutes. That is the
+-- right shape for its actual job — stopping someone who knows a display name (they are
+-- visible on the feed) from burning the victim's 3-strike PIN counter and locking them
+-- out repeatedly. But the name is attacker-chosen, so cycling names mints a fresh bucket
+-- every time and the per-IP cost is unbounded.
+--
+-- Behind that limiter sits a cost-12 bcrypt verify, including an UNCONDITIONAL throwaway
+-- verify for names that don't exist — deliberately, to close a timing oracle. So an
+-- unknown name is the cheapest possible way to make the server do ~200ms of hashing.
+-- Without a ceiling, one client can saturate the box's CPU with a name generator.
+--
+-- 30/min is far above any real recovery attempt (a guest tries their PIN a handful of
+-- times) while capping a name-cycling flood. The per-(ip, name) bucket is unchanged and
+-- remains the anti-guessing control.
+INSERT INTO config (key, value) VALUES
+    ('recover_ip_rate_per_min', '30')
+ON CONFLICT (key) DO NOTHING;

backend/migrations/020_social_rate.down.sql

@@ -0,0 +1 @@
+DELETE FROM config WHERE key IN ('social_rate_per_min', 'social_rate_enabled');

backend/migrations/020_social_rate.up.sql

@@ -0,0 +1,16 @@
+-- Per-user rate limit for social writes (likes, comments, comment deletions).
+--
+-- These were the only writes in the app with no limit at all. Every other mutating
+-- path -- upload, join, recover, export, admin login -- carries one; social.rs
+-- carried none, so the coverage was asymmetric rather than deliberately open.
+--
+-- Severity is genuinely low for an invited-guest event, and the amplification worry
+-- turned out to be contained: a like fans an SSE broadcast to ~100 clients, but the
+-- export regeneration it could otherwise trigger is debounced (REGEN_DEBOUNCE 20s)
+-- and superseded workers are inert. So this closes the gap for symmetry, not urgency,
+-- and the ceiling is set high enough that no real guest will ever meet it -- a
+-- double-tapping enthusiast at a wedding is not the thing being defended against.
+INSERT INTO config (key, value) VALUES
+    ('social_rate_per_min',  '120'),
+    ('social_rate_enabled',  'true')
+ON CONFLICT (key) DO NOTHING;

backend/src/auth/handlers.rs

@@ -1,11 +1,12 @@
 use std::time::Duration;
 
 use axum::Json;
-use axum::extract::State;
+use axum::extract::{ConnectInfo, State};
 use axum::http::{HeaderMap, StatusCode};
 use chrono::Utc;
 use rand::Rng;
 use serde::{Deserialize, Serialize};
+use std::net::SocketAddr;
 use uuid::Uuid;
 
 use crate::auth::jwt;
@@ -33,22 +34,32 @@ pub struct JoinResponse {
 
 pub async fn join(
     State(state): State<AppState>,
+    ConnectInfo(peer): ConnectInfo<SocketAddr>,
     headers: HeaderMap,
     Json(body): Json<JoinRequest>,
 ) -> Result<(StatusCode, Json<JoinResponse>), AppError> {
-    let ip = client_ip(&headers, "unknown");
+    let ip = client_ip(&headers, &peer.ip().to_string());
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     let join_rate_on = config::get_bool(&state.config_cache, "join_rate_enabled", true).await;
-    if rate_limits_on
-        && join_rate_on
-        && !state
-            .rate_limiter
-            .check(format!("join:{ip}"), 5, Duration::from_secs(60))
-    {
-        return Err(AppError::TooManyRequests(
-            "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
-            None,
-        ));
+
+    // Coarse per-IP flood ceiling. `/join` is pre-auth so there is no user to key on, and
+    // at a venue EVERY guest arrives from one public IP — a tight per-IP bucket meant the
+    // 6th person through the door was turned away by the 5 ahead of them. So the per-IP
+    // limit here only bounds raw volume; the real anti-spam bucket is per-name below.
+    // Cheap enough to run before validation, which keeps a flood of malformed bodies from
+    // being free.
+    if rate_limits_on && join_rate_on {
+        let ip_ceiling = config::get_usize(&state.config_cache, "join_ip_rate_per_min", 60).await;
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+            format!("join_ip:{ip}"),
+            ip_ceiling,
+            Duration::from_secs(60),
+        ) {
+            return Err(AppError::TooManyRequests(
+                "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
+                Some(retry_after_secs),
+            ));
+        }
     }
 
     let display_name = body.display_name.trim();
@@ -66,6 +77,23 @@ pub async fn join(
         ));
     }
 
+    // Per-guest bucket, keyed like the `recover:{ip}:{name}` limiter below. This carries
+    // the original 5/60s anti-spam intent, but one guest retrying can no longer consume
+    // the allowance of everyone else sharing the venue's NAT.
+    if rate_limits_on && join_rate_on {
+        let name_key = display_name.to_lowercase();
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+            format!("join:{ip}:{name_key}"),
+            5,
+            Duration::from_secs(60),
+        ) {
+            return Err(AppError::TooManyRequests(
+                "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
+                Some(retry_after_secs),
+            ));
+        }
+    }
+
     let event = Event::find_or_create(
         &state.pool,
         &state.config.event_slug,
@@ -83,7 +111,7 @@ pub async fn join(
 
     // Generate a 4-digit PIN
     let pin: String = format!("{:04}", rand::rng().random_range(0..10000u32));
-    let pin_hash = bcrypt::hash(&pin, 12).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
+    let pin_hash = hash_password(pin.clone(), 12).await?;
 
     // The pre-check above is racy: two simultaneous joins with the same name can both
     // pass it, and the DB's unique index then rejects the loser. Map that unique
@@ -147,8 +175,31 @@ fn dummy_pin_hash() -> &'static str {
     })
 }
 
+/// Run a bcrypt verify on the blocking pool.
+///
+/// bcrypt at cost 12 is ~200ms of deliberate CPU. Called inline on an async task it pins a
+/// tokio WORKER thread for that whole time, and the runtime only has one per core — so a
+/// flood of `/recover` or `/admin/login` attempts stalls every other request on the box,
+/// including the feed. Offloading moves that cost to the blocking pool, which is sized for
+/// exactly this and whose saturation degrades logins rather than the whole app.
+async fn verify_password(candidate: String, hash: String) -> bool {
+    tokio::task::spawn_blocking(move || bcrypt::verify(&candidate, &hash).unwrap_or(false))
+        .await
+        .unwrap_or(false)
+}
+
+/// Hash a secret on the blocking pool. Same reasoning as [`verify_password`] — and this one
+/// runs on the busiest auth path there is, since every guest who joins gets a PIN hashed.
+pub async fn hash_password(secret: String, cost: u32) -> Result<String, AppError> {
+    tokio::task::spawn_blocking(move || bcrypt::hash(&secret, cost))
+        .await
+        .map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?
+        .map_err(|e| AppError::Internal(anyhow::anyhow!(e)))
+}
+
 pub async fn recover(
     State(state): State<AppState>,
+    ConnectInfo(peer): ConnectInfo<SocketAddr>,
     headers: HeaderMap,
     Json(body): Json<RecoverRequest>,
 ) -> Result<Json<RecoverResponse>, AppError> {
@@ -159,19 +210,39 @@ pub async fn recover(
     // burn through 3 wrong PINs and lock the victim for 15 minutes — repeated
     // every 15 minutes, indefinitely. 5 attempts per 15 minutes per (IP, name)
     // softens that into a real cost.
-    let ip = client_ip(&headers, "unknown");
+    let ip = client_ip(&headers, &peer.ip().to_string());
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     let recover_rate_on = config::get_bool(&state.config_cache, "recover_rate_enabled", true).await;
     if rate_limits_on && recover_rate_on {
+        // Coarse per-IP ceiling FIRST. The per-(ip, name) bucket below is the anti-guessing
+        // control, but the name is attacker-chosen, so cycling names mints a fresh bucket
+        // every time and leaves the per-IP cost unbounded. That matters more here than
+        // anywhere else: every call runs a cost-12 bcrypt verify, including an
+        // unconditional throwaway one for names that don't exist (see below), so an unknown
+        // name is the CHEAPEST way to make the server do ~200ms of hashing. Checked before
+        // the per-name bucket so a name generator can't walk past it.
+        let ip_ceiling =
+            config::get_usize(&state.config_cache, "recover_ip_rate_per_min", 30).await;
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+            format!("recover_ip:{ip}"),
+            ip_ceiling,
+            Duration::from_secs(60),
+        ) {
+            return Err(AppError::TooManyRequests(
+                "Zu viele Versuche. Bitte warte kurz und versuche es erneut.".into(),
+                Some(retry_after_secs),
+            ));
+        }
+
         let name_key = display_name.to_lowercase();
-        if !state.rate_limiter.check(
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
             format!("recover:{ip}:{name_key}"),
             5,
             Duration::from_secs(15 * 60),
         ) {
             return Err(AppError::TooManyRequests(
                 "Zu viele Versuche. Bitte warte kurz und versuche es erneut.".into(),
-                None,
+                Some(retry_after_secs),
             ));
         }
     }
@@ -188,7 +259,7 @@ pub async fn recover(
         // PIN — so "no such name" and "wrong PIN" are indistinguishable by response or
         // timing. Display names are already public on the feed, but this still closes
         // the /recover enumeration + timing oracle.
-        let _ = bcrypt::verify(&body.pin, dummy_pin_hash());
+        let _ = verify_password(body.pin.clone(), dummy_pin_hash().to_string()).await;
         return Err(AppError::Unauthorized("PIN ist falsch.".into()));
     }
 
@@ -200,16 +271,19 @@ pub async fn recover(
         // is effectively permanently fragile.
         if let Some(locked_until) = user.pin_locked_until {
             if Utc::now() < locked_until {
+                // The exact deadline is known, so surface it as Retry-After instead of
+                // making the client guess at the "15 Minuten" in the copy.
+                let retry_after_secs = (locked_until - Utc::now()).num_seconds().max(1) as u64;
                 return Err(AppError::TooManyRequests(
                     "Zu viele Versuche. Bitte warte 15 Minuten.".into(),
-                    None,
+                    Some(retry_after_secs),
                 ));
             }
             // Lockout window expired — wipe the counter and the timestamp.
             User::reset_pin_attempts(&state.pool, user.id).await?;
         }
 
-        let pin_matches = bcrypt::verify(&body.pin, &user.recovery_pin_hash).unwrap_or(false);
+        let pin_matches = verify_password(body.pin.clone(), user.recovery_pin_hash.clone()).await;
 
         if pin_matches {
             // Reset failed attempts on success
@@ -274,6 +348,7 @@ pub struct AdminLoginResponse {
 
 pub async fn admin_login(
     State(state): State<AppState>,
+    ConnectInfo(peer): ConnectInfo<SocketAddr>,
     headers: HeaderMap,
     Json(body): Json<AdminLoginRequest>,
 ) -> Result<Json<AdminLoginResponse>, AppError> {
@@ -287,23 +362,31 @@ pub async fn admin_login(
     // verify) but with no IP-level limit a determined attacker can still mount
     // a long-running guess campaign. 5 attempts / minute / IP is plenty for
     // honest typos.
-    let ip = client_ip(&headers, "unknown");
+    let ip = client_ip(&headers, &peer.ip().to_string());
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     let admin_rate_on =
         config::get_bool(&state.config_cache, "admin_login_rate_enabled", true).await;
+    // Stays keyed by IP on purpose: this guards a single shared credential, so a per-user
+    // or per-name key would just hand an attacker a fresh bucket per guess.
     if rate_limits_on
         && admin_rate_on
-        && !state
-            .rate_limiter
-            .check(format!("admin_login:{ip}"), 5, Duration::from_secs(60))
+        && let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+            format!("admin_login:{ip}"),
+            5,
+            Duration::from_secs(60),
+        )
     {
         return Err(AppError::TooManyRequests(
             "Zu viele Anmeldeversuche. Bitte warte kurz und versuche es erneut.".into(),
-            None,
+            Some(retry_after_secs),
         ));
     }
 
-    let valid = bcrypt::verify(&body.password, &state.config.admin_password_hash).unwrap_or(false);
+    let valid = verify_password(
+        body.password.clone(),
+        state.config.admin_password_hash.clone(),
+    )
+    .await;
 
     if !valid {
         tracing::warn!(ip = %ip, "admin_login: wrong password");
@@ -329,8 +412,7 @@ pub async fn admin_login(
         let dummy_pin: String = (0..32)
             .map(|_| rand::rng().random_range(b'a'..=b'z') as char)
             .collect();
-        let dummy_hash =
-            bcrypt::hash(&dummy_pin, 4).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
+        let dummy_hash = hash_password(dummy_pin.clone(), 4).await?;
         let user = User::create(&state.pool, event.id, admin_name, &dummy_hash).await?;
         sqlx::query("UPDATE \"user\" SET role = 'admin' WHERE id = $1")
             .bind(user.id)
@@ -390,22 +472,23 @@ pub struct PinResetRequestBody {
 /// feed already exposes.
 pub async fn request_pin_reset(
     State(state): State<AppState>,
+    ConnectInfo(peer): ConnectInfo<SocketAddr>,
     headers: HeaderMap,
     Json(body): Json<PinResetRequestBody>,
 ) -> Result<StatusCode, AppError> {
     let display_name = body.display_name.trim();
-    let ip = client_ip(&headers, "unknown");
+    let ip = client_ip(&headers, &peer.ip().to_string());
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     if rate_limits_on {
         let name_key = display_name.to_lowercase();
-        if !state.rate_limiter.check(
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
             format!("pin_reset_req:{ip}:{name_key}"),
             3,
             Duration::from_secs(15 * 60),
         ) {
             return Err(AppError::TooManyRequests(
                 "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
-                None,
+                Some(retry_after_secs),
             ));
         }
     }

backend/src/config.rs

@@ -63,8 +63,25 @@ pub struct AppConfig {
     pub app_port: u16,
     /// Number of concurrent media compression workers (read once at boot).
     pub compression_concurrency: usize,
+    /// Master switch for the comment feature (env `COMMENTS_ENABLED`, default true).
+    /// When false the backend rejects new comments and the frontend hides the whole
+    /// comment UI. Existing comments stay in the DB (hidden), so flipping it back
+    /// restores them. Boot-time immutable, like `compression_concurrency`.
+    pub comments_enabled: bool,
+    /// Default colour theme, used as the fallback when the DB config keys are unset.
+    /// Runtime overrides live in the `config` table (admin UI); these env vars only
+    /// seed the initial default. `preset` is an id the frontend knows (e.g.
+    /// "champagne-gold", "rose", … or "custom"); the two seeds are `#rrggbb` brand +
+    /// accent colours the whole palette is derived from.
+    pub default_theme_preset: String,
+    pub default_theme_primary: String,
+    pub default_theme_accent: String,
 }
 
+/// The shipped default brand/accent seed (champagne gold — matches the hand-tuned
+/// ramp in tailwind-theme.css). Kept here so an unset env still yields the current look.
+const DEFAULT_THEME_SEED: &str = "#8a6a2b";
+
 impl AppConfig {
     pub fn from_env() -> Result<Self> {
         let app_env = std::env::var("APP_ENV").unwrap_or_else(|_| "development".to_string());
@@ -100,6 +117,20 @@ impl AppConfig {
                 .and_then(|v| v.parse().ok())
                 .filter(|&n| n >= 1)
                 .unwrap_or(2),
+            comments_enabled: std::env::var("COMMENTS_ENABLED")
+                .map(|v| {
+                    !matches!(
+                        v.trim().to_ascii_lowercase().as_str(),
+                        "false" | "0" | "no" | "off"
+                    )
+                })
+                .unwrap_or(true),
+            default_theme_preset: std::env::var("THEME_PRESET")
+                .unwrap_or_else(|_| "champagne-gold".to_string()),
+            default_theme_primary: std::env::var("THEME_PRIMARY")
+                .unwrap_or_else(|_| DEFAULT_THEME_SEED.to_string()),
+            default_theme_accent: std::env::var("THEME_ACCENT")
+                .unwrap_or_else(|_| DEFAULT_THEME_SEED.to_string()),
         })
     }
 }

backend/src/handlers/admin.rs

@@ -3,13 +3,13 @@ use std::time::Duration;
 
 use axum::Json;
 use axum::extract::{Query, State};
-use axum::http::{HeaderMap, StatusCode};
+use axum::http::StatusCode;
 use serde::{Deserialize, Serialize};
+use uuid::Uuid;
 
 use crate::auth::middleware::RequireAdmin;
 use crate::error::AppError;
 use crate::services::config;
-use crate::services::rate_limiter::client_ip;
 use crate::state::AppState;
 
 // ── DTOs ─────────────────────────────────────────────────────────────────────
@@ -120,6 +120,16 @@ pub async fn patch_config(
         ("upload_rate_per_hour", true, 1.0, 100_000.0),
         ("feed_rate_per_min", true, 1.0, 100_000.0),
         ("export_rate_per_day", true, 1.0, 100_000.0),
+        // Loose per-IP ceiling on /join. The real anti-spam bucket is per (ip, name); this
+        // only bounds raw volume from one source, so it must stay well above the size of a
+        // party arriving at once (see migration 017).
+        ("join_ip_rate_per_min", true, 1.0, 100_000.0),
+        // Same shape for /recover: the per-(ip, name) bucket is the anti-guessing control,
+        // this only bounds a name-cycling flood in front of a cost-12 bcrypt (migration 019).
+        ("recover_ip_rate_per_min", true, 1.0, 100_000.0),
+        // Aggregate ceiling on likes + comments + comment deletions, per user per minute.
+        // These were the only mutating endpoints with no limit at all (migration 020).
+        ("social_rate_per_min", true, 1.0, 100_000.0),
         ("quota_tolerance", false, 0.0, 1.0),
         ("estimated_guest_count", true, 1.0, 1_000_000.0),
     ];
@@ -134,14 +144,32 @@ pub async fn patch_config(
         // missing from this allowlist — so the switch existed in code and could never be flipped.
         "admin_login_rate_enabled",
         "recover_rate_enabled",
+        "social_rate_enabled",
         "quota_enabled",
         "storage_quota_enabled",
         "upload_count_quota_enabled",
     ];
-    const TEXT_KEYS: &[&str] = &["privacy_note"];
+    const TEXT_KEYS: &[&str] = &[
+        "privacy_note",
+        "theme_preset",
+        "theme_primary",
+        "theme_accent",
+    ];
     const PRIVACY_NOTE_MAX_LEN: usize = 16 * 1024; // 16 KiB free text is plenty
+    // Preset ids the frontend knows how to render (mirror of PRESETS in
+    // frontend/src/lib/theme/palette.ts). "custom" means "use the theme_primary/accent
+    // seeds verbatim". Kept in sync by hand — a new preset must be added in both places.
+    const THEME_PRESETS: &[&str] = &[
+        "champagne-gold",
+        "rose",
+        "sage",
+        "dusk-blue",
+        "classic-silver",
+        "custom",
+    ];
 
     let mut privacy_note_changed = false;
+    let mut theme_changed = false;
 
     // Validate every key first so a bad value in the batch can't leave a partial
     // update behind — validation must fully precede any write.
@@ -169,6 +197,23 @@ pub async fn patch_config(
                     "Wert für {key} liegt außerhalb des zulässigen Bereichs ({min}–{max})."
                 )));
             }
+            // Zero is in range and catastrophic. `quota_tolerance` is the multiplier in
+            // `free_disk * tolerance / active_uploaders`, so 0 makes every per-user limit 0 and
+            // refuses EVERY upload — mid-event, with "Du hast dein Upload-Limit für dieses Event
+            // erreicht", an error naming the wrong cause entirely. `storage_quota_enabled` is the
+            // intended off-switch.
+            //
+            // Rejecting the value rather than raising the floor: very small tolerances are
+            // legitimate (they are how a large disk is throttled down to a sensible per-guest
+            // ceiling, and how the e2e quota tests steer it — around 1e-5 on a 174 GB volume), so
+            // a floor of, say, 0.01 would forbid real configurations to prevent one typo.
+            if key_str == "quota_tolerance" && n == 0.0 {
+                return Err(AppError::BadRequest(
+                    "quota_tolerance = 0 würde jeden Upload blockieren. Zum Abschalten der \
+                     Speicher-Quote stattdessen „Speicher-Quote aktiv“ ausschalten."
+                        .into(),
+                ));
+            }
         } else if BOOL_KEYS.contains(&key_str) {
             match value.trim().to_ascii_lowercase().as_str() {
                 "true" | "false" | "1" | "0" | "yes" | "no" | "on" | "off" => {}
@@ -186,8 +231,23 @@ pub async fn patch_config(
                     "Wert für {key} ist zu lang (max. {PRIVACY_NOTE_MAX_LEN} Zeichen)."
                 )));
             }
-            if key_str == "privacy_note" {
-                privacy_note_changed = true;
+            match key_str {
+                "privacy_note" => privacy_note_changed = true,
+                "theme_preset" => {
+                    if !THEME_PRESETS.contains(&value.trim()) {
+                        return Err(AppError::BadRequest(format!("Ungültiges Theme: {value}.")));
+                    }
+                    theme_changed = true;
+                }
+                "theme_primary" | "theme_accent" => {
+                    if !is_hex_color(value.trim()) {
+                        return Err(AppError::BadRequest(format!(
+                            "Ungültige Farbe für {key}: muss #rrggbb sein."
+                        )));
+                    }
+                    theme_changed = true;
+                }
+                _ => {}
             }
         } else {
             return Err(AppError::BadRequest(format!(
@@ -217,16 +277,30 @@ pub async fn patch_config(
 
     // Notify all clients that a publicly-readable config value changed so their stores
     // (e.g. the privacy note in My Account) refresh without a manual reload.
-    if privacy_note_changed {
+    if privacy_note_changed || theme_changed {
+        let mut keys: Vec<&str> = Vec::new();
+        if privacy_note_changed {
+            keys.push("privacy_note");
+        }
+        if theme_changed {
+            keys.push("theme");
+        }
         let _ = state.sse_tx.send(crate::state::SseEvent::new(
             "event-updated",
-            serde_json::json!({ "keys": ["privacy_note"] }).to_string(),
+            serde_json::json!({ "keys": keys }).to_string(),
         ));
     }
 
     Ok(StatusCode::NO_CONTENT)
 }
 
+/// A strict `#rrggbb` hex-colour check (6 hex digits, leading `#`). Deliberately not
+/// accepting shorthand/`#rgba` so the value is safe to drop straight into CSS.
+fn is_hex_color(s: &str) -> bool {
+    let bytes = s.as_bytes();
+    bytes.len() == 7 && bytes[0] == b'#' && bytes[1..].iter().all(|b| b.is_ascii_hexdigit())
+}
+
 pub async fn get_export_jobs(
     State(state): State<AppState>,
     RequireAdmin(_auth): RequireAdmin,
@@ -274,25 +348,26 @@ pub async fn export_ticket(
 }
 
 /// Validate a download ticket (single-use) and confirm its session still exists.
-async fn authenticate_download_ticket(state: &AppState, ticket: &str) -> Result<(), AppError> {
+/// Resolve a single-use download ticket to the user who minted it. The caller needs the
+/// id to key the export rate limit per-user (see `enforce_export_rate`).
+async fn authenticate_download_ticket(state: &AppState, ticket: &str) -> Result<Uuid, AppError> {
     let token_hash = state
         .sse_tickets
         .consume(ticket)
         .ok_or_else(|| AppError::Unauthorized("Ticket ungültig oder abgelaufen.".into()))?;
-    crate::models::session::Session::find_by_token_hash(&state.pool, &token_hash)
+    let session = crate::models::session::Session::find_by_token_hash(&state.pool, &token_hash)
         .await
         .map_err(|e| AppError::Internal(e.into()))?
         .ok_or_else(|| AppError::Unauthorized("Sitzung nicht gefunden.".into()))?;
-    Ok(())
+    Ok(session.user_id)
 }
 
 pub async fn download_zip(
     State(state): State<AppState>,
     Query(q): Query<DownloadQuery>,
-    headers: HeaderMap,
 ) -> Result<axum::response::Response, AppError> {
-    authenticate_download_ticket(&state, &q.ticket).await?;
-    enforce_export_rate(&state, &headers).await?;
+    let user_id = authenticate_download_ticket(&state, &q.ticket).await?;
+    enforce_export_rate(&state, user_id).await?;
 
     let path =
         resolve_export_file(&state, "zip", "Der ZIP-Export ist noch nicht verfügbar.").await?;
@@ -343,10 +418,9 @@ async fn resolve_export_file(
 pub async fn download_html(
     State(state): State<AppState>,
     Query(q): Query<DownloadQuery>,
-    headers: HeaderMap,
 ) -> Result<axum::response::Response, AppError> {
-    authenticate_download_ticket(&state, &q.ticket).await?;
-    enforce_export_rate(&state, &headers).await?;
+    let user_id = authenticate_download_ticket(&state, &q.ticket).await?;
+    enforce_export_rate(&state, user_id).await?;
 
     let path =
         resolve_export_file(&state, "html", "Der HTML-Export ist noch nicht verfügbar.").await?;
@@ -403,8 +477,13 @@ pub async fn export_status(
     // worker superseded mid-run) is meaningless — surfacing its frozen `running`/77% would show a
     // progress bar that never moves for a keepsake nobody is building. It reads as "locked" (no
     // current job), which is exactly what it is.
-    let jobs: Vec<(String, String, i16)> = sqlx::query_as(
-        "SELECT j.type::text, j.status::text, j.progress_pct
+    // `error_message` is carried here, not just on the admin dashboard's job list. The host is the
+    // one who releases the keepsake and the one who owns the "Erneut versuchen" button, but this
+    // endpoint used to hand them a bare `failed` — so a fully actionable reason (notably the disk
+    // preflight's "needs X GB, Y GB free") was written to the row and then shown to nobody who
+    // could act on it. An admin-only diagnostic is not a diagnostic for the person on the spot.
+    let jobs: Vec<(String, String, i16, Option<String>)> = sqlx::query_as(
+        "SELECT j.type::text, j.status::text, j.progress_pct, j.error_message
            FROM export_job j
            JOIN event e ON e.id = j.event_id
           WHERE e.id = $1 AND j.epoch = e.export_epoch",
@@ -415,9 +494,21 @@ pub async fn export_status(
 
     let job_status = |type_name: &str| {
         jobs.iter()
-            .find(|(t, _, _)| t == type_name)
-            .map(|(_, status, pct)| serde_json::json!({ "status": status, "progress_pct": pct }))
-            .unwrap_or_else(|| serde_json::json!({ "status": "locked", "progress_pct": 0 }))
+            .find(|(t, _, _, _)| t == type_name)
+            .map(|(_, status, pct, err)| {
+                serde_json::json!({
+                    "status": status,
+                    "progress_pct": pct,
+                    // Only on a failure. A stale message left on a row that has since been re-armed
+                    // would otherwise show an error next to a running progress bar.
+                    "error_message": if status == "failed" { err.clone() } else { None },
+                })
+            })
+            .unwrap_or_else(|| {
+                serde_json::json!({
+                    "status": "locked", "progress_pct": 0, "error_message": null,
+                })
+            })
     };
 
     Ok(Json(serde_json::json!({
@@ -430,21 +521,24 @@ pub async fn export_status(
 /// Centralised guard for the export rate limit. Same pattern as upload/feed: master
 /// switch + per-endpoint switch + numeric value, all stored in `config` and read on
 /// each request.
-async fn enforce_export_rate(state: &AppState, headers: &HeaderMap) -> Result<(), AppError> {
+async fn enforce_export_rate(state: &AppState, user_id: Uuid) -> Result<(), AppError> {
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     let export_rate_on = config::get_bool(&state.config_cache, "export_rate_enabled", true).await;
     if !(rate_limits_on && export_rate_on) {
         return Ok(());
     }
-    let ip = client_ip(headers, "unknown");
     let limit = config::get_usize(&state.config_cache, "export_rate_per_day", 3).await;
-    if !state
-        .rate_limiter
-        .check(format!("export:{ip}"), limit, Duration::from_secs(86400))
-    {
+    // Keyed per-user. This was the worst of the IP-keyed limiters: 3 downloads per DAY
+    // shared across every guest behind the venue's public IP, so the fourth person to
+    // fetch their keepsake was locked out until the next day.
+    if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+        format!("export:{user_id}"),
+        limit,
+        Duration::from_secs(86400),
+    ) {
         return Err(AppError::TooManyRequests(
             "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
-            None,
+            Some(retry_after_secs),
         ));
     }
     Ok(())

backend/src/handlers/feed.rs

@@ -2,7 +2,6 @@ use std::time::Duration;
 
 use axum::Json;
 use axum::extract::{Query, State};
-use axum::http::HeaderMap;
 use chrono::{DateTime, Utc};
 use serde::{Deserialize, Serialize};
 use uuid::Uuid;
@@ -10,7 +9,6 @@ use uuid::Uuid;
 use crate::auth::middleware::AuthUser;
 use crate::error::AppError;
 use crate::services::config;
-use crate::services::rate_limiter::client_ip;
 use crate::state::AppState;
 
 #[derive(Deserialize)]
@@ -27,6 +25,8 @@ pub struct FeedUpload {
     pub uploader_name: String,
     pub preview_url: Option<String>,
     pub thumbnail_url: Option<String>,
+    /// Big-screen (~2048px) variant for the diashow. Absent until the derivative exists.
+    pub display_url: Option<String>,
     pub mime_type: String,
     pub caption: Option<String>,
     pub like_count: i64,
@@ -48,6 +48,7 @@ struct FeedRow {
     uploader_name: String,
     preview_path: Option<String>,
     thumbnail_path: Option<String>,
+    display_path: Option<String>,
     mime_type: String,
     caption: Option<String>,
     like_count: i64,
@@ -58,21 +59,23 @@ struct FeedRow {
 pub async fn feed(
     State(state): State<AppState>,
     auth: AuthUser,
-    headers: HeaderMap,
     Query(q): Query<FeedQuery>,
 ) -> Result<Json<FeedResponse>, AppError> {
-    let ip = client_ip(&headers, "unknown");
     let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
     let feed_rate_on = config::get_bool(&state.config_cache, "feed_rate_enabled", true).await;
     if rate_limits_on && feed_rate_on {
         let rate_limit = config::get_usize(&state.config_cache, "feed_rate_per_min", 60).await;
-        if !state
-            .rate_limiter
-            .check(format!("feed:{ip}"), rate_limit, Duration::from_secs(60))
-        {
+        // Keyed per-user, exactly like `feed_delta` below: at a venue every guest shares
+        // one public IP, so an IP key gave the whole party a single 60/min bucket and the
+        // fastest scroller starved everyone else.
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
+            format!("feed:{}", auth.user_id),
+            rate_limit,
+            Duration::from_secs(60),
+        ) {
             return Err(AppError::TooManyRequests(
                 "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
-                None,
+                Some(retry_after_secs),
             ));
         }
     }
@@ -94,7 +97,8 @@ pub async fn feed(
         let tag = hashtag.trim().trim_start_matches('#').to_lowercase();
         sqlx::query_as::<_, FeedRow>(
             "SELECT v.id, v.user_id, v.uploader_name, v.preview_path, v.thumbnail_path,
-                    v.mime_type, v.caption, v.like_count, v.comment_count, v.created_at
+                    v.display_path, v.mime_type, v.caption, v.like_count, v.comment_count,
+                    v.created_at
              FROM v_feed v
              JOIN upload_hashtag uh ON uh.upload_id = v.id
              JOIN hashtag h ON h.id = uh.hashtag_id AND h.tag = $1
@@ -113,7 +117,7 @@ pub async fn feed(
     } else {
         sqlx::query_as::<_, FeedRow>(
             "SELECT id, user_id, uploader_name, preview_path, thumbnail_path,
-                    mime_type, caption, like_count, comment_count, created_at
+                    display_path, mime_type, caption, like_count, comment_count, created_at
              FROM v_feed
              WHERE event_id = $1
                AND ($2::timestamptz IS NULL OR (created_at, id) < ($2, $3))
@@ -154,6 +158,10 @@ pub async fn feed(
                 .thumbnail_path
                 .as_ref()
                 .map(|_| format!("/api/v1/upload/{}/thumbnail", r.id));
+            let display_url = r
+                .display_path
+                .as_ref()
+                .map(|_| format!("/api/v1/upload/{}/display", r.id));
             FeedUpload {
                 liked_by_me: liked_set.contains(&r.id),
                 id: r.id,
@@ -161,6 +169,7 @@ pub async fn feed(
                 uploader_name: r.uploader_name,
                 preview_url,
                 thumbnail_url,
+                display_url,
                 mime_type: r.mime_type,
                 caption: r.caption,
                 like_count: r.like_count,
@@ -216,14 +225,14 @@ pub async fn feed_delta(
     let feed_rate_on = config::get_bool(&state.config_cache, "feed_rate_enabled", true).await;
     if rate_limits_on && feed_rate_on {
         let rate_limit = config::get_usize(&state.config_cache, "feed_rate_per_min", 60).await;
-        if !state.rate_limiter.check(
+        if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
             format!("feed_delta:{}", auth.user_id),
             rate_limit,
             Duration::from_secs(60),
         ) {
             return Err(AppError::TooManyRequests(
                 "Zu viele Anfragen. Bitte warte kurz und versuche es erneut.".into(),
-                None,
+                Some(retry_after_secs),
             ));
         }
     }
@@ -247,7 +256,7 @@ pub async fn feed_delta(
     // response's `server_time`, so this doesn't re-fetch on every subsequent delta.
     let rows = sqlx::query_as::<_, FeedRow>(
         "SELECT id, user_id, uploader_name, preview_path, thumbnail_path,
-                mime_type, caption, like_count, comment_count, created_at
+                display_path, mime_type, caption, like_count, comment_count, created_at
          FROM v_feed
          WHERE event_id = $1 AND created_at >= $2
          ORDER BY created_at DESC, id DESC
@@ -304,6 +313,10 @@ pub async fn feed_delta(
                 .thumbnail_path
                 .as_ref()
                 .map(|_| format!("/api/v1/upload/{}/thumbnail", r.id)),
+            display_url: r
+                .display_path
+                .as_ref()
+                .map(|_| format!("/api/v1/upload/{}/display", r.id)),
             mime_type: r.mime_type,
             caption: r.caption,
             like_count: r.like_count,

backend/src/handlers/host.rs

@@ -35,6 +35,32 @@ pub struct EventStatus {
     pub is_active: bool,
     pub uploads_locked: bool,
     pub export_released: bool,
+    /// Free space on the volume the keepsake is written to. `None` when the mount can't be
+    /// resolved — the UI hides the widget rather than rendering a confident zero.
+    pub disk_free_bytes: Option<u64>,
+    /// What a full keepsake build would need right now (both halves).
+    pub keepsake_required_bytes: u64,
+    /// Whether the host should be warned. See [`disk_is_low`].
+    pub disk_low: bool,
+}
+
+/// Absolute floor below which free space is worth surfacing regardless of gallery size — the
+/// threshold the README has carried on the roadmap since v1.
+const LOW_DISK_FLOOR_BYTES: u64 = 10_000_000_000;
+
+/// Is free space low enough that the host needs to know?
+///
+/// Two triggers, because a fixed threshold answers the wrong question. `postgres_data`,
+/// `media_data` and `exports_data` are all Docker named volumes on one filesystem, so a full disk
+/// does not degrade one subsystem — it stops Postgres writing and takes the event down. That is
+/// what the absolute floor is for.
+///
+/// The second trigger is the one that actually earns its place: the keepsake needs room for two
+/// gallery-sized archives, and the only moment a host can do anything about that is BEFORE they
+/// release. Warning at "you could not build the keepsake right now" turns a post-event dead end
+/// into a decision someone can still make.
+fn disk_is_low(free: u64, keepsake_required: u64) -> bool {
+    free < LOW_DISK_FLOOR_BYTES || free < keepsake_required
 }
 
 /// Count non-banned hosts/admins in the event OTHER than `excluding` — the operators
@@ -72,11 +98,29 @@ pub async fn get_event_status(
         .await?
         .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
 
+    // Measured on the EXPORT volume, not the media one: that is where the cliff is, and it is a
+    // distinct mount point even when both are backed by the same filesystem. The cached reading is
+    // right here — this is advisory, polled on every dashboard load, and a 15s-stale number costs
+    // nothing (unlike the export preflight, which reads uncached because it is about to write).
+    let free = state
+        .disk_cache
+        .snapshot(&state.config.export_path)
+        .map(|d| d.free);
+    let keepsake_required_bytes =
+        crate::services::export::keepsake_space_required(&state.pool, event.id)
+            .await
+            .unwrap_or(0);
+
     Ok(Json(EventStatus {
         name: event.name,
         is_active: event.is_active,
         uploads_locked: event.uploads_locked_at.is_some(),
         export_released: event.export_released_at.is_some(),
+        disk_free_bytes: free,
+        keepsake_required_bytes,
+        // Unknown free space is NOT low. Fails open, exactly as the upload quota and the export
+        // preflight do: a scary banner on an unreadable mount would train the host to ignore it.
+        disk_low: free.is_some_and(|f| disk_is_low(f, keepsake_required_bytes)),
     }))
 }
 
@@ -302,6 +346,7 @@ pub async fn rebuild_export(
         r.event_id,
         r.event_name,
         r.epoch,
+        state.config.comments_enabled,
         std::time::Duration::ZERO,
         state.pool.clone(),
         state.config.media_path.clone(),
@@ -432,7 +477,7 @@ pub async fn reset_user_pin(
     }
 
     let pin: String = format!("{:04}", rand::rng().random_range(0..10000u32));
-    let pin_hash = bcrypt::hash(&pin, 12).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
+    let pin_hash = crate::auth::handlers::hash_password(pin.clone(), 12).await?;
 
     sqlx::query(
         "UPDATE \"user\"
@@ -549,6 +594,7 @@ pub fn start_regen(state: &AppState, regen: crate::services::export::PendingRege
         regen.event_id,
         regen.event_name,
         regen.epoch,
+        state.config.comments_enabled,
         // Debounced: a takedown pass is a burst, and each request retires the last generation. The
         // delay lets superseded workers fail their claim and do zero work instead of each building
         // a full archive. See export::REGEN_DEBOUNCE.
@@ -753,6 +799,7 @@ pub async fn release_gallery(
         event_id,
         event_name,
         epoch,
+        state.config.comments_enabled,
         std::time::Duration::ZERO,
         state.pool.clone(),
         state.config.media_path.clone(),
@@ -762,3 +809,45 @@ pub async fn release_gallery(
 
     Ok(StatusCode::NO_CONTENT)
 }
+
+#[cfg(test)]
+mod tests {
+    use super::{LOW_DISK_FLOOR_BYTES, disk_is_low};
+
+    const GB: u64 = 1_000_000_000;
+
+    #[test]
+    fn a_healthy_disk_with_room_for_the_keepsake_is_not_low() {
+        assert!(!disk_is_low(40 * GB, 25 * GB));
+    }
+
+    #[test]
+    fn the_absolute_floor_fires_even_when_the_gallery_is_tiny() {
+        // All three volumes share one filesystem, so running out doesn't degrade one subsystem —
+        // Postgres stops being able to write and the event goes down. A 1 GB gallery would clear
+        // the keepsake test comfortably; the floor is what catches this.
+        assert!(disk_is_low(5 * GB, GB));
+        assert!(disk_is_low(LOW_DISK_FLOOR_BYTES - 1, 0));
+        assert!(!disk_is_low(LOW_DISK_FLOOR_BYTES, 0));
+    }
+
+    #[test]
+    fn plenty_of_space_is_still_low_when_the_keepsake_would_not_fit() {
+        // THE case the fixed threshold misses, and the one that matters: 30 GB free is nowhere near
+        // any floor, but a 30 GB gallery needs room for TWO archives. The host can act on this
+        // before releasing; after releasing, they cannot.
+        assert!(disk_is_low(30 * GB, 66 * GB));
+    }
+
+    #[test]
+    fn the_keepsake_trigger_is_exact_at_the_boundary() {
+        assert!(!disk_is_low(66 * GB, 66 * GB), "exactly enough is enough");
+        assert!(disk_is_low(66 * GB - 1, 66 * GB));
+    }
+
+    #[test]
+    fn an_empty_gallery_needs_nothing_and_only_the_floor_applies() {
+        assert!(!disk_is_low(11 * GB, 0));
+        assert!(disk_is_low(9 * GB, 0));
+    }
+}

backend/src/handlers/me.rs

@@ -14,7 +14,7 @@ use serde::Serialize;
 use crate::auth::middleware::AuthUser;
 use crate::error::AppError;
 use crate::handlers::upload::compute_storage_quota;
-use crate::models::user::User;
+use crate::models::user::{User, UserRole};
 use crate::services::config;
 use crate::state::AppState;
 
@@ -37,12 +37,26 @@ pub async fn get_quota(
 
     let estimate = compute_storage_quota(&state).await;
 
+    // Raw server telemetry (free disk, concurrent uploader count) is staff-only — it
+    // must never reach a guest, even though the guest upload UI no longer renders it.
+    // A guest still gets their own `used`/`limit` so enforcement stays transparent to
+    // the code paths that consume it; only the server-wide fields are zeroed.
+    let is_staff = matches!(auth.role, UserRole::Host | UserRole::Admin);
+
     Ok(Json(QuotaDto {
         enabled: estimate.limit_bytes.is_some(),
         used_bytes: user.total_upload_bytes,
         limit_bytes: estimate.limit_bytes,
-        active_uploaders: estimate.active_uploaders,
-        free_disk_bytes: estimate.free_disk_bytes,
+        active_uploaders: if is_staff {
+            estimate.active_uploaders
+        } else {
+            0
+        },
+        free_disk_bytes: if is_staff {
+            estimate.free_disk_bytes
+        } else {
+            0
+        },
     }))
 }
 

backend/src/handlers/public.rs

@@ -4,21 +4,41 @@ use axum::Json;
 use axum::extract::State;
 use serde::Serialize;
 
+use crate::services::config;
 use crate::state::AppState;
 
 #[derive(Serialize)]
 pub struct PublicEventDto {
     pub name: String,
     pub slug: String,
+    /// Whether the comment feature is on (env `COMMENTS_ENABLED`). The frontend hides
+    /// the whole comment UI when false; exposed here so even the pre-auth shell knows.
+    pub comments_enabled: bool,
+    /// Active colour theme. `preset` is an id the frontend maps to a palette (or
+    /// "custom"); `primary`/`accent` are the `#rrggbb` seeds the ramps derive from.
+    /// Resolved as DB-config override → env default. Public so the theme applies on
+    /// the very first (pre-auth) paint without a flash.
+    pub theme_preset: String,
+    pub theme_primary: String,
+    pub theme_accent: String,
 }
 
-/// Public event identity, used by the pre-auth join/recover screens so a guest can
-/// see *which* event they're joining. Only the display name and slug are exposed —
-/// nothing user-scoped — so this is safe without a token. Served straight from the
-/// instance config (no DB round-trip needed).
+/// Public event identity + presentation config, used by the pre-auth join/recover
+/// screens (which event am I joining, what does it look like). Only non-user-scoped
+/// fields are exposed, so this is safe without a token. Identity comes straight from
+/// instance config; the theme is resolved from the runtime `config` table (admin UI)
+/// falling back to the env-seeded default.
 pub async fn get_public_event(State(state): State<AppState>) -> Json<PublicEventDto> {
+    let cache = &state.config_cache;
     Json(PublicEventDto {
         name: state.config.event_name.clone(),
         slug: state.config.event_slug.clone(),
+        comments_enabled: state.config.comments_enabled,
+        theme_preset: config::get_str(cache, "theme_preset", &state.config.default_theme_preset)
+            .await,
+        theme_primary: config::get_str(cache, "theme_primary", &state.config.default_theme_primary)
+            .await,
+        theme_accent: config::get_str(cache, "theme_accent", &state.config.default_theme_accent)
+            .await,
     })
 }

backend/src/handlers/social.rs

@@ -10,8 +10,40 @@ use crate::error::AppError;
 use crate::models::comment::{Comment, CommentDto};
 use crate::models::hashtag::{self, Hashtag};
 use crate::models::upload::Upload;
+use crate::services::config;
 use crate::state::AppState;
 
+/// Throttle a social write. Keyed PER USER, like the feed and upload limits and for the same
+/// reason: at a venue every guest sits behind one NAT, so an IP key hands the whole party a
+/// single bucket and the most active guest starves everyone else.
+///
+/// These were the only mutating endpoints in the app with no limit at all — the coverage was
+/// asymmetric, not deliberately open. The ceiling is set well above anything a real guest
+/// produces; this bounds a script, not an enthusiastic double-tapper.
+async fn check_social_rate(state: &AppState, user_id: Uuid) -> Result<(), AppError> {
+    let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
+    let social_rate_on = config::get_bool(&state.config_cache, "social_rate_enabled", true).await;
+    if !(rate_limits_on && social_rate_on) {
+        return Ok(());
+    }
+    let rate_limit = config::get_usize(&state.config_cache, "social_rate_per_min", 120).await;
+    // ONE bucket across likes, comments and comment deletions. Separate buckets would let a
+    // caller triple the aggregate write rate just by alternating between them.
+    state
+        .rate_limiter
+        .check_with_retry(
+            format!("social:{user_id}"),
+            rate_limit,
+            std::time::Duration::from_secs(60),
+        )
+        .map_err(|retry_after_secs| {
+            AppError::TooManyRequests(
+                "Zu viele Aktionen. Bitte warte kurz und versuche es erneut.".into(),
+                Some(retry_after_secs),
+            )
+        })
+}
+
 #[derive(Serialize)]
 pub struct LikeResponse {
     /// The caller's like state *after* this toggle. The client sets `liked_by_me` from
@@ -35,6 +67,7 @@ pub async fn toggle_like(
     if user.is_banned {
         return Err(AppError::Forbidden("Du bist gesperrt.".into()));
     }
+    check_social_rate(&state, auth.user_id).await?;
 
     // Event-scope: the upload must belong to the caller's event (404 otherwise),
     // matching the host handlers' find_by_id_and_event pattern.
@@ -129,12 +162,19 @@ pub async fn add_comment(
     Path(upload_id): Path<Uuid>,
     Json(body): Json<AddCommentRequest>,
 ) -> Result<(StatusCode, Json<CommentDto>), AppError> {
+    // Comments can be disabled instance-wide (env COMMENTS_ENABLED). The frontend hides
+    // the UI, but gate the API too so a stale client or direct call can't slip one in.
+    if !state.config.comments_enabled {
+        return Err(AppError::Forbidden("Kommentare sind deaktiviert.".into()));
+    }
+
     let user = crate::models::user::User::find_by_id(&state.pool, auth.user_id)
         .await?
         .ok_or_else(|| AppError::NotFound("Benutzer nicht gefunden.".into()))?;
     if user.is_banned {
         return Err(AppError::Forbidden("Du bist gesperrt.".into()));
     }
+    check_social_rate(&state, auth.user_id).await?;
 
     // Event-scope: only comment on an upload that belongs to the caller's event.
     Upload::find_by_id_and_event(&state.pool, upload_id, auth.event_id)
@@ -210,6 +250,7 @@ pub async fn delete_comment(
     if auth.is_banned {
         return Err(AppError::Forbidden("Du bist gesperrt.".into()));
     }
+    check_social_rate(&state, auth.user_id).await?;
     let comment = Comment::find_by_id(&state.pool, comment_id)
         .await?
         .ok_or_else(|| AppError::NotFound("Kommentar nicht gefunden.".into()))?;

backend/src/handlers/test_admin.rs

@@ -13,9 +13,10 @@ use crate::auth::middleware::RequireAdmin;
 use crate::error::AppError;
 use crate::state::AppState;
 
-/// Truncates every event-scoped table, wipes media on disk, and reseeds the
-/// `config` table from migration defaults. Requires an admin JWT — even with
-/// `EVENTSNAP_TEST_MODE=1` it cannot be hit anonymously.
+/// Truncates every event-scoped table, wipes media on disk, and reseeds the `config`
+/// table: numeric values from the migration defaults, but every feature toggle forced
+/// OFF (production seeds them ON — see the note at the reseed below). Requires an admin
+/// JWT — even with `EVENTSNAP_TEST_MODE=1` it cannot be hit anonymously.
 pub async fn truncate_all(
     State(state): State<AppState>,
     RequireAdmin(_auth): RequireAdmin,
@@ -40,15 +41,29 @@ pub async fn truncate_all(
     .execute(&state.pool)
     .await?;
 
-    // Reseed config — mirrors migrations 005 and 009. Kept in sync by hand
-    // because pulling SQL out of the migration files at runtime is fragile.
+    // Reseed config. The NUMERIC values mirror migrations 005/015/016/017/019; the BOOLEAN
+    // toggles deliberately do NOT — migration 009 seeds every one of them `true`
+    // (production), and this forces them `false` so the suite isn't fighting rate limits
+    // and quotas it isn't testing.
+    //
+    // Be aware of what that costs: this runs as an auto-fixture before EVERY test, so no
+    // test starts from production's config unless it explicitly turns a toggle back on
+    // (02-upload/rate-limit, 07-adversarial/ddos, 01-auth/rate-limit-nat, …). That blind
+    // spot is exactly why an entire class of per-IP limiter bugs went unnoticed: the
+    // limiters were simply off. When adding a limiter or quota, add a spec that enables it.
+    //
+    // Kept in sync by hand because pulling SQL out of the migration files at runtime is
+    // fragile — if you add a config key in a migration, add it here too.
     sqlx::query(
         r#"INSERT INTO config (key, value) VALUES
             ('max_image_size_mb',          '20'),
             ('max_video_size_mb',          '500'),
-            ('upload_rate_per_hour',       '10'),
+            ('upload_rate_per_hour',       '100'),
             ('feed_rate_per_min',          '60'),
             ('export_rate_per_day',        '3'),
+            ('join_ip_rate_per_min',       '60'),
+            ('recover_ip_rate_per_min',    '30'),
+            ('social_rate_per_min',        '120'),
             ('quota_tolerance',            '0.75'),
             ('estimated_guest_count',      '100'),
             ('compression_concurrency',    '2'),
@@ -57,6 +72,8 @@ pub async fn truncate_all(
             ('feed_rate_enabled',          'false'),
             ('export_rate_enabled',        'false'),
             ('join_rate_enabled',          'false'),
+            ('social_rate_enabled',        'false'),
+            ('admin_login_rate_enabled',   'false'),
             ('quota_enabled',              'false'),
             ('storage_quota_enabled',      'false'),
             ('upload_count_quota_enabled', 'false'),

backend/src/handlers/upload.rs

@@ -48,7 +48,7 @@ pub async fn upload(
     let upload_rate_on = config::get_bool(&state.config_cache, "upload_rate_enabled", true).await;
     if rate_limits_on && upload_rate_on {
         let upload_rate =
-            config::get_i64(&state.config_cache, "upload_rate_per_hour", 10).await as usize;
+            config::get_i64(&state.config_cache, "upload_rate_per_hour", 100).await as usize;
         if let Err(retry_after_secs) = state.rate_limiter.check_with_retry(
             format!("upload:{}", auth.user_id),
             upload_rate,
@@ -233,6 +233,26 @@ pub async fn upload(
         )));
     }
 
+    // Images only: refuse anything the compression worker could never decode, reading just
+    // the header. Without this the upload is accepted with a 201 and then silently
+    // soft-deleted minutes later when the worker gives up — the guest sees the photo
+    // vanish with, at best, a vague "could not be processed". Rejecting here gives them a
+    // reason at the door that they can act on, and it uses the SAME budget the worker
+    // enforces, so admission and processing cannot disagree.
+    if mime.starts_with("image/") && crate::services::imaging::exceeds_decode_budget(&temp_abs) {
+        let mp = crate::services::imaging::megapixels(&temp_abs);
+        tracing::info!(
+            %mime, megapixels = ?mp,
+            "rejecting an image that exceeds the decode budget at admission"
+        );
+        let _ = tokio::fs::remove_file(&temp_abs).await;
+        let detail = mp.map_or(String::new(), |mp| format!(" (ca. {mp:.0} Megapixel)"));
+        return Err(AppError::BadRequest(format!(
+            "Bild hat zu viele Bildpunkte{detail} und kann nicht verarbeitet werden. \
+             Bitte verkleinere es und lade es erneut hoch."
+        )));
+    }
+
     // Per-user storage quota — dynamic formula based on available disk space and the
     // number of active uploaders. Gated by master + per-area toggles so the admin can
     // disable it on trusted instances.
@@ -647,12 +667,95 @@ pub async fn compute_storage_quota(state: &AppState) -> QuotaEstimate {
     }
 }
 
+/// Outcome of parsing a `Range` request header against a known file length.
+#[derive(Debug, PartialEq, Eq)]
+enum RangeSpec {
+    /// No `Range` header, or one we deliberately don't honour (multi-range, non-`bytes`
+    /// unit, malformed). RFC 9110 lets a server ignore a Range it can't process and reply
+    /// 200 with the full body, which is what every one of these cases does.
+    Full,
+    /// A single satisfiable range, resolved to inclusive absolute offsets.
+    Partial { start: u64, end: u64 },
+    /// Syntactically valid but starts beyond EOF — must be answered 416, not 200, or a
+    /// player can loop re-requesting it.
+    Unsatisfiable,
+}
+
+/// Parse a single-range `bytes=` header against `len`.
+///
+/// Deliberately supports only the three forms a media element actually sends —
+/// `bytes=N-`, `bytes=N-M`, `bytes=-S` (suffix) — and treats everything else as `Full`.
+/// Multi-range responses need `multipart/byteranges`, which no `<video>` requires.
+fn parse_range(header: Option<&str>, len: u64) -> RangeSpec {
+    let Some(raw) = header else {
+        return RangeSpec::Full;
+    };
+    let Some(spec) = raw.trim().strip_prefix("bytes=") else {
+        return RangeSpec::Full;
+    };
+    // Multi-range → fall back to the whole body rather than lie about the content.
+    if spec.contains(',') {
+        return RangeSpec::Full;
+    }
+    let Some((from, to)) = spec.split_once('-') else {
+        return RangeSpec::Full;
+    };
+    let (from, to) = (from.trim(), to.trim());
+
+    // A zero-length file can satisfy no range at all.
+    if len == 0 {
+        return if from.is_empty() && to.is_empty() {
+            RangeSpec::Full
+        } else {
+            RangeSpec::Unsatisfiable
+        };
+    }
+
+    let (start, end) = if from.is_empty() {
+        // Suffix form: the last `to` bytes.
+        let Ok(suffix) = to.parse::<u64>() else {
+            return RangeSpec::Full;
+        };
+        if suffix == 0 {
+            return RangeSpec::Unsatisfiable;
+        }
+        (len.saturating_sub(suffix), len - 1)
+    } else {
+        let Ok(start) = from.parse::<u64>() else {
+            return RangeSpec::Full;
+        };
+        let end = if to.is_empty() {
+            len - 1
+        } else {
+            match to.parse::<u64>() {
+                // An end past EOF is clamped, not rejected (RFC 9110 §14.1.1).
+                Ok(end) => end.min(len - 1),
+                Err(_) => return RangeSpec::Full,
+            }
+        };
+        (start, end)
+    };
+
+    if start >= len || start > end {
+        RangeSpec::Unsatisfiable
+    } else {
+        RangeSpec::Partial { start, end }
+    }
+}
+
 /// Stream a media file from disk into an HTTP response with a fixed set of security
-/// headers. Every media response (original, preview, thumbnail) goes through here so
-/// they consistently carry `X-Content-Type-Options: nosniff` (defense-in-depth against
+/// headers. Every media response (original, preview, display, thumbnail) goes through here
+/// so they consistently carry `X-Content-Type-Options: nosniff` (defense-in-depth against
 /// content-type confusion, even if the edge proxy is bypassed) plus an explicit
 /// `Content-Disposition` and `Cache-Control`.
+///
+/// Honours a single `Range`. This is not an optimisation: iOS Safari opens every `<video>`
+/// with a `Range: bytes=0-1` probe and abandons the load unless it gets a `206` with a
+/// `Content-Range`. Without this, video is unplayable on the app's primary platform no
+/// matter what `src` the element is given. `Accept-Ranges: bytes` is advertised on every
+/// response so clients know seeking is available before they ask.
 async fn stream_media_file(
+    req_headers: &axum::http::HeaderMap,
     absolute: &std::path::Path,
     content_type: String,
     disposition: &str,
@@ -660,30 +763,60 @@ async fn stream_media_file(
 ) -> Result<axum::response::Response, AppError> {
     use axum::body::Body;
     use axum::http::{Response, StatusCode, header};
+    use tokio::io::{AsyncReadExt, AsyncSeekExt};
     use tokio_util::io::ReaderStream;
 
     if !absolute.exists() {
         return Err(AppError::NotFound("Datei nicht gefunden.".into()));
     }
 
-    let file = tokio::fs::File::open(absolute)
+    let mut file = tokio::fs::File::open(absolute)
         .await
         .map_err(|e| AppError::Internal(e.into()))?;
-    let metadata = file
+    let len = file
         .metadata()
         .await
-        .map_err(|e| AppError::Internal(e.into()))?;
-    let stream = ReaderStream::new(file);
+        .map_err(|e| AppError::Internal(e.into()))?
+        .len();
 
-    Response::builder()
-        .status(StatusCode::OK)
-        .header(header::CONTENT_TYPE, content_type)
-        .header(header::CONTENT_DISPOSITION, disposition)
-        .header(header::CONTENT_LENGTH, metadata.len())
-        .header(header::CACHE_CONTROL, cache_control)
-        .header(header::X_CONTENT_TYPE_OPTIONS, "nosniff")
-        .body(Body::from_stream(stream))
-        .map_err(|e| AppError::Internal(e.into()))
+    let range = parse_range(
+        req_headers.get(header::RANGE).and_then(|v| v.to_str().ok()),
+        len,
+    );
+
+    let base = |status: StatusCode| {
+        Response::builder()
+            .status(status)
+            .header(header::CONTENT_TYPE, content_type.clone())
+            .header(header::CONTENT_DISPOSITION, disposition)
+            .header(header::CACHE_CONTROL, cache_control)
+            .header(header::X_CONTENT_TYPE_OPTIONS, "nosniff")
+            .header(header::ACCEPT_RANGES, "bytes")
+    };
+
+    match range {
+        RangeSpec::Full => base(StatusCode::OK)
+            .header(header::CONTENT_LENGTH, len)
+            .body(Body::from_stream(ReaderStream::new(file)))
+            .map_err(|e| AppError::Internal(e.into())),
+
+        RangeSpec::Partial { start, end } => {
+            file.seek(std::io::SeekFrom::Start(start))
+                .await
+                .map_err(|e| AppError::Internal(e.into()))?;
+            let span = end - start + 1;
+            base(StatusCode::PARTIAL_CONTENT)
+                .header(header::CONTENT_LENGTH, span)
+                .header(header::CONTENT_RANGE, format!("bytes {start}-{end}/{len}"))
+                .body(Body::from_stream(ReaderStream::new(file.take(span))))
+                .map_err(|e| AppError::Internal(e.into()))
+        }
+
+        RangeSpec::Unsatisfiable => base(StatusCode::RANGE_NOT_SATISFIABLE)
+            .header(header::CONTENT_RANGE, format!("bytes */{len}"))
+            .body(Body::empty())
+            .map_err(|e| AppError::Internal(e.into())),
+    }
 }
 
 /// Streaming download of the original file behind an upload. Used by:
@@ -700,6 +833,7 @@ async fn stream_media_file(
 /// [`get_preview`] / [`get_thumbnail`]).
 pub async fn get_original(
     State(state): State<AppState>,
+    headers: axum::http::HeaderMap,
     Path(upload_id): Path<Uuid>,
 ) -> Result<axum::response::Response, AppError> {
     let media = Upload::find_visible_media(&state.pool, upload_id)
@@ -711,10 +845,22 @@ pub async fn get_original(
         .file_name()
         .and_then(|n| n.to_str())
         .unwrap_or("original");
-    let disposition = format!("attachment; filename=\"{filename}\"");
+    // `inline`, not `attachment`. This route is the only source of playable video bytes
+    // (there is no video derivative), and an attachment disposition is hostile to a
+    // `<video>` element — Safari in particular. It also matches what the UI promises:
+    // the action is labelled "Original anzeigen", i.e. view, not download.
+    let disposition = format!("inline; filename=\"{filename}\"");
 
-    // Full-res original: force download, never cache at the edge.
-    stream_media_file(&absolute, media.mime_type, &disposition, "no-store").await
+    // Full-res original: never cache at the edge, so a takedown revokes access promptly.
+    // Range requests still work under no-store; the client simply re-fetches each range.
+    stream_media_file(
+        &headers,
+        &absolute,
+        media.mime_type,
+        &disposition,
+        "no-store",
+    )
+    .await
 }
 
 /// Streaming access to an upload's compressed **preview** image. Gated exactly like
@@ -729,6 +875,7 @@ pub async fn get_original(
 /// `upload-deleted` / `user-hidden` SSE events, so this only bounds the raw-URL edge case.
 pub async fn get_preview(
     State(state): State<AppState>,
+    headers: axum::http::HeaderMap,
     Path(upload_id): Path<Uuid>,
 ) -> Result<axum::response::Response, AppError> {
     let media = Upload::find_visible_media(&state.pool, upload_id)
@@ -739,6 +886,33 @@ pub async fn get_preview(
         .ok_or_else(|| AppError::NotFound("Vorschau nicht verfügbar.".into()))?;
     let absolute = state.config.media_path.join(&rel);
     stream_media_file(
+        &headers,
+        &absolute,
+        "image/jpeg".to_string(),
+        "inline",
+        "private, max-age=300",
+    )
+    .await
+}
+
+/// Streaming access to an upload's big-screen **display** derivative (~2048px), used by the
+/// diashow. Gated identically to [`get_preview`]. 404s when the derivative doesn't exist yet
+/// (still compressing, or an old upload the backfill hasn't reached) — the diashow then falls
+/// back to the original.
+pub async fn get_display(
+    State(state): State<AppState>,
+    headers: axum::http::HeaderMap,
+    Path(upload_id): Path<Uuid>,
+) -> Result<axum::response::Response, AppError> {
+    let media = Upload::find_visible_media(&state.pool, upload_id)
+        .await?
+        .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
+    let rel = media
+        .display_path
+        .ok_or_else(|| AppError::NotFound("Anzeige nicht verfügbar.".into()))?;
+    let absolute = state.config.media_path.join(&rel);
+    stream_media_file(
+        &headers,
         &absolute,
         "image/jpeg".to_string(),
         "inline",
@@ -751,6 +925,7 @@ pub async fn get_preview(
 /// [`get_preview`].
 pub async fn get_thumbnail(
     State(state): State<AppState>,
+    headers: axum::http::HeaderMap,
     Path(upload_id): Path<Uuid>,
 ) -> Result<axum::response::Response, AppError> {
     let media = Upload::find_visible_media(&state.pool, upload_id)
@@ -761,6 +936,7 @@ pub async fn get_thumbnail(
         .ok_or_else(|| AppError::NotFound("Thumbnail nicht verfügbar.".into()))?;
     let absolute = state.config.media_path.join(&rel);
     stream_media_file(
+        &headers,
         &absolute,
         "image/jpeg".to_string(),
         "inline",
@@ -771,7 +947,108 @@ pub async fn get_thumbnail(
 
 #[cfg(test)]
 mod tests {
-    use super::quota_limit_bytes;
+    use super::{RangeSpec, parse_range, quota_limit_bytes};
+
+    // `Range` handling exists because iOS Safari probes every `<video>` with
+    // `Range: bytes=0-1` and abandons the load without a 206. These pin the forms a
+    // media element actually sends, plus the edges that decide 206 vs 200 vs 416.
+    #[test]
+    fn no_range_header_is_a_full_response() {
+        assert_eq!(parse_range(None, 100), RangeSpec::Full);
+    }
+
+    #[test]
+    fn open_ended_range_runs_to_eof() {
+        assert_eq!(
+            parse_range(Some("bytes=10-"), 100),
+            RangeSpec::Partial { start: 10, end: 99 }
+        );
+    }
+
+    #[test]
+    fn closed_range_is_inclusive_on_both_ends() {
+        // The iOS probe. Two bytes, 0 and 1 — an exclusive end would return one.
+        assert_eq!(
+            parse_range(Some("bytes=0-1"), 100),
+            RangeSpec::Partial { start: 0, end: 1 }
+        );
+    }
+
+    #[test]
+    fn suffix_range_returns_the_last_n_bytes() {
+        assert_eq!(
+            parse_range(Some("bytes=-20"), 100),
+            RangeSpec::Partial { start: 80, end: 99 }
+        );
+    }
+
+    #[test]
+    fn suffix_longer_than_the_file_clamps_to_the_whole_file() {
+        assert_eq!(
+            parse_range(Some("bytes=-500"), 100),
+            RangeSpec::Partial { start: 0, end: 99 }
+        );
+    }
+
+    #[test]
+    fn end_past_eof_is_clamped_not_rejected() {
+        // RFC 9110 §14.1.1 — players routinely ask for more than is there.
+        assert_eq!(
+            parse_range(Some("bytes=90-999"), 100),
+            RangeSpec::Partial { start: 90, end: 99 }
+        );
+    }
+
+    #[test]
+    fn start_past_eof_is_416_not_a_full_body() {
+        // Answering 200 here makes a player re-request forever.
+        assert_eq!(
+            parse_range(Some("bytes=100-"), 100),
+            RangeSpec::Unsatisfiable
+        );
+        assert_eq!(
+            parse_range(Some("bytes=200-300"), 100),
+            RangeSpec::Unsatisfiable
+        );
+    }
+
+    #[test]
+    fn inverted_range_is_unsatisfiable() {
+        assert_eq!(
+            parse_range(Some("bytes=50-10"), 100),
+            RangeSpec::Unsatisfiable
+        );
+    }
+
+    #[test]
+    fn unsupported_or_malformed_forms_fall_back_to_the_full_body() {
+        // Ignoring a Range we can't process and sending 200 is explicitly allowed, and
+        // safer than guessing. Multi-range would need multipart/byteranges, which no
+        // <video> asks for.
+        for header in [
+            "bytes=0-10,20-30", // multi-range
+            "items=0-10",       // non-bytes unit
+            "bytes=abc-def",    // garbage
+            "bytes=",           // empty spec
+            "nonsense",         // no unit at all
+        ] {
+            assert_eq!(parse_range(Some(header), 100), RangeSpec::Full, "{header}");
+        }
+    }
+
+    #[test]
+    fn last_byte_is_reachable() {
+        assert_eq!(
+            parse_range(Some("bytes=99-99"), 100),
+            RangeSpec::Partial { start: 99, end: 99 }
+        );
+    }
+
+    #[test]
+    fn empty_file_satisfies_no_range() {
+        assert_eq!(parse_range(Some("bytes=0-"), 0), RangeSpec::Unsatisfiable);
+        assert_eq!(parse_range(None, 0), RangeSpec::Full);
+    }
 
     #[test]
     fn divides_free_space_by_uploaders_with_tolerance() {

backend/src/main.rs

@@ -2,7 +2,6 @@ use anyhow::Result;
 use axum::Router;
 use axum::extract::DefaultBodyLimit;
 use axum::routing::{delete, get, patch, post};
-use tower_http::services::ServeDir;
 use tower_http::trace::TraceLayer;
 use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};
 
@@ -45,6 +44,13 @@ async fn main() -> Result<()> {
 
     let state = AppState::new(pool.clone(), config.clone());
 
+    // Regenerate image derivatives an older pipeline produced: the big-screen display for
+    // uploads processed before it existed (v0.17.x), and anything predating the current
+    // DERIVATIVES_REV (rev 1 applies the EXIF orientation, without which every portrait
+    // phone photo is stored sideways). Fire-and-forget behind the compression semaphore;
+    // originals are never touched, so a failure just retries on the next start.
+    state.compression.backfill_stale_derivatives().await;
+
     // Re-spawn exports for events that were released but whose keepsake never finished
     // (crash mid-export). Needs the media/export paths + SSE sender, so it runs here
     // rather than inside `startup_recovery`. Fire-and-forget: the workers run in the
@@ -53,6 +59,7 @@ async fn main() -> Result<()> {
         pool.clone(),
         config.media_path.clone(),
         config.export_path.clone(),
+        config.comments_enabled,
         state.sse_tx.clone(),
     )
     .await;
@@ -63,6 +70,7 @@ async fn main() -> Result<()> {
         pool,
         state.rate_limiter.clone(),
         state.sse_tickets.clone(),
+        config.media_path.clone(),
     );
 
     // Ensure media directories exist
@@ -106,6 +114,10 @@ async fn main() -> Result<()> {
             "/api/v1/upload/{id}/preview",
             get(handlers::upload::get_preview),
         )
+        .route(
+            "/api/v1/upload/{id}/display",
+            get(handlers::upload::get_display),
+        )
         .route(
             "/api/v1/upload/{id}/thumbnail",
             get(handlers::upload::get_thumbnail),
@@ -219,41 +231,39 @@ async fn main() -> Result<()> {
         api
     };
 
-    // Serve media files from disk
-    let media_service = ServeDir::new(&config.media_path);
-
+    // NOTE: media is deliberately NOT served over HTTP.
+    //
+    // Files live under `media_path` so the compression worker and the export job can read
+    // them off disk, but nothing may pull them straight from `/media/**` — that bypasses
+    // the visibility checks (soft-delete + ban-hide) that make a host takedown stick.
+    // Every legitimate fetch goes through `/api/v1/upload/{id}/{original,preview,display,
+    // thumbnail}`, which filter via `find_visible_media`; those are the only media URLs the
+    // backend ever emits (see `handlers::feed`).
+    //
+    // This used to be a `ServeDir` on `/media` with four `nest_service` blockers on the
+    // subtrees above it. That was bypassable: axum routes on the RAW path while `ServeDir`
+    // percent-decodes afterwards, so `/media/%70reviews/{id}.jpg` missed every blocker,
+    // fell through to the `ServeDir`, and was decoded back to `previews/` on disk — serving
+    // a taken-down photo to anyone, unauthenticated. Any single escaped byte worked, in all
+    // four subtrees. Deleting the route removes the vector outright rather than racing the
+    // decoder; `/media/**` now 404s regardless of encoding.
     let router = Router::new()
         .route("/health", get(|| async { "ok" }))
         .merge(api)
-        // Block direct HTTP access to ALL media subtrees. The files live under
-        // `media_path` (so the compression worker and export can read them off disk) but
-        // must NOT be pullable straight from `/media/**` — that bypasses the visibility
-        // checks (soft-delete + ban-hide) in the gated handlers. Every legitimate fetch
-        // goes through `/api/v1/upload/{id}/{original,preview,thumbnail}`, which filter
-        // via `find_visible_media`. The more specific nests take precedence over the
-        // `/media` ServeDir below (which, with all three subtrees blocked, now serves
-        // nothing — kept as a backstop).
-        .nest_service(
-            "/media/originals",
-            get(|| async { axum::http::StatusCode::NOT_FOUND }),
-        )
-        .nest_service(
-            "/media/previews",
-            get(|| async { axum::http::StatusCode::NOT_FOUND }),
-        )
-        .nest_service(
-            "/media/thumbnails",
-            get(|| async { axum::http::StatusCode::NOT_FOUND }),
-        )
-        .nest_service("/media", media_service)
         .layer(TraceLayer::new_for_http())
         .with_state(state);
 
     let listener = tokio::net::TcpListener::bind(("0.0.0.0", config.app_port)).await?;
     tracing::info!("listening on {}", listener.local_addr()?);
-    axum::serve(listener, router)
-        .with_graceful_shutdown(shutdown_signal())
-        .await?;
+    // `into_make_service_with_connect_info` is required by the pre-auth handlers, which
+    // extract `ConnectInfo<SocketAddr>` to use the peer address as the rate-limit key when
+    // X-Forwarded-For is absent. Without it those extractors fail at runtime.
+    axum::serve(
+        listener,
+        router.into_make_service_with_connect_info::<std::net::SocketAddr>(),
+    )
+    .with_graceful_shutdown(shutdown_signal())
+    .await?;
 
     Ok(())
 }

backend/src/models/upload.rs

@@ -46,6 +46,7 @@ pub struct VisibleMedia {
     pub original_path: String,
     pub preview_path: Option<String>,
     pub thumbnail_path: Option<String>,
+    pub display_path: Option<String>,
     pub mime_type: String,
 }
 
@@ -93,7 +94,7 @@ impl Upload {
         id: Uuid,
     ) -> Result<Option<VisibleMedia>, sqlx::Error> {
         sqlx::query_as::<_, VisibleMedia>(
-            "SELECT up.original_path, up.preview_path, up.thumbnail_path, up.mime_type
+            "SELECT up.original_path, up.preview_path, up.thumbnail_path, up.display_path, up.mime_type
              FROM upload up
              JOIN \"user\" u ON u.id = up.user_id
              WHERE up.id = $1 AND up.deleted_at IS NULL
@@ -134,6 +135,30 @@ impl Upload {
         Ok(())
     }
 
+    pub async fn set_display_path(
+        pool: &PgPool,
+        id: Uuid,
+        display_path: &str,
+    ) -> Result<(), sqlx::Error> {
+        sqlx::query("UPDATE upload SET display_path = $2 WHERE id = $1")
+            .bind(id)
+            .bind(display_path)
+            .execute(pool)
+            .await?;
+        Ok(())
+    }
+
+    /// Stamp which revision of the derivative pipeline produced this row's preview/display,
+    /// so the startup backfill can find rows generated by an older one exactly once.
+    pub async fn set_derivatives_rev(pool: &PgPool, id: Uuid, rev: i16) -> Result<(), sqlx::Error> {
+        sqlx::query("UPDATE upload SET derivatives_rev = $2 WHERE id = $1")
+            .bind(id)
+            .bind(rev)
+            .execute(pool)
+            .await?;
+        Ok(())
+    }
+
     pub async fn set_thumbnail_path(
         pool: &PgPool,
         id: Uuid,

backend/src/services/compression.rs

@@ -48,6 +48,16 @@ impl CompressionWorker {
         self.generation.fetch_add(1, Ordering::SeqCst);
     }
 
+    /// How many times `do_process` is attempted before an upload is given up on. The
+    /// give-up path is user-visible (the photo disappears), so transient infrastructure
+    /// errors must not reach it.
+    const MAX_PROCESS_ATTEMPTS: u32 = 3;
+
+    /// Revision of the image-derivative pipeline. Bump this whenever a change makes existing
+    /// previews/displays wrong, so `backfill_stale_derivatives` regenerates them once on the
+    /// next start. Rev 1 = EXIF orientation is applied.
+    const DERIVATIVES_REV: i16 = 1;
+
     /// Spawn a background task to process an uploaded file.
     pub fn process(&self, upload_id: Uuid, original_path: String, mime_type: String) {
         let worker = self.clone();
@@ -60,10 +70,42 @@ impl CompressionWorker {
             if worker.generation.load(Ordering::SeqCst) != born_at {
                 return;
             }
-            match worker
-                .do_process(upload_id, &original_path, &mime_type)
-                .await
-            {
+            // Retry before giving up. Most failures here are transient and self-clearing —
+            // an ENOSPC spike while several guests upload at once, a momentary DB-pool
+            // exhaustion, a panic inside the image codec — and the give-up path is
+            // user-visible data loss, so it is worth a few seconds to avoid entering it.
+            //
+            // But only for failures that CAN clear. An image that exceeds the decode budget,
+            // is corrupt, or is in an unsupported format fails identically on every attempt,
+            // so retrying it just burns 2s + 4s of backoff and writes three near-identical
+            // warnings before reaching the same conclusion. Give up on those immediately.
+            let mut attempt = 1u32;
+            let outcome = loop {
+                match worker
+                    .do_process(upload_id, &original_path, &mime_type)
+                    .await
+                {
+                    Ok(v) => break Ok(v),
+                    Err(e)
+                        if attempt < Self::MAX_PROCESS_ATTEMPTS
+                            && !crate::services::imaging::is_permanent_image_error(&e) =>
+                    {
+                        tracing::warn!(
+                            error = ?e, %upload_id, attempt,
+                            "compression attempt failed; retrying"
+                        );
+                        tokio::time::sleep(std::time::Duration::from_secs(2u64.pow(attempt))).await;
+                        attempt += 1;
+                        // The data may have been reset while we slept (e2e TRUNCATE).
+                        if worker.generation.load(Ordering::SeqCst) != born_at {
+                            return;
+                        }
+                    }
+                    Err(e) => break Err(e),
+                }
+            };
+
+            match outcome {
                 Ok(_) => {
                     tracing::info!("compression completed for upload {upload_id}");
                     let _ = worker.sse_tx.send(SseEvent {
@@ -72,21 +114,31 @@ impl CompressionWorker {
                     });
                 }
                 Err(e) => {
-                    tracing::error!("compression failed for upload {upload_id}: {e:#}");
-                    // Auto-cleanup: a failed transcode would otherwise leave a
-                    // permanently broken feed card, silently charge the uploader's
-                    // quota, and orphan the original on disk. Refund + soft-delete
-                    // (one tx, so v_feed excludes it), remove the orphan file, then
-                    // tell the uploader (upload-error toast) and evict the card
-                    // everywhere (upload-deleted, already handled by the feed).
+                    tracing::error!(
+                        "compression failed for upload {upload_id} after {attempt} attempt(s): {e:#}"
+                    );
+                    // Refund + soft-delete (one tx, so v_feed excludes it) so a failed
+                    // transcode doesn't leave a permanently broken feed card or silently
+                    // charge the uploader's quota. Then tell the uploader (upload-error
+                    // toast) and evict the card everywhere (upload-deleted).
+                    //
+                    // The ORIGINAL IS DELIBERATELY KEPT. This path used to `remove_file` it
+                    // unconditionally, which meant any transient error — a disk-full blip
+                    // while saving a derivative, a pool hiccup, a panic in the image codec —
+                    // irreversibly destroyed the guest's only copy of a photo they can never
+                    // retake. The row is only soft-deleted, so keeping the bytes makes the
+                    // upload fully recoverable; the file is orphaned rather than lost, and
+                    // the path is logged so it can be found. `backfill_stale_derivatives`
+                    // already refuses to destroy data on error for exactly this reason.
                     let _ = Upload::set_compression_status(&worker.pool, upload_id, "failed").await;
                     if let Err(del) = Upload::soft_delete(&worker.pool, upload_id).await {
                         tracing::warn!(error = ?del, %upload_id, "failed to soft-delete after compression failure");
                     }
-                    let orphan = worker.media_path.join(&original_path);
-                    if let Err(rm) = tokio::fs::remove_file(&orphan).await {
-                        tracing::warn!(error = ?rm, path = %orphan.display(), "failed to remove orphaned original");
-                    }
+                    tracing::warn!(
+                        %upload_id,
+                        path = %worker.media_path.join(&original_path).display(),
+                        "original retained for recovery after compression failure"
+                    );
                     let _ = worker.sse_tx.send(SseEvent {
                         event_type: "upload-error".to_string(),
                         data: serde_json::json!({ "upload_id": upload_id, "error": e.to_string() })
@@ -112,11 +164,13 @@ impl CompressionWorker {
         let original = self.media_path.join(original_path);
 
         if mime_type.starts_with("image/") {
-            let preview_rel = self
-                .generate_image_preview(upload_id, &original, mime_type)
+            let (preview_rel, display_rel) = self
+                .generate_image_derivatives(upload_id, &original, mime_type)
                 .await?;
             Upload::set_preview_path(&self.pool, upload_id, &preview_rel).await?;
-            tracing::info!("preview generated for upload {upload_id}");
+            Upload::set_display_path(&self.pool, upload_id, &display_rel).await?;
+            Upload::set_derivatives_rev(&self.pool, upload_id, Self::DERIVATIVES_REV).await?;
+            tracing::info!("preview + display generated for upload {upload_id}");
         } else if mime_type.starts_with("video/") {
             let thumb_rel = self.generate_video_thumbnail(upload_id, &original).await?;
             Upload::set_thumbnail_path(&self.pool, upload_id, &thumb_rel).await?;
@@ -127,44 +181,63 @@ impl CompressionWorker {
         Ok(())
     }
 
-    async fn generate_image_preview(
+    /// Longest edge of the big-screen "display" derivative used by the diashow. Sized to be
+    /// sharp on 1080p/4K while staying bounded (a ~2048px JPEG decodes to ~16 MB — trivial
+    /// for any kiosk, unlike a raw multi-thousand-pixel original).
+    const DISPLAY_MAX_EDGE: u32 = 2048;
+    /// Longest edge of the phone-feed "preview" (data-saver default).
+    const PREVIEW_MAX_EDGE: u32 = 800;
+
+    /// Decode the image ONCE and emit both derivatives — the 800px `preview` (phone feed)
+    /// and the 2048px `display` (diashow). Returns `(preview_rel, display_rel)`.
+    async fn generate_image_derivatives(
         &self,
         upload_id: Uuid,
         original: &Path,
         mime_type: &str,
-    ) -> Result<String> {
+    ) -> Result<(String, String)> {
         let previews_dir = self.media_path.join("previews");
+        let displays_dir = self.media_path.join("displays");
         tokio::fs::create_dir_all(&previews_dir).await?;
+        tokio::fs::create_dir_all(&displays_dir).await?;
 
-        let preview_filename = format!("{upload_id}.jpg");
-        let preview_path = previews_dir.join(&preview_filename);
+        let filename = format!("{upload_id}.jpg");
+        let preview_path = previews_dir.join(&filename);
+        let display_path = displays_dir.join(&filename);
         let original = original.to_path_buf();
-        let preview_path_clone = preview_path.clone();
         let mime_owned = mime_type.to_string();
+        let preview_max = Self::PREVIEW_MAX_EDGE;
+        let display_max = Self::DISPLAY_MAX_EDGE;
 
         // Run blocking image operations in a spawn_blocking task
         tokio::task::spawn_blocking(move || -> Result<()> {
-            // Reject decompression bombs *before* fully decoding: the upload body
-            // cap bounds the file size on disk, but a small file can still decode to
-            // enormous dimensions (e.g. a ~1 MB image expanding to 50k×50k px →
-            // gigabytes), OOM-ing the box during decode/resize. 12000×12000 covers
-            // any real phone photo; max_alloc hard-caps the decode allocation.
-            let mut reader = image::ImageReader::open(&original)
-                .context("failed to open image")?
-                .with_guessed_format()
-                .context("failed to read image header")?;
-            let mut limits = image::Limits::default();
-            limits.max_image_width = Some(12_000);
-            limits.max_image_height = Some(12_000);
-            limits.max_alloc = Some(256 * 1024 * 1024);
-            reader.limits(limits);
-            let img = reader.decode().context("failed to decode image")?;
+            // Decompression-bomb limits + EXIF orientation, both in one place — see
+            // services::imaging for why neither may be skipped.
+            let img = crate::services::imaging::decode_oriented(&original)?;
 
-            // Resize to max 800px wide, preserving aspect ratio
-            let preview = img.resize(800, 800, image::imageops::FilterType::Lanczos3);
-            preview
-                .save_with_format(&preview_path_clone, image::ImageFormat::Jpeg)
-                .context("failed to save preview")?;
+            // Preview: max 800px, preserving aspect ratio (data-saver feed).
+            img.resize(
+                preview_max,
+                preview_max,
+                image::imageops::FilterType::Lanczos3,
+            )
+            .save_with_format(&preview_path, image::ImageFormat::Jpeg)
+            .context("failed to save preview")?;
+
+            // Display: max 2048px for the diashow. Only DOWNSCALE — never upscale a smaller
+            // original (that adds bytes with no quality gain); re-encode it as JPEG as-is.
+            let display = if img.width() > display_max || img.height() > display_max {
+                img.resize(
+                    display_max,
+                    display_max,
+                    image::imageops::FilterType::Lanczos3,
+                )
+            } else {
+                img
+            };
+            display
+                .save_with_format(&display_path, image::ImageFormat::Jpeg)
+                .context("failed to save display")?;
 
             // If the original is PNG, try lossless compression in-place
             if mime_owned == "image/png" {
@@ -183,7 +256,73 @@ impl CompressionWorker {
         })
         .await??;
 
-        Ok(format!("previews/{preview_filename}"))
+        Ok((
+            format!("previews/{filename}"),
+            format!("displays/{filename}"),
+        ))
+    }
+
+    /// Regenerate image derivatives that an older pipeline produced. Fire-and-forget from
+    /// startup; picks up two cases, both of which leave the ORIGINAL untouched:
+    ///
+    /// - uploads processed before the `display` derivative existed (preview but no
+    ///   `display_path`), and
+    /// - uploads whose derivatives predate `DERIVATIVES_REV` — currently rev 1, which applies
+    ///   the EXIF orientation. Everything generated before it is stored sideways for any
+    ///   portrait phone photo.
+    ///
+    /// Unlike the failure path in `process`, a backfill error is logged and skipped — it must
+    /// NEVER destroy or soft-delete an upload that already has a working preview.
+    pub async fn backfill_stale_derivatives(&self) {
+        let rows = sqlx::query_as::<_, (Uuid, String, String)>(
+            "SELECT id, original_path, mime_type FROM upload
+             WHERE deleted_at IS NULL AND mime_type LIKE 'image/%'
+               AND original_path IS NOT NULL
+               AND (
+                     (display_path IS NULL AND preview_path IS NOT NULL)
+                  OR derivatives_rev < $1
+               )",
+        )
+        .bind(Self::DERIVATIVES_REV)
+        .fetch_all(&self.pool)
+        .await;
+        let rows = match rows {
+            Ok(r) => r,
+            Err(e) => {
+                tracing::warn!(error = ?e, "derivative backfill query failed");
+                return;
+            }
+        };
+        if rows.is_empty() {
+            return;
+        }
+        tracing::info!("regenerating derivatives for {} upload(s)", rows.len());
+        for (id, original_path, mime_type) in rows {
+            let worker = self.clone();
+            tokio::spawn(async move {
+                let _permit = worker.semaphore.acquire().await;
+                let original = worker.media_path.join(&original_path);
+                match worker
+                    .generate_image_derivatives(id, &original, &mime_type)
+                    .await
+                {
+                    Ok((preview_rel, display_rel)) => {
+                        let _ = Upload::set_preview_path(&worker.pool, id, &preview_rel).await;
+                        let _ = Upload::set_display_path(&worker.pool, id, &display_rel).await;
+                        let _ =
+                            Upload::set_derivatives_rev(&worker.pool, id, Self::DERIVATIVES_REV)
+                                .await;
+                        tracing::info!("derivatives regenerated for upload {id}");
+                    }
+                    Err(e) => {
+                        // Leave the existing derivatives and the original intact; this row is
+                        // simply retried on the next start. The rev stays behind, which is the
+                        // marker that it still needs doing.
+                        tracing::warn!(error = ?e, %id, "derivative backfill failed; leaving as-is");
+                    }
+                }
+            });
+        }
     }
 
     async fn generate_video_thumbnail(&self, upload_id: Uuid, original: &Path) -> Result<String> {

backend/src/services/disk.rs

@@ -76,6 +76,17 @@ impl Default for DiskCache {
     }
 }
 
+/// UNCACHED free-space reading for the filesystem backing `path`.
+///
+/// Deliberately bypasses [`DiskCache`]. The cache exists for the quota poll, where a 15s-stale
+/// number is fine because it is only ever advisory. The export preflight is the opposite case: it
+/// decides whether to start writing a multi-GB archive, and the sibling export worker running
+/// concurrently can move free space by tens of gigabytes well inside the TTL. A stale reading there
+/// would authorise exactly the write that fills the disk.
+pub fn free_bytes(path: &Path) -> Option<u64> {
+    read_disk_for_path(path).map(|d| d.free)
+}
+
 /// Resolve the filesystem backing `media_path` and read its total/free bytes.
 ///
 /// Snapshots the mount table via `sysinfo`, then delegates the selection to the pure

backend/src/services/export.rs

@@ -20,6 +20,29 @@ use crate::state::SseEvent;
 
 static VIEWER_DIR: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/static/export-viewer");
 
+// ── Shared visibility filter ─────────────────────────────────────────────────
+
+/// The predicate that decides what lands in a keepsake, as ONE definition.
+///
+/// Two queries have to agree on it: [`query_uploads`], which selects the rows the archives are
+/// built from, and [`estimate_export_bytes`], which sizes them for the disk preflight. They used
+/// to state it separately, and the direction of drift matters — an estimate that misses rows the
+/// archive writes UNDER-reserves, which is the exact ENOSPC the preflight exists to prevent.
+///
+/// A `SRC:`-marked copy in the integration tests cannot catch that: drift means production moved
+/// and the copy didn't, so both sides of such a test sit still and it keeps passing. Sharing the
+/// fragment removes the failure by construction instead, and leaves the test doing what it is
+/// actually good at — pinning the behaviour.
+///
+/// CONTRACT: callers must alias `upload` as `u` and join `"user"` as `usr`, and bind the event id
+/// as `$1`.
+macro_rules! export_visibility_where {
+    () => {
+        "WHERE u.event_id = $1 AND u.deleted_at IS NULL
+           AND usr.uploads_hidden = FALSE AND usr.is_banned = FALSE"
+    };
+}
+
 // ── DB query rows ────────────────────────────────────────────────────────────
 
 #[derive(sqlx::FromRow)]
@@ -53,6 +76,9 @@ struct ViewerData {
 struct ViewerEvent {
     name: String,
     exported_at: String,
+    // Mirrors the live COMMENTS_ENABLED flag so the offline keepsake hides all comment
+    // UI (buttons, counts, sections) when the feature was off for the event.
+    comments_enabled: bool,
 }
 
 #[derive(Serialize)]
@@ -238,6 +264,7 @@ pub async fn recover_exports(
     pool: PgPool,
     media_path: PathBuf,
     export_path: PathBuf,
+    comments_enabled: bool,
     sse_tx: broadcast::Sender<SseEvent>,
 ) {
     let rows = match sqlx::query_as::<_, (Uuid, String, i64)>(
@@ -297,6 +324,7 @@ pub async fn recover_exports(
             event_id,
             event_name,
             epoch,
+            comments_enabled,
             Duration::ZERO,
             pool.clone(),
             media_path.clone(),
@@ -403,6 +431,7 @@ pub fn spawn_export_jobs(
     event_id: Uuid,
     event_name: String,
     epoch: i64,
+    comments_enabled: bool,
     delay: Duration,
     pool: PgPool,
     media_path: PathBuf,
@@ -439,6 +468,7 @@ pub fn spawn_export_jobs(
             event_id,
             epoch,
             &event_name2,
+            comments_enabled,
             &pool2,
             &media_path2,
             &export_path2,
@@ -469,6 +499,15 @@ async fn run_zip_export(
         return Ok(());
     }
 
+    // Reclaim BEFORE measuring: the superseded archive is already unreachable, and the space it
+    // holds is very often exactly the space this rebuild needs.
+    prune_superseded_archives(pool, export_path, "Gallery", event_id, epoch).await;
+    // AFTER the claim, not before. A preflight that bailed before claiming would leave the row
+    // `pending` with no worker and no error — the spinner-forever state `mark_failed`'s status
+    // guard was widened to prevent. Failing here goes through the caller's `mark_failed`, so the
+    // host gets the reason.
+    ensure_export_space(pool, event_id, export_path).await?;
+
     // On error, mark THIS generation failed — a no-op if we've since been superseded (the
     // caller in `spawn_export_jobs` does it, epoch-guarded). Temp artifacts are cleaned up
     // here so a failing export can't leak them (which is what fills the disk in the first place).
@@ -541,7 +580,7 @@ async fn run_zip_export_inner(
             };
             let entry_name = format!("{folder}/{date}_{name_safe}_{}.{ext}", row.id);
 
-            let builder = ZipEntryBuilder::new(entry_name.into(), Compression::Stored);
+            let builder = keepsake_entry(entry_name, Compression::Stored);
 
             // Open BEFORE writing the entry header. A missing source is skipped (the media file
             // was deleted, or its processing failed) — but it must be skipped without aborting the
@@ -635,10 +674,12 @@ impl MediaSource {
     }
 }
 
+#[allow(clippy::too_many_arguments)]
 async fn run_html_export(
     event_id: Uuid,
     epoch: i64,
     event_name: &str,
+    comments_enabled: bool,
     pool: &PgPool,
     media_path: &Path,
     export_path: &Path,
@@ -649,10 +690,16 @@ async fn run_html_export(
         return Ok(());
     }
 
+    // See run_zip_export: reclaim the superseded generation first, then refuse at the door rather
+    // than ENOSPC mid-write.
+    prune_superseded_archives(pool, export_path, "Memories", event_id, epoch).await;
+    ensure_export_space(pool, event_id, export_path).await?;
+
     let res = run_html_export_inner(
         epoch,
         event_id,
         event_name,
+        comments_enabled,
         pool,
         media_path,
         export_path,
@@ -672,10 +719,12 @@ async fn run_html_export(
     abandon_if_superseded("HTML", event_id, epoch, res)
 }
 
+#[allow(clippy::too_many_arguments)]
 async fn run_html_export_inner(
     epoch: i64,
     event_id: Uuid,
     event_name: &str,
+    comments_enabled: bool,
     pool: &PgPool,
     media_path: &Path,
     export_path: &Path,
@@ -708,10 +757,11 @@ async fn run_html_export_inner(
         let src = media_path.join(&row.original_path);
         // Stat ONCE, up front, and skip this upload if the source is gone. The old code probed with
         // `exists()` here and then did `metadata(&src).await?` further down — a TOCTOU whose `?`
-        // aborted the ENTIRE keepsake if the file vanished in between. It genuinely can: the
-        // compression worker hard-deletes an original when its transcode fails, and it can still be
-        // running when the gallery is released. A missing source must degrade one entry, never the
-        // whole archive (which, once released, the host cannot rebuild without reopening uploads).
+        // aborted the ENTIRE keepsake if the file vanished in between. It can still happen: the
+        // compression worker no longer deletes originals on failure, but the hourly sweep reclaims
+        // them once past the retention window, and an owner or host delete can land mid-export. A
+        // missing source must degrade one entry, never the whole archive (which, once released, the
+        // host cannot rebuild without reopening uploads).
         let src_meta = match tokio::fs::metadata(&src).await {
             Ok(m) => m,
             Err(e) => {
@@ -778,7 +828,12 @@ async fn run_html_export_inner(
             let thumb_path_clone = thumb_path.clone();
 
             let thumb_result = tokio::task::spawn_blocking(move || -> Result<()> {
-                let img = image::open(&src_clone).context("failed to open image for thumbnail")?;
+                // `decode_oriented`, not `image::open`: the latter ignores the EXIF
+                // orientation tag AND applies no decode limits. Using it here is why every
+                // portrait photo came out sideways in the keepsake's HTML viewer grid — the
+                // re-encode below drops the tag, so the viewer cannot recover it.
+                let img = crate::services::imaging::decode_oriented(&src_clone)
+                    .context("failed to open image for thumbnail")?;
                 let resized = img.resize(400, 400, image::imageops::FilterType::Lanczos3);
                 resized
                     .save_with_format(&thumb_path_clone, image::ImageFormat::Jpeg)
@@ -799,8 +854,12 @@ async fn run_html_export_inner(
                 let full_path_clone = full_path.clone();
 
                 let compress_result = tokio::task::spawn_blocking(move || -> Result<()> {
-                    let img =
-                        image::open(&src_clone).context("failed to open image for compression")?;
+                    // Same reason as the thumbnail above. This branch only runs for originals
+                    // over 5 MB, which is why the viewer's full image looked correct for small
+                    // photos and sideways for large ones — an inconsistency that reads as a
+                    // viewer bug rather than an export one.
+                    let img = crate::services::imaging::decode_oriented(&src_clone)
+                        .context("failed to open image for compression")?;
                     let resized = img.resize(2000, 2000, image::imageops::FilterType::Lanczos3);
                     resized
                         .save_with_format(&full_path_clone, image::ImageFormat::Jpeg)
@@ -882,12 +941,17 @@ async fn run_html_export_inner(
         event: ViewerEvent {
             name: event_name.to_string(),
             exported_at: Utc::now().to_rfc3339(),
+            comments_enabled,
         },
         posts: viewer_posts,
     };
     let data_json =
         serde_json::to_string_pretty(&viewer_data).context("failed to serialize data.json")?;
 
+    // Match the live app's colour theme in the offline keepsake.
+    let (theme_primary, theme_accent) = resolve_theme_seeds(pool).await;
+    let theme_css = theme_override_css(&theme_primary, &theme_accent);
+
     let _ = update_progress(pool, event_id, "html", epoch, 72).await;
 
     // 5. Create ZIP (per-generation paths — see run_zip_export)
@@ -899,14 +963,17 @@ async fn run_html_export_inner(
         let file = tokio::fs::File::create(&tmp_path).await?;
         let mut zip = ZipFileWriter::with_tokio(file);
 
-        // Write embedded viewer assets (index.html, _app/*, etc.)
-        write_dir_to_zip(&VIEWER_DIR, &mut zip).await?;
+        // Write the embedded single-file viewer, injecting the export data as a
+        // `window.__EXPORT_DATA__` global into index.html. Guests double-click
+        // index.html (file://), where a cross-origin fetch() of a sibling file is
+        // blocked — so the data must be inlined rather than fetched from data.json.
+        write_viewer_with_data(&VIEWER_DIR, &mut zip, &data_json, theme_css.as_deref()).await?;
 
         let _ = update_progress(pool, event_id, "html", epoch, 75).await;
 
         // Write data.json
         {
-            let builder = ZipEntryBuilder::new("data.json".into(), Compression::Deflate);
+            let builder = keepsake_entry("data.json".into(), Compression::Deflate);
             let mut entry = zip.write_entry_stream(builder).await?;
             let mut cursor = AllowStdIo::new(std::io::Cursor::new(data_json.as_bytes()));
             fcopy(&mut cursor, &mut entry).await?;
@@ -915,7 +982,7 @@ async fn run_html_export_inner(
 
         // Write README.txt
         {
-            let builder = ZipEntryBuilder::new("README.txt".into(), Compression::Deflate);
+            let builder = keepsake_entry("README.txt".into(), Compression::Deflate);
             let mut entry = zip.write_entry_stream(builder).await?;
             let mut cursor = AllowStdIo::new(std::io::Cursor::new(README_TEXT.as_bytes()));
             fcopy(&mut cursor, &mut entry).await?;
@@ -933,9 +1000,9 @@ async fn run_html_export_inner(
 
         for (name, source) in &media_manifest {
             let path = source.path();
-            // Open-first: a source that disappeared between the manifest being built and now (the
-            // compression worker deletes originals on transcode failure) must skip this entry, not
-            // fail the whole viewer. Opening collapses the check and the use into one operation.
+            // Open-first: a source that disappeared between the manifest being built and now (a
+            // delete, or the hourly sweep reclaiming a long-failed original) must skip this entry,
+            // not fail the whole viewer. Opening collapses the check and the use into one operation.
             let src_file = match tokio::fs::File::open(path).await {
                 Ok(f) => f,
                 Err(e) => {
@@ -948,7 +1015,7 @@ async fn run_html_export_inner(
             };
 
             let entry_name = format!("media/{name}");
-            let builder = ZipEntryBuilder::new(entry_name.into(), Compression::Stored);
+            let builder = keepsake_entry(entry_name, Compression::Stored);
             let mut zip_entry = zip.write_entry_stream(builder).await?;
             let mut f = src_file.compat();
             fcopy(&mut f, &mut zip_entry).await?;
@@ -1007,7 +1074,7 @@ async fn run_html_export_inner(
 // ── DB helpers ───────────────────────────────────────────────────────────────
 
 async fn query_uploads(pool: &PgPool, event_id: Uuid) -> Result<Vec<ExportUploadRow>> {
-    Ok(sqlx::query_as::<_, ExportUploadRow>(
+    Ok(sqlx::query_as::<_, ExportUploadRow>(concat!(
         "SELECT u.id, u.original_path, u.mime_type, u.caption,
                 usr.display_name AS uploader_name,
                 COUNT(DISTINCT l.user_id) AS like_count,
@@ -1015,11 +1082,12 @@ async fn query_uploads(pool: &PgPool, event_id: Uuid) -> Result<Vec<ExportUpload
          FROM upload u
          JOIN \"user\" usr ON usr.id = u.user_id
          LEFT JOIN \"like\" l ON l.upload_id = u.id
-         WHERE u.event_id = $1 AND u.deleted_at IS NULL
-           AND usr.uploads_hidden = FALSE AND usr.is_banned = FALSE
+         ",
+        export_visibility_where!(),
+        "
          GROUP BY u.id, usr.display_name
          ORDER BY u.created_at ASC",
-    )
+    ))
     .bind(event_id)
     .fetch_all(pool)
     .await?)
@@ -1131,6 +1199,197 @@ fn parse_gen_seq(name: &str, prefix: &str, suffix: &str) -> Option<i64> {
         .ok()
 }
 
+/// Filenames a live (current-epoch, `done`) job row still points at — OFF LIMITS to every prune,
+/// regardless of the epoch encoded in the name.
+///
+/// A ViewerOnly regeneration carries the finished ZIP forward by re-stamping its row to the new
+/// epoch WITHOUT renaming the file, so `Gallery.<event>.<older>.zip` is still the served archive and
+/// deleting it by filename-epoch would 404 the download.
+async fn protected_files(pool: &PgPool, event_id: Uuid) -> Vec<String> {
+    sqlx::query_scalar::<_, String>(
+        "SELECT split_part(j.file_path, '/', -1) FROM export_job j
+          JOIN event e ON e.id = j.event_id
+         WHERE j.event_id = $1 AND j.epoch = e.export_epoch
+           AND j.status = 'done' AND j.file_path IS NOT NULL",
+    )
+    .bind(event_id)
+    .fetch_all(pool)
+    .await
+    .unwrap_or_default()
+}
+
+/// Reclaim superseded FINAL archives BEFORE this generation starts writing its own.
+///
+/// Peak disk usage used to be two full generations, because the only prune ran after the new archive
+/// was written, renamed and finalised. That ordering reads as durability ("don't delete the good
+/// keepsake before the replacement is safe") but it buys nothing: readiness is derived from
+/// `job.epoch = event.export_epoch AND status = 'done'`, so the moment `invalidate_and_arm` bumps
+/// the epoch the old archive is ALREADY unreachable — `GET /export/zip` 404s whether the file is on
+/// disk or not. Keeping it only reserves gigabytes for a download nobody can perform, and for
+/// `Affects::Both` (a takedown) it is content someone has explicitly asked to have removed. So a
+/// rebuild reclaims first and peaks at one generation.
+///
+/// Narrower than [`prune_stale_export_files`] on purpose: FINAL archives only. Those are inert — a
+/// superseded worker either already renamed its file (and will delete it itself when its guarded
+/// `finalize_job` fails) or never will. `.tmp` files and `viewer_tmp_` staging dirs are NOT touched
+/// here: a superseded worker can still be streaming into those, and at build START it is far more
+/// likely to be alive than at finalize time.
+async fn prune_superseded_archives(
+    pool: &PgPool,
+    exports_dir: &Path,
+    prefix: &str,
+    event_id: Uuid,
+    keep_seq: i64,
+) {
+    let protected = protected_files(pool, event_id).await;
+    let final_prefix = format!("{prefix}.{event_id}.");
+    let mut rd = match tokio::fs::read_dir(exports_dir).await {
+        Ok(rd) => rd,
+        Err(_) => return,
+    };
+    let mut reclaimed = 0u64;
+    while let Ok(Some(entry)) = rd.next_entry().await {
+        let name = entry.file_name();
+        let name = name.to_string_lossy();
+        if !is_superseded_archive(&name, &final_prefix, keep_seq, &protected) {
+            continue;
+        }
+        let len = entry.metadata().await.map(|m| m.len()).unwrap_or(0);
+        if tokio::fs::remove_file(entry.path()).await.is_ok() {
+            reclaimed += len;
+        }
+    }
+    if reclaimed > 0 {
+        tracing::info!(
+            "reclaimed {reclaimed} bytes of superseded {prefix} archives before rebuilding \
+             event {event_id} @ epoch {keep_seq}"
+        );
+    }
+}
+
+/// Is `name` a FINAL archive of a strictly-older generation that no live row points at?
+///
+/// Pure so the two dangerous cases can be pinned without a filesystem: the carried-forward archive
+/// (protected despite an older epoch in its name) and the in-flight `.tmp` (never matched at all).
+fn is_superseded_archive(
+    name: &str,
+    final_prefix: &str,
+    keep_seq: i64,
+    protected: &[String],
+) -> bool {
+    if protected.iter().any(|p| p == name) {
+        return false;
+    }
+    parse_gen_seq(name, final_prefix, ".zip").is_some_and(|n| n < keep_seq)
+}
+
+/// Bytes the media in this event's keepsake will occupy, as an UPPER BOUND per archive.
+///
+/// Both archives write their media entries `Compression::Stored`, so an archive is essentially a
+/// byte-for-byte second copy of the originals: `Gallery.zip` always, and `Memories.zip` for every
+/// video ([`MediaSource::Original`]) and every image at or under 5 MB. Images over 5 MB are
+/// downscaled to 2000px first, which only makes this estimate more conservative — the direction we
+/// want, since being wrong low means ENOSPC halfway through.
+///
+/// Shares [`query_uploads`]' visibility filter via [`export_visibility_where`], so hidden/banned
+/// uploads can't be counted here but skipped there (or the reverse, which under-reserves).
+pub async fn estimate_export_bytes(pool: &PgPool, event_id: Uuid) -> Result<u64> {
+    let (bytes,): (i64,) = sqlx::query_as(concat!(
+        "SELECT COALESCE(SUM(u.original_size_bytes), 0)::bigint
+           FROM upload u
+           JOIN \"user\" usr ON usr.id = u.user_id
+           ",
+        export_visibility_where!(),
+    ))
+    .bind(event_id)
+    .fetch_one(pool)
+    .await
+    .context("estimating the export size")?;
+    Ok(bytes.max(0) as u64)
+}
+
+/// Headroom multiplier over the raw media sum: ZIP central directory, per-entry headers, the
+/// embedded viewer, and the HTML export's temp staging.
+const EXPORT_SIZE_OVERHEAD_PCT: u64 = 110;
+
+/// Bytes this export must have available, given the raw media sum and how many jobs are competing.
+///
+/// `armed` is the multiplier that keeps two concurrent workers honest. `spawn_export_jobs` starts
+/// the ZIP and the HTML halves at the same instant and both are gallery-sized, so a worker that
+/// reserved only for itself would see "it fits", its sibling would independently see the same, and
+/// together they would not fit — which is precisely the ENOSPC this preflight exists to prevent.
+/// Computed in `u128` and clamped, NOT with `saturating_mul`: saturating first and then dividing by
+/// 100 quietly turns an overflow into a number ~100x too small, which is the one direction that
+/// matters here — an under-estimate authorises the very write the preflight exists to refuse.
+fn required_free_bytes(media_bytes: u64, armed: i64) -> u64 {
+    let needed = media_bytes as u128 * EXPORT_SIZE_OVERHEAD_PCT as u128 / 100
+        * armed.max(1).min(i64::from(u32::MAX)) as u128;
+    needed.min(u64::MAX as u128) as u64
+}
+
+/// Free bytes a full keepsake build would need RIGHT NOW, both halves included.
+///
+/// The same arithmetic the preflight uses, exposed so the host dashboard can warn BEFORE the
+/// release rather than reporting a failure after it. The preflight can only ever say "this didn't
+/// fit"; at that point the gallery is full, the event is over, and the remedies (ask guests to stop
+/// uploading, grow the volume) are all much harder. Hard-codes both halves because that is what a
+/// release arms.
+pub async fn keepsake_space_required(pool: &PgPool, event_id: Uuid) -> Result<u64> {
+    Ok(required_free_bytes(
+        estimate_export_bytes(pool, event_id).await?,
+        2,
+    ))
+}
+
+/// Refuse to start an export that cannot fit, with a reason the host can act on.
+///
+/// Without this the failure mode is ENOSPC halfway through a multi-GB write, and the wreckage
+/// outlives it: the epoch has already moved, so the job row is `failed` at the CURRENT generation
+/// and `GET /export/zip` 404s, while the last good archive sits on disk unreferenced. The host's
+/// only escape (`POST /host/export/rebuild`) needs the very space that isn't there. Failing at the
+/// door instead leaves the disk untouched and puts a number in front of the operator.
+///
+/// Both halves are spawned concurrently and both are gallery-sized, so a worker must reserve for
+/// its live sibling too — otherwise each independently sees "it fits", and together they don't.
+async fn ensure_export_space(pool: &PgPool, event_id: Uuid, export_path: &Path) -> Result<()> {
+    let media_bytes = estimate_export_bytes(pool, event_id).await?;
+
+    // Every job armed at any epoch for this event that hasn't finished is competing for this disk.
+    let (armed,): (i64,) = sqlx::query_as(
+        "SELECT COUNT(*) FROM export_job
+          WHERE event_id = $1 AND status IN ('pending', 'running')",
+    )
+    .bind(event_id)
+    .fetch_one(pool)
+    .await
+    .context("counting armed export jobs")?;
+    let needed = required_free_bytes(media_bytes, armed);
+
+    // `None` = the mount couldn't be resolved. Fail OPEN, exactly as the upload quota does: refusing
+    // to build the keepsake because we can't read a number would be a worse failure than trying.
+    let Some(free) = crate::services::disk::free_bytes(export_path) else {
+        tracing::warn!("export preflight: disk snapshot unavailable; proceeding without the check");
+        return Ok(());
+    };
+
+    if free < needed {
+        let gb = |b: u64| b as f64 / 1_000_000_000.0;
+        tracing::error!(
+            needed,
+            free,
+            armed,
+            "export preflight: not enough free space to build the keepsake for event {event_id}"
+        );
+        anyhow::bail!(
+            "Nicht genug Speicherplatz für das Keepsake: benötigt ca. {:.1} GB, frei sind {:.1} GB. \
+             Bitte Speicher freigeben und das Keepsake anschließend neu erstellen.",
+            gb(needed),
+            gb(free)
+        );
+    }
+    Ok(())
+}
+
 /// Best-effort removal of stale per-generation export artifacts for one export type. Deletes
 /// ONLY strictly-older generations (`n < keep_seq`) — never `keep_seq`'s own current file,
 /// and never a NEWER generation that a concurrent re-release may already be producing (that
@@ -1147,20 +1406,7 @@ async fn prune_stale_export_files(
     event_id: Uuid,
     keep_seq: i64,
 ) {
-    // Files still referenced by a live (current-epoch) job row are OFF LIMITS regardless of the
-    // epoch in their name. A ViewerOnly regeneration carries the finished ZIP forward by re-stamping
-    // its row to the new epoch WITHOUT renaming the file — so `Gallery.<event>.<older>.zip` is still
-    // the served archive, and deleting it by filename-epoch would 404 the download.
-    let protected: Vec<String> = sqlx::query_scalar::<_, String>(
-        "SELECT split_part(j.file_path, '/', -1) FROM export_job j
-          JOIN event e ON e.id = j.event_id
-         WHERE j.event_id = $1 AND j.epoch = e.export_epoch
-           AND j.status = 'done' AND j.file_path IS NOT NULL",
-    )
-    .bind(event_id)
-    .fetch_all(pool)
-    .await
-    .unwrap_or_default();
+    let protected = protected_files(pool, event_id).await;
 
     // EVERY shape is event-scoped. All events share one exports volume, so a name keyed only by
     // generation would let event A's prune delete event B's live keepsake (and let two events
@@ -1301,26 +1547,199 @@ async fn maybe_broadcast_complete(
     }
 }
 
-/// Recursively write all files from an embedded `include_dir::Dir` into a ZIP.
-async fn write_dir_to_zip(
+/// Write the embedded viewer into the ZIP, injecting the export data as a
+/// `window.__EXPORT_DATA__` global into `index.html`. The keepsake is opened by
+/// double-clicking `index.html` (file://), where browsers block a cross-origin
+/// `fetch()` of a sibling `data.json` — so the data is inlined into the page.
+/// (`data.json` is still written separately for the http-served case.)
+/// Permissions stamped on every entry in both archives: `rw-r--r--`.
+///
+/// `ZipEntryBuilder::new` leaves the external file attribute at zero, and the host compatibility
+/// defaults to Unix — so every entry was written with a stored mode of **0000**. Windows Explorer
+/// ignores Unix modes and was fine, which is exactly why this survived: on Linux and macOS
+/// `unzip` faithfully applies what the archive asks for, and the guest gets a directory of files
+/// none of which they can open. `?---------` on every line of `unzip -Z`.
+///
+/// That is the keepsake — the artifact the whole event exists to produce — arriving unreadable,
+/// after distribution, with no server-side symptom at all.
+/// `S_IFREG | 0644`. The type bits are included because the mode is written whole into the high
+/// half of the external file attribute: without them extractors see a file of type "unknown"
+/// (`unzip -Z` renders `?rw-r--r--`), which works but is not what the archive means to say.
+const KEEPSAKE_ENTRY_MODE: u16 = 0o100_644;
+
+/// Build a ZIP entry for the keepsake. ALL entries in both archives go through here so the mode
+/// can't be forgotten at one of the six call sites.
+fn keepsake_entry(name: String, compression: Compression) -> ZipEntryBuilder {
+    ZipEntryBuilder::new(name.into(), compression).unix_permissions(KEEPSAKE_ENTRY_MODE)
+}
+
+/// Escape a JSON payload for inlining inside a `<script>` element.
+///
+/// See the call site in [`write_viewer_with_data`] for why this is every `<` and not just `</`.
+/// Kept separate so the property that matters — no `<` survives, and the value still decodes to
+/// the original — can be asserted without building a ZIP.
+fn escape_json_for_script(data_json: &str) -> String {
+    data_json.replace('<', "\\u003c")
+}
+
+async fn write_viewer_with_data(
     dir: &include_dir::Dir<'_>,
     zip: &mut ZipFileWriter<tokio::fs::File>,
+    data_json: &str,
+    theme_css: Option<&str>,
 ) -> Result<()> {
     for file in dir.files() {
         let path = file.path().to_string_lossy().to_string();
-        let contents = file.contents();
-        let builder = ZipEntryBuilder::new(path.into(), Compression::Deflate);
-        let mut entry = zip.write_entry_stream(builder).await?;
-        let mut cursor = AllowStdIo::new(std::io::Cursor::new(contents));
-        fcopy(&mut cursor, &mut entry).await?;
-        entry.close().await?;
+        if path == "index.html" {
+            let html = std::str::from_utf8(file.contents())
+                .context("export-viewer index.html is not valid UTF-8")?;
+            // Escape EVERY `<`, not just `</`.
+            //
+            // `</` -> `<\/` stops the obvious break-out (`</script><img onerror=…>`) and is inert
+            // against XSS. It does not stop the caption steering the HTML TOKENIZER. A caption
+            // containing `<!--<script` with no later `-->` puts the parser into
+            // script-data-double-escaped state; from there the template's own `</script>` only
+            // steps back to script-data-escaped instead of closing the element, and the rest of the
+            // document — including the viewer bundle — is swallowed as script data. Nothing
+            // executes and nothing leaks; `window.__EXPORT_DATA__` is simply never assigned and the
+            // keepsake opens blank.
+            //
+            // That failure is silent and POST-DISTRIBUTION: the export succeeds, the ZIP is
+            // well-formed, the job writes `done`, /export/status is green, and the host hands out a
+            // file that only fails when a guest double-clicks index.html — in every copy, with no
+            // way to fix it after the fact. Reachable from any guest-authored caption or comment,
+            // since both are embedded in the viewer.
+            //
+            // `<` never appears in JSON structural syntax — only inside string values — so a global
+            // replace is sound, and `<` is valid in both JSON and a JS string literal. One
+            // rule covers `</script`, `<!--` and `<script` together, which is the point: the
+            // previous escape was named for the single case it did handle.
+            //
+            // NOTE this is deliberately only for the INLINED copy. `data.json` is written
+            // separately, in no HTML context, and must stay literal.
+            let safe = escape_json_for_script(data_json);
+            // Match the live app's colour theme: inject the same `:root:root{…}` override
+            // the app builds at runtime so a rose/sage/custom event exports a rose/sage
+            // keepsake (not the embedded default gold). The CSS is generated purely from
+            // hex seeds (theme_override_css), so there's nothing to escape.
+            let mut head_inject = String::new();
+            if let Some(css) = theme_css {
+                head_inject.push_str(&format!("<style id=\"es-theme\">{css}</style>"));
+            }
+            head_inject.push_str(&format!("<script>window.__EXPORT_DATA__={safe};</script>"));
+            let injected = match html.find("</head>") {
+                Some(idx) => format!("{}{}{}", &html[..idx], head_inject, &html[idx..]),
+                None => format!("{head_inject}{html}"),
+            };
+            let builder = keepsake_entry(path, Compression::Deflate);
+            let mut entry = zip.write_entry_stream(builder).await?;
+            let mut cursor = AllowStdIo::new(std::io::Cursor::new(injected.as_bytes()));
+            fcopy(&mut cursor, &mut entry).await?;
+            entry.close().await?;
+        } else {
+            let builder = keepsake_entry(path, Compression::Deflate);
+            let mut entry = zip.write_entry_stream(builder).await?;
+            let mut cursor = AllowStdIo::new(std::io::Cursor::new(file.contents()));
+            fcopy(&mut cursor, &mut entry).await?;
+            entry.close().await?;
+        }
     }
     for sub_dir in dir.dirs() {
-        Box::pin(write_dir_to_zip(sub_dir, zip)).await?;
+        Box::pin(write_viewer_with_data(sub_dir, zip, data_json, theme_css)).await?;
     }
     Ok(())
 }
 
+/// Default champagne-gold seed — matches the hand-tuned ramp already embedded in the
+/// viewer, so a default-themed event injects no override.
+const KEEPSAKE_DEFAULT_SEED: &str = "#8a6a2b";
+
+// stop → color-mix instruction. MIRRORS `LADDER` in frontend/src/lib/theme/palette.ts —
+// keep the two in sync so an exported keepsake matches the live app pixel-for-pixel.
+const THEME_LADDER: &[(u16, Option<&str>)] = &[
+    (50, Some("white 90%")),
+    (100, Some("white 80%")),
+    (200, Some("white 62%")),
+    (300, Some("white 42%")),
+    (400, Some("white 22%")),
+    (500, Some("white 9%")),
+    (600, None),
+    (700, Some("black 15%")),
+    (800, Some("black 30%")),
+    (900, Some("black 45%")),
+    (950, Some("black 63%")),
+];
+
+fn theme_stop_value(seed: &str, mix: Option<&str>) -> String {
+    match mix {
+        Some(m) => format!("color-mix(in oklab, {seed}, {m})"),
+        None => seed.to_string(),
+    }
+}
+
+fn theme_ramp(families: &[&str], seed: &str) -> String {
+    let mut out = String::new();
+    for (stop, mix) in THEME_LADDER {
+        let val = theme_stop_value(seed, *mix);
+        for fam in families {
+            out.push_str(&format!("--color-{fam}-{stop}:{val};"));
+        }
+    }
+    out
+}
+
+fn is_hex_color(s: &str) -> bool {
+    let b = s.as_bytes();
+    b.len() == 7 && b[0] == b'#' && b[1..].iter().all(|c| c.is_ascii_hexdigit())
+}
+
+/// Build the keepsake's `:root:root{…}` colour override from two seed colours, or None
+/// for the default gold (viewer already carries that ramp) or an invalid seed (fall back
+/// to the embedded default rather than emit unsafe CSS). MIRRORS `buildPaletteCss` in
+/// frontend/src/lib/theme/palette.ts.
+fn theme_override_css(primary: &str, accent: &str) -> Option<String> {
+    if !is_hex_color(primary) || !is_hex_color(accent) {
+        return None;
+    }
+    if primary.eq_ignore_ascii_case(KEEPSAKE_DEFAULT_SEED)
+        && accent.eq_ignore_ascii_case(KEEPSAKE_DEFAULT_SEED)
+    {
+        return None;
+    }
+    let accent500 = theme_stop_value(accent, Some("white 9%"));
+    let mut css = String::from(":root:root{");
+    css.push_str(&theme_ramp(&["blue", "primary"], primary));
+    css.push_str(&theme_ramp(&["purple"], accent));
+    css.push_str(&format!(
+        "--color-violet-500:{accent500};--color-violet-600:{accent};"
+    ));
+    css.push_str(&format!(
+        "--color-accent-500:{accent500};--color-accent-600:{accent};"
+    ));
+    css.push('}');
+    Some(css)
+}
+
+/// Read the active theme seeds from the runtime `config` table (set by the admin UI),
+/// falling back to the default gold. NOTE: an env-only default (THEME_PRIMARY set but
+/// never saved via the admin UI) isn't stored in this table, so such a keepsake would
+/// use gold; admin-set themes — the normal path — match the app exactly.
+async fn resolve_theme_seeds(pool: &PgPool) -> (String, String) {
+    async fn read(pool: &PgPool, key: &str) -> String {
+        sqlx::query_scalar::<_, String>("SELECT value FROM config WHERE key = $1")
+            .bind(key)
+            .fetch_optional(pool)
+            .await
+            .ok()
+            .flatten()
+            .unwrap_or_else(|| KEEPSAKE_DEFAULT_SEED.to_string())
+    }
+    (
+        read(pool, "theme_primary").await,
+        read(pool, "theme_accent").await,
+    )
+}
+
 fn ext_from_path(path: &str) -> &str {
     path.rsplit('.').next().unwrap_or("bin")
 }
@@ -1354,3 +1773,187 @@ So geht's:\n\
    Alles ist lokal auf deinem Gerät gespeichert.\n\
 \n\
 Viel Freude mit den Erinnerungen!\n";
+
+// ── Tests ────────────────────────────────────────────────────────────────────
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    const EVT: &str = "11111111-1111-1111-1111-111111111111";
+
+    fn gallery_prefix() -> String {
+        format!("Gallery.{EVT}.")
+    }
+
+    #[test]
+    fn a_strictly_older_archive_is_reclaimed() {
+        // The whole point: at the start of a rebuild at epoch 5, generation 4's archive is dead
+        // weight — readiness is derived from `epoch = event.export_epoch`, so it is already
+        // unreachable — and its bytes are very often exactly the bytes the rebuild needs.
+        assert!(is_superseded_archive(
+            &format!("Gallery.{EVT}.4.zip"),
+            &gallery_prefix(),
+            5,
+            &[]
+        ));
+    }
+
+    #[test]
+    fn our_own_and_newer_generations_are_never_touched() {
+        // `keep_seq` is OUR generation; a NEWER one belongs to a re-release that has already
+        // superseded us, and deleting it would let a lagging worker nuke a live keepsake.
+        for seq in [5, 6] {
+            assert!(
+                !is_superseded_archive(
+                    &format!("Gallery.{EVT}.{seq}.zip"),
+                    &gallery_prefix(),
+                    5,
+                    &[]
+                ),
+                "generation {seq} must survive a prune keeping 5"
+            );
+        }
+    }
+
+    #[test]
+    fn a_carried_forward_archive_survives_despite_an_older_epoch_in_its_name() {
+        // THE dangerous case. A ViewerOnly regeneration (a moderated comment) re-stamps the
+        // finished ZIP's row to the new epoch WITHOUT renaming the file, so the SERVED archive
+        // legitimately carries an older generation number. Pruning it by filename-epoch would 404
+        // the photo download to change nothing in it. The protected set is what stops that, and
+        // moving the prune to build-start makes this case reachable far more often.
+        let carried = format!("Gallery.{EVT}.4.zip");
+        assert!(!is_superseded_archive(
+            &carried,
+            &gallery_prefix(),
+            5,
+            std::slice::from_ref(&carried)
+        ));
+    }
+
+    #[test]
+    fn temps_and_staging_dirs_are_out_of_scope_for_the_early_prune() {
+        // A superseded worker may still be streaming into these, and at build START it is much
+        // more likely to be alive than at finalize time. Only inert FINAL archives are reclaimed
+        // here; `prune_stale_export_files` still handles the rest after we win.
+        for name in [
+            format!("Gallery.{EVT}.4.tmp"),
+            format!("viewer_tmp_{EVT}_4"),
+            format!("Memories.{EVT}.4.zip"),
+        ] {
+            assert!(
+                !is_superseded_archive(&name, &gallery_prefix(), 5, &[]),
+                "{name} must not be reclaimed by the pre-build prune"
+            );
+        }
+    }
+
+    #[test]
+    fn another_events_archive_is_never_reclaimed() {
+        // All events share one exports volume, so the prefix carries the event id.
+        let other = "22222222-2222-2222-2222-222222222222";
+        assert!(!is_superseded_archive(
+            &format!("Gallery.{other}.4.zip"),
+            &gallery_prefix(),
+            5,
+            &[]
+        ));
+    }
+
+    #[test]
+    fn unrelated_files_are_left_alone() {
+        for name in ["Gallery.zip", "notes.txt", "Gallery..4.zip"] {
+            assert!(!is_superseded_archive(name, &gallery_prefix(), 5, &[]));
+        }
+    }
+
+    /// Every `<` is escaped, whatever it is part of.
+    ///
+    /// PREVENTS the regression to `</` -> `<\\/`, which is named for the one case it handles.
+    /// `<!--<script` with no later `-->` drives the HTML tokenizer into
+    /// script-data-double-escaped state, where the template's own `</script>` no longer closes
+    /// the element — the viewer bundle is swallowed as script data, `__EXPORT_DATA__` is never
+    /// assigned, and the keepsake opens blank in every copy the host has already handed out.
+    #[test]
+    fn no_left_angle_bracket_survives_inlining() {
+        for payload in [
+            r#"{"caption":"<!--<script"}"#,
+            r#"{"caption":"</script><img src=x onerror=alert(1)>"}"#,
+            r#"{"caption":"<!--"}"#,
+            r#"{"caption":"<script>"}"#,
+            r#"{"caption":"a < b"}"#,
+        ] {
+            let escaped = escape_json_for_script(payload);
+            assert!(
+                !escaped.contains('<'),
+                "a surviving `<` can still steer the tokenizer: {escaped}"
+            );
+        }
+    }
+
+    /// The escape must not change what the viewer READS — it is a transport encoding, not a
+    /// sanitiser. A caption is guest-authored text that has to render back exactly.
+    #[test]
+    fn the_payload_still_decodes_to_the_original_value() {
+        // `<` appears only inside JSON string values, never in structural syntax, so a global
+        // replace is sound — this is the assertion that says so.
+        for caption in [
+            "<!--<script",
+            "</script><img src=x onerror=alert(1)>",
+            "a < b und c > d",
+            "ganz normale Bildunterschrift",
+            "Herz <3",
+        ] {
+            let json = serde_json::json!({ "posts": [{ "caption": caption }] }).to_string();
+            let escaped = escape_json_for_script(&json);
+            let back: serde_json::Value =
+                serde_json::from_str(&escaped).expect("the escaped form must still be valid JSON");
+            assert_eq!(
+                back["posts"][0]["caption"].as_str(),
+                Some(caption),
+                "the caption must survive the round trip unchanged"
+            );
+        }
+    }
+
+    /// Nothing else in the document is touched.
+    #[test]
+    fn a_payload_with_no_angle_brackets_is_unchanged() {
+        let json = r#"{"posts":[{"caption":"schönes Foto"}]}"#;
+        assert_eq!(escape_json_for_script(json), json);
+    }
+
+    #[test]
+    fn a_lone_armed_job_reserves_for_one_archive() {
+        // A ViewerOnly regeneration re-arms only the HTML half — reserving for two would refuse
+        // a rebuild that fits perfectly well.
+        assert_eq!(required_free_bytes(1_000, 1), 1_100);
+    }
+
+    #[test]
+    fn two_concurrent_halves_reserve_for_both() {
+        // The bug this exists to prevent: each worker independently sees "it fits", and together
+        // they don't. Both halves are gallery-sized, so the reservation must be for the pair.
+        assert_eq!(required_free_bytes(1_000, 2), 2_200);
+    }
+
+    #[test]
+    fn a_zero_count_still_reserves_for_one() {
+        // Defensive: a racing status transition must never yield a zero requirement, which would
+        // wave through an export of any size onto a full disk.
+        assert_eq!(required_free_bytes(1_000, 0), 1_100);
+    }
+
+    #[test]
+    fn an_empty_gallery_needs_nothing() {
+        assert_eq!(required_free_bytes(0, 2), 0);
+    }
+
+    #[test]
+    fn a_pathological_size_saturates_instead_of_wrapping() {
+        // u64 overflow would wrap to a TINY requirement and authorise the exact write we're
+        // guarding against — the failure mode must be "refuse", never "wrap and allow".
+        assert_eq!(required_free_bytes(u64::MAX, 2), u64::MAX);
+    }
+}

backend/src/services/imaging.rs

@@ -0,0 +1,263 @@
+//! Shared image decoding.
+//!
+//! Exists so there is exactly ONE way to turn a file on disk into a `DynamicImage` in this
+//! codebase. Two properties have to hold everywhere an image is decoded, and both were
+//! previously re-derived per call site — which is how they drifted apart:
+//!
+//! - **EXIF orientation must be applied.** Phones do not rotate sensor data; they record how
+//!   the camera was held in a tag and store the pixels as shot. `image::open` and
+//!   `ImageReader::decode` both hand back the raw pixels and ignore that tag, and re-encoding
+//!   to JPEG writes no EXIF, so the derivative is permanently sideways while the untouched
+//!   original still renders upright. The compression worker was fixed; the export worker was
+//!   not, so every portrait photo came out sideways in the keepsake's HTML viewer.
+//! - **Decode limits must be set.** The upload body cap bounds the file on disk, but a small
+//!   file can decode to enormous dimensions (a ~1 MB image expanding to 50k×50k px), OOM-ing
+//!   the box. `image::open` applies NO limits at all, so the export path was also decoding
+//!   arbitrary user-supplied images unbounded.
+
+use anyhow::{Context, Result};
+use image::{DynamicImage, ImageDecoder};
+use std::path::Path;
+
+/// Bounds for any decode of user-supplied image data. The per-axis cap covers any real phone
+/// photo; `max_alloc` bounds the decoded buffer — but only because `decode_oriented` reserves
+/// against it explicitly, see there.
+///
+/// Sized against the deployment: the app container is capped at 1 GiB and the compression
+/// worker runs `compression_concurrency` decodes at once (default 2), so 256 MiB per decode
+/// leaves headroom for the resize buffers and the runtime.
+fn decode_limits() -> image::Limits {
+    let mut limits = image::Limits::default();
+    limits.max_image_width = Some(12_000);
+    limits.max_image_height = Some(12_000);
+    limits.max_alloc = Some(256 * 1024 * 1024);
+    limits
+}
+
+/// True when re-running the exact same work on the exact same bytes cannot possibly
+/// succeed, so retrying only burns wall-clock and log noise.
+///
+/// Deliberately narrow. Only the `ImageError` variants that are a property of the *input*
+/// count: the file will not shrink, gain codec support, or un-corrupt itself between
+/// attempts. `IoError` is excluded on purpose — an ENOSPC while writing a derivative, or
+/// EMFILE under load, is exactly the transient case the retry exists for.
+pub fn is_permanent_image_error(err: &anyhow::Error) -> bool {
+    err.chain().any(|cause| {
+        matches!(
+            cause.downcast_ref::<image::ImageError>(),
+            Some(
+                image::ImageError::Limits(_)
+                    | image::ImageError::Unsupported(_)
+                    | image::ImageError::Decoding(_)
+            )
+        )
+    })
+}
+
+/// Build a decoder for `path` with the budget enforced, WITHOUT reading any pixels.
+///
+/// Single source of truth for "may this image be decoded at all": both the upload
+/// admission check and the compression worker go through here, so they cannot disagree
+/// about what is acceptable.
+fn decoder_within_budget(path: &Path) -> Result<impl image::ImageDecoder> {
+    let mut reader = image::ImageReader::open(path)
+        .context("failed to open image")?
+        .with_guessed_format()
+        .context("failed to read image header")?;
+    let mut limits = decode_limits();
+    reader.limits(limits.clone());
+
+    // We need `into_decoder` rather than `decode()` to read the EXIF orientation tag before
+    // the pixels are consumed. But the two are NOT equivalent on safety: `decode()` performs
+    //
+    //     limits.reserve(decoder.total_bytes())?;
+    //
+    // between building the decoder and reading the image, and `into_decoder()` skips it (the
+    // crate's own FIXME concedes `from_decoder` doesn't compensate). Nothing else enforces
+    // `max_alloc` — the JPEG decoder's `set_limits` only checks support and dimensions — so
+    // without the line below the budget is inert and the ONLY bound is the per-axis cap. That
+    // leaves 12000x12000 decodable at 412 MiB, and two concurrent at 824 MiB against a 1 GiB
+    // container. Re-add it, exactly as `decode()` does.
+    let mut decoder = reader.into_decoder().context("failed to decode image")?;
+    limits
+        .reserve(decoder.total_bytes())
+        .context("image too large to decode within the memory budget")?;
+    decoder
+        .set_limits(limits)
+        .context("image too large to decode within the memory budget")?;
+    Ok(decoder)
+}
+
+/// Megapixels an image would decode to, or `None` if its header can't be read. Used only
+/// to put a concrete number in the message the guest sees.
+pub fn megapixels(path: &Path) -> Option<f64> {
+    let reader = image::ImageReader::open(path)
+        .ok()?
+        .with_guessed_format()
+        .ok()?;
+    let (w, h) = reader.into_dimensions().ok()?;
+    Some(f64::from(w) * f64::from(h) / 1_000_000.0)
+}
+
+/// True when an image cannot be decoded specifically because it would exceed the memory
+/// budget — read from the header, no pixels touched.
+///
+/// Called at upload admission so a guest who sends a 100 MP photo is told at the door, with
+/// a reason they can act on, instead of the upload being accepted with a 201 and then
+/// silently soft-deleted minutes later when the worker gives up on it.
+///
+/// Deliberately narrow: ONLY the budget. A corrupt, truncated or unsupported file also
+/// fails to build a decoder, but rejecting those here would change a contract the
+/// adversarial suite pins on purpose — acceptance follows the magic bytes, and a payload
+/// with a valid JPEG header is accepted regardless of what follows it. Those go to the
+/// compression worker as before, which handles them gracefully and (since the retry
+/// classifier) no longer burns backoff on them.
+pub fn exceeds_decode_budget(path: &Path) -> bool {
+    match decoder_within_budget(path) {
+        Ok(_) => false,
+        Err(e) => e.chain().any(|cause| {
+            matches!(
+                cause.downcast_ref::<image::ImageError>(),
+                Some(image::ImageError::Limits(_))
+            )
+        }),
+    }
+}
+
+/// Decode an image from disk with decompression-bomb limits applied and its EXIF
+/// orientation baked into the pixels.
+///
+/// Blocking — call inside `spawn_blocking`.
+pub fn decode_oriented(path: &Path) -> Result<DynamicImage> {
+    let mut decoder = decoder_within_budget(path)?;
+
+    // Cheap, and it happens BEFORE any pixels are read: an oversized image costs a header
+    // parse, not an allocation.
+    let orientation = decoder
+        .orientation()
+        .unwrap_or(image::metadata::Orientation::NoTransforms);
+    let mut img = DynamicImage::from_decoder(decoder).context("failed to decode image")?;
+    img.apply_orientation(orientation);
+    Ok(img)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    /// Shared with the e2e suite rather than duplicating 568 KiB of binary: the same file
+    /// drives `02-upload/oversized-image` so both layers assert on one artefact.
+    const HUGE: &str = concat!(
+        env!("CARGO_MANIFEST_DIR"),
+        "/../e2e/fixtures/media/huge-99mp.jpg"
+    );
+
+    #[test]
+    fn rejects_an_image_that_would_blow_the_allocation_budget() {
+        // 11000x9000 = 99 MP. Deliberately UNDER the 12000px per-axis cap, so the axis check
+        // cannot reject it — the allocation budget is the only thing that can, which is
+        // exactly what makes this a regression test rather than a restatement of the axis cap.
+        // 283 MiB decoded as RGB8 against a 256 MiB budget, from 568 KiB on disk.
+        //
+        // This failed before the guard was restored: `ImageReader::decode` performs
+        // `limits.reserve(decoder.total_bytes())`, and `into_decoder()` — which we need for
+        // the EXIF tag — skips it, so `max_alloc` was inert and this decoded happily.
+        // Map the Ok arm to its dimensions first: on failure `expect_err` Debug-prints the
+        // value, and Debug on a DynamicImage dumps every pixel — 283 MiB of output.
+        let err = decode_oriented(Path::new(HUGE))
+            .map(|img| (img.width(), img.height()))
+            .expect_err("a 99 MP image must be refused, not allocated");
+        let msg = format!("{err:#}");
+        assert!(
+            msg.to_lowercase().contains("limit") || msg.to_lowercase().contains("memory"),
+            "expected a limits error, got: {msg}"
+        );
+    }
+
+    #[test]
+    fn an_oversized_image_is_a_permanent_failure() {
+        // The retry loop must not burn 2s + 4s of backoff on this: the file will not shrink
+        // between attempts, so all three attempts reach the identical conclusion.
+        let err = decode_oriented(Path::new(HUGE))
+            .map(|img| (img.width(), img.height()))
+            .expect_err("fixture must exceed the budget");
+        assert!(
+            is_permanent_image_error(&err),
+            "a Limits error can never succeed on retry: {err:#}"
+        );
+    }
+
+    #[test]
+    fn a_plain_io_error_is_not_permanent() {
+        // The mirror that keeps the classifier honest. ENOSPC while writing a derivative, or
+        // EMFILE under load, is exactly what the retry exists for — misclassifying those as
+        // permanent would turn a transient blip back into the data loss round 1 fixed.
+        let err = decode_oriented(Path::new("/nonexistent/definitely-not-here.jpg"))
+            .map(|img| (img.width(), img.height()))
+            .expect_err("a missing file must error");
+        assert!(
+            !is_permanent_image_error(&err),
+            "an IO error must stay retryable: {err:#}"
+        );
+    }
+
+    #[test]
+    fn admission_rejects_only_the_over_budget_case() {
+        // Admission and processing must agree about SIZE — a photo accepted at the door and
+        // then rejected by the worker for being too big is the failure this pair prevents.
+        assert!(
+            exceeds_decode_budget(Path::new(HUGE)),
+            "admission must reject what the decoder rejects for size"
+        );
+        let ordinary = concat!(
+            env!("CARGO_MANIFEST_DIR"),
+            "/../e2e/fixtures/media/portrait-exif6.jpg"
+        );
+        assert!(
+            !exceeds_decode_budget(Path::new(ordinary)),
+            "admission must accept an ordinary photo"
+        );
+    }
+
+    #[test]
+    fn admission_does_not_reject_a_merely_undecodable_file() {
+        // The narrowing that keeps the adversarial contract intact: a payload with valid
+        // JPEG magic bytes and nothing behind them cannot be decoded, but acceptance follows
+        // the magic bytes by design (07-adversarial/file-upload-attacks). It is the worker's
+        // job to fail it, not admission's — admission is only the resource guard.
+        let dir = std::env::temp_dir().join("eventsnap-imaging-test");
+        std::fs::create_dir_all(&dir).expect("tmp dir");
+        let stub = dir.join("magic-only.jpg");
+        let mut bytes = vec![0u8; 1024];
+        bytes[..3].copy_from_slice(&[0xFF, 0xD8, 0xFF]);
+        std::fs::write(&stub, &bytes).expect("write stub");
+
+        assert!(
+            !exceeds_decode_budget(&stub),
+            "a corrupt file is not an over-budget file"
+        );
+        assert!(
+            decode_oriented(&stub)
+                .map(|i| (i.width(), i.height()))
+                .is_err(),
+            "...but it must still fail in the worker"
+        );
+        let _ = std::fs::remove_file(&stub);
+    }
+
+    #[test]
+    fn still_decodes_an_ordinary_photo_and_applies_orientation() {
+        // The guard must not have become a blanket refusal. This fixture is 40x20 stored with
+        // EXIF Orientation=6, so a correct decode returns it rotated to 20x40 portrait.
+        let path = concat!(
+            env!("CARGO_MANIFEST_DIR"),
+            "/../e2e/fixtures/media/portrait-exif6.jpg"
+        );
+        let img = decode_oriented(Path::new(path)).expect("an ordinary photo must decode");
+        assert_eq!(
+            (img.width(), img.height()),
+            (20, 40),
+            "EXIF orientation must still be applied after restoring the guard"
+        );
+    }
+}

backend/src/services/maintenance.rs

@@ -9,10 +9,13 @@
 //!    users staring at a spinner. Resetting them on startup recovers gracefully.
 //!
 //! 2. **Periodic tasks** — pruning that should happen "every hour" rather than per
-//!    request: expired sessions (otherwise the table grows unboundedly), and the
+//!    request: expired sessions (otherwise the table grows unboundedly), the
 //!    rate-limiter's in-memory windows (so keys for IPs that left long ago don't
-//!    accumulate).
+//!    accumulate), and the media of soft-deleted uploads — both the ones whose compression
+//!    permanently failed and the ones a guest or host deliberately removed — which are
+//!    retained for a recovery window and then reclaimed.
 
+use std::path::PathBuf;
 use std::time::Duration;
 
 use sqlx::PgPool;
@@ -20,6 +23,42 @@ use sqlx::PgPool;
 use crate::services::rate_limiter::RateLimiter;
 use crate::services::sse_tickets::SseTicketStore;
 
+/// How long a permanently-failed upload's original is kept on disk before it is
+/// reclaimed.
+///
+/// The compression worker stops deleting originals on failure — a transient error must
+/// never destroy the guest's only copy of a photo they can't retake. But the row is
+/// soft-deleted and the uploader's quota IS refunded, so without a sweep those bytes are
+/// invisible, unowned, and free: a reproducible codec failure lets one guest accumulate
+/// orphans at no personal cost, and because `active_uploaders` counts only users with
+/// non-deleted uploads, dropping out of that count actually RAISES everyone's per-user
+/// ceiling while the disk gets fuller.
+///
+/// Two weeks is comfortably longer than any single event, so an operator investigating a
+/// failed upload still has the file, while the leak stays bounded.
+const FAILED_ORIGINAL_RETENTION_DAYS: i64 = 14;
+
+/// How long a DELIBERATELY deleted upload's files are kept before they are reclaimed.
+///
+/// The same leak, reached by the ordinary path rather than the exceptional one.
+/// `soft_delete_in_event` stamps `deleted_at` and refunds `total_upload_bytes`, but nothing ever
+/// removed the bytes — so the quota stopped bounding the disk. Upload 500 MB, delete, quota is back
+/// to zero, upload another 500 MB: not an attack, just a guest curating their camera roll, which is
+/// what people do. The host then sees guests hitting "Du hast dein Upload-Limit erreicht" while the
+/// admin widget shows a disk full of files no upload row points at, and the quota message is
+/// actively misleading because the space really is gone — just not to anyone the accounting can
+/// name.
+///
+/// Much shorter than the failure window on purpose. Fourteen days outlives the whole event, so a
+/// deliberate delete would never reclaim anything while it mattered. A day still gives an operator
+/// a recovery window for a mis-tap.
+///
+/// NOTE what this does NOT do: within the window the bytes are still spent and still unaccounted,
+/// so a guest deleting and re-uploading through an eight-hour event can outrun the sweep. Bounding
+/// that would mean holding the quota until the file is actually reclaimed rather than refunding at
+/// `deleted_at` — a deliberate trade, and the reason the low-disk warning exists.
+const DELETED_UPLOAD_RETENTION_HOURS: i64 = 24;
+
 /// Reset rows left in flight by a previous crashed instance. Run once on startup,
 /// before the HTTP server starts taking requests, so users never observe the
 /// half-state.
@@ -87,7 +126,12 @@ pub async fn startup_recovery(pool: &PgPool) {
 /// - drops expired SSE tickets (30s TTL but the map keeps the slot until pruned)
 ///
 /// Cadence is 1h — fine for both jobs at our scale.
-pub fn spawn_periodic_tasks(pool: PgPool, rate_limiter: RateLimiter, sse_tickets: SseTicketStore) {
+pub fn spawn_periodic_tasks(
+    pool: PgPool,
+    rate_limiter: RateLimiter,
+    sse_tickets: SseTicketStore,
+    media_path: PathBuf,
+) {
     tokio::spawn(async move {
         let mut tick = tokio::time::interval(Duration::from_secs(3600));
         // Fire the first tick immediately, then hourly.
@@ -95,12 +139,117 @@ pub fn spawn_periodic_tasks(pool: PgPool, rate_limiter: RateLimiter, sse_tickets
         loop {
             tick.tick().await;
             cleanup_sessions(&pool).await;
+            cleanup_deleted_media(&pool, &media_path).await;
             rate_limiter.prune();
             sse_tickets.prune();
         }
     });
 }
 
+/// Reclaim the media of soft-deleted uploads once they are past their retention window.
+///
+/// ONLY ever touches rows with `deleted_at IS NOT NULL`, so it can never reach a live upload. Two
+/// classes, two windows, because the two deletes mean different things:
+///
+/// - a compression failure the guest didn't ask for and may want investigated —
+///   [`FAILED_ORIGINAL_RETENTION_DAYS`];
+/// - a deliberate removal by the guest or the host — [`DELETED_UPLOAD_RETENTION_HOURS`].
+///
+/// ALL FOUR paths are reclaimed, not just the original. The previous version cleared
+/// `original_path` alone, which was right for its only case (a failed compression produces no
+/// derivatives) but wrong the moment the sweep reaches a successfully processed upload: preview,
+/// display and thumbnail are each a separate file on disk, none of them counted in
+/// `original_size_bytes`, and nothing else ever removed them.
+///
+/// Every column is cleared in the same pass, which makes the sweep idempotent and stops a later run
+/// re-reporting files that are already gone. The ROW is kept: it is the audit trail, it costs a few
+/// hundred bytes, and `backfill_stale_derivatives` is guarded on `deleted_at IS NULL` so a nulled
+/// `preview_path` can never make it regenerate what was just reclaimed.
+async fn cleanup_deleted_media(pool: &PgPool, media_path: &std::path::Path) {
+    type Row = (
+        uuid::Uuid,
+        String,
+        Option<String>,
+        Option<String>,
+        Option<String>,
+    );
+    let rows = sqlx::query_as::<_, Row>(
+        "SELECT id, original_path, preview_path, display_path, thumbnail_path FROM upload
+         WHERE deleted_at IS NOT NULL
+           AND CASE WHEN compression_status = 'failed'
+                    THEN deleted_at < NOW() - ($1 || ' days')::interval
+                    ELSE deleted_at < NOW() - ($2 || ' hours')::interval
+               END
+           AND (original_path <> '' OR preview_path IS NOT NULL
+                OR display_path IS NOT NULL OR thumbnail_path IS NOT NULL)",
+    )
+    .bind(FAILED_ORIGINAL_RETENTION_DAYS.to_string())
+    .bind(DELETED_UPLOAD_RETENTION_HOURS.to_string())
+    .fetch_all(pool)
+    .await;
+
+    let rows = match rows {
+        Ok(r) => r,
+        Err(e) => {
+            tracing::warn!(error = ?e, "deleted-media sweep query failed");
+            return;
+        }
+    };
+    if rows.is_empty() {
+        return;
+    }
+
+    let mut reclaimed = 0usize;
+    for (id, original, preview, display, thumbnail) in rows {
+        let paths: Vec<String> = std::iter::once(original)
+            .filter(|p| !p.is_empty())
+            .chain([preview, display, thumbnail].into_iter().flatten())
+            .collect();
+
+        // All-or-nothing per row: the columns are only cleared once every file for that upload is
+        // gone. Clearing after a partial success would strand the survivors with nothing pointing
+        // at them — the same unowned-bytes state this sweep exists to drain.
+        let mut all_gone = true;
+        for rel in &paths {
+            let absolute = media_path.join(rel);
+            match tokio::fs::remove_file(&absolute).await {
+                Ok(()) => reclaimed += 1,
+                // Already gone (manual cleanup, restored backup) — still counts as reclaimed for
+                // the purpose of clearing the columns, or the row is re-selected every hour forever.
+                Err(e) if e.kind() == std::io::ErrorKind::NotFound => {}
+                Err(e) => {
+                    tracing::warn!(error = ?e, %id, path = %absolute.display(),
+                        "could not reclaim deleted media; leaving the row for the next sweep");
+                    all_gone = false;
+                }
+            }
+        }
+        if !all_gone {
+            continue;
+        }
+
+        if let Err(e) = sqlx::query(
+            "UPDATE upload SET original_path = '', preview_path = NULL,
+                    display_path = NULL, thumbnail_path = NULL
+             WHERE id = $1",
+        )
+        .bind(id)
+        .execute(pool)
+        .await
+        {
+            tracing::warn!(error = ?e, %id, "reclaimed the files but could not clear the paths");
+        }
+    }
+
+    if reclaimed > 0 {
+        tracing::info!(
+            "reclaimed {reclaimed} file(s) from soft-deleted uploads (deliberate deletes after \
+             {DELETED_UPLOAD_RETENTION_HOURS}h, compression failures after \
+             {FAILED_ORIGINAL_RETENTION_DAYS}d)"
+        );
+    }
+}
+
 async fn cleanup_sessions(pool: &PgPool) {
     match sqlx::query("DELETE FROM session WHERE expires_at < NOW() - INTERVAL '1 day'")
         .execute(pool)

backend/src/services/mod.rs

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

backend/src/services/rate_limiter.rs

@@ -17,13 +17,14 @@ impl RateLimiter {
         }
     }
 
-    /// Returns `true` if the request is allowed, `false` if rate-limited.
-    pub fn check(&self, key: impl Into<String>, max: usize, window: Duration) -> bool {
-        self.check_with_retry(key, max, window).is_ok()
-    }
-
     /// Returns `Ok(())` if allowed, `Err(retry_after_secs)` if rate-limited.
     /// `retry_after_secs` is how long until the oldest slot in the window expires.
+    ///
+    /// This is deliberately the ONLY entry point. There used to be a `check()` wrapper
+    /// returning a plain bool, and 7 of the 8 call sites used it and then hard-coded
+    /// `None` for the response's `Retry-After` — so a throttled client was told to back
+    /// off but never for how long. Forcing every caller through the `Result` makes the
+    /// retry delay impossible to discard by accident.
     pub fn check_with_retry(
         &self,
         key: impl Into<String>,
@@ -84,6 +85,11 @@ impl RateLimiter {
 /// appends is the real client. A client can prepend arbitrary spoofed values to
 /// the left of XFF to dodge throttles — those are ignored here. This assumes
 /// exactly one trusted proxy (Caddy); revisit if that changes.
+///
+/// Pass the peer address as `fallback`, never a constant. Every caller used to pass
+/// the literal `"unknown"`, so any request that arrived without XFF — i.e. anything
+/// reaching the app directly rather than through Caddy — shared ONE bucket with every
+/// other such request, turning the limiter into a self-inflicted global throttle.
 pub fn client_ip(headers: &axum::http::HeaderMap, fallback: &str) -> String {
     headers
         .get("x-forwarded-for")
@@ -104,29 +110,35 @@ mod tests {
     #[test]
     fn allows_up_to_max_then_blocks() {
         let rl = RateLimiter::new();
-        assert!(rl.check("k", 3, MIN));
-        assert!(rl.check("k", 3, MIN));
-        assert!(rl.check("k", 3, MIN));
-        assert!(!rl.check("k", 3, MIN), "the 4th request must be blocked");
+        assert!(rl.check_with_retry("k", 3, MIN).is_ok());
+        assert!(rl.check_with_retry("k", 3, MIN).is_ok());
+        assert!(rl.check_with_retry("k", 3, MIN).is_ok());
+        assert!(
+            rl.check_with_retry("k", 3, MIN).is_err(),
+            "the 4th request must be blocked"
+        );
     }
 
     #[test]
     fn keys_are_independent() {
         let rl = RateLimiter::new();
-        assert!(rl.check("a", 1, MIN));
-        assert!(!rl.check("a", 1, MIN));
-        assert!(rl.check("b", 1, MIN), "a different key has its own window");
+        assert!(rl.check_with_retry("a", 1, MIN).is_ok());
+        assert!(rl.check_with_retry("a", 1, MIN).is_err());
+        assert!(
+            rl.check_with_retry("b", 1, MIN).is_ok(),
+            "a different key has its own window"
+        );
     }
 
     #[test]
     fn window_slides_and_allows_again_after_expiry() {
         let rl = RateLimiter::new();
         let w = Duration::from_millis(40);
-        assert!(rl.check("k", 1, w));
-        assert!(!rl.check("k", 1, w));
+        assert!(rl.check_with_retry("k", 1, w).is_ok());
+        assert!(rl.check_with_retry("k", 1, w).is_err());
         std::thread::sleep(Duration::from_millis(55));
         assert!(
-            rl.check("k", 1, w),
+            rl.check_with_retry("k", 1, w).is_ok(),
             "the slot should expire once the window passes"
         );
     }
@@ -191,10 +203,13 @@ mod tests {
     #[test]
     fn clear_resets_every_window() {
         let rl = RateLimiter::new();
-        assert!(rl.check("k", 1, MIN));
-        assert!(!rl.check("k", 1, MIN));
+        assert!(rl.check_with_retry("k", 1, MIN).is_ok());
+        assert!(rl.check_with_retry("k", 1, MIN).is_err());
         rl.clear();
-        assert!(rl.check("k", 1, MIN), "clear() must free the window");
+        assert!(
+            rl.check_with_retry("k", 1, MIN).is_ok(),
+            "clear() must free the window"
+        );
     }
 
     /// `prune()` is a memory-leak guard: without it a long-lived process keeps one HashMap
@@ -216,7 +231,7 @@ mod tests {
             .insert("stale".to_string(), vec![ancient]);
 
         // ...alongside a key that is still inside its window.
-        assert!(rl.check("live", 5, MIN));
+        assert!(rl.check_with_retry("live", 5, MIN).is_ok());
         assert_eq!(rl.windows.lock().unwrap().len(), 2);
 
         rl.prune();
@@ -239,13 +254,13 @@ mod tests {
         // 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));
+        assert!(rl.check_with_retry("k", 1, MIN).is_ok());
+        assert!(rl.check_with_retry("k", 1, MIN).is_err());
 
         rl.prune();
 
         assert!(
-            !rl.check("k", 1, MIN),
+            rl.check_with_retry("k", 1, MIN).is_err(),
             "prune() must not clear a window that is still active"
         );
     }

backend/static/export-viewer/_app/env.js

@@ -1 +0,0 @@
-export const env={}

backend/static/export-viewer/_app/immutable/chunks/BJ__EZ0W.js

@@ -1 +0,0 @@
-import{u as o,n as t,o as c}from"./CcONa1Mr.js";function u(e){throw new Error("https://svelte.dev/e/lifecycle_outside_component")}function r(e){t===null&&u(),o(()=>{const n=c(e);if(typeof n=="function")return n})}export{r as o};

backend/static/export-viewer/_app/immutable/chunks/BRDva_z9.js

@@ -1 +0,0 @@
-import{f as l,g as o,p as u,i as n,j as d,k as m,h as p,e as _,m as v,l as k}from"./CcONa1Mr.js";class w{anchor;#t=new Map;#s=new Map;#e=new Map;#i=new Set;#f=!0;constructor(t,s=!0){this.anchor=t,this.#f=s}#a=t=>{if(this.#t.has(t)){var s=this.#t.get(t),e=this.#s.get(s);if(e)l(e),this.#i.delete(s);else{var f=this.#e.get(s);f&&(this.#s.set(s,f.effect),this.#e.delete(s),f.fragment.lastChild.remove(),this.anchor.before(f.fragment),e=f.effect)}for(const[i,a]of this.#t){if(this.#t.delete(i),i===t)break;const r=this.#e.get(a);r&&(o(r.effect),this.#e.delete(a))}for(const[i,a]of this.#s){if(i===s||this.#i.has(i))continue;const r=()=>{if(Array.from(this.#t.values()).includes(i)){var c=document.createDocumentFragment();v(a,c),c.append(n()),this.#e.set(i,{effect:a,fragment:c})}else o(a);this.#i.delete(i),this.#s.delete(i)};this.#f||!e?(this.#i.add(i),u(a,r,!1)):r()}}};#r=t=>{this.#t.delete(t);const s=Array.from(this.#t.values());for(const[e,f]of this.#e)s.includes(e)||(o(f.effect),this.#e.delete(e))};ensure(t,s){var e=m,f=k();if(s&&!this.#s.has(t)&&!this.#e.has(t))if(f){var i=document.createDocumentFragment(),a=n();i.append(a),this.#e.set(t,{effect:d(()=>s(a)),fragment:i})}else this.#s.set(t,d(()=>s(this.anchor)));if(this.#t.set(e,t),f){for(const[r,h]of this.#s)r===t?e.unskip_effect(h):e.skip_effect(h);for(const[r,h]of this.#e)r===t?e.unskip_effect(h.effect):e.skip_effect(h.effect);e.oncommit(this.#a),e.ondiscard(this.#r)}else p&&(this.anchor=_),this.#a(e)}}export{w as B};

backend/static/export-viewer/_app/immutable/chunks/Bxn6SmGf.js

@@ -1 +0,0 @@
-import{b as c,h as o,a as l,E as b,r as p,s as v,c as g,d,e as m}from"./CcONa1Mr.js";import{B as y}from"./BRDva_z9.js";function k(f,h,_=!1){var n;o&&(n=m,l());var s=new y(f),u=_?b:0;function t(a,r){if(o){var e=p(n);if(a!==parseInt(e.substring(1))){var i=v();g(i),s.anchor=i,d(!1),s.ensure(a,r),d(!0);return}}s.ensure(a,r)}c(()=>{var a=!1;h((r,e=0)=>{a=!0,t(e,r)}),a||t(-1,null)},u)}export{k as i};

backend/static/export-viewer/_app/immutable/chunks/RsTAN2PN.js

@@ -1 +0,0 @@
-import{A as v,i as d,B as l,C as u,D as T,T as p,F as h,h as i,e as s,R as E,a as y,G as g,c as w,H as N}from"./CcONa1Mr.js";const A=globalThis?.window?.trustedTypes&&globalThis.window.trustedTypes.createPolicy("svelte-trusted-html",{createHTML:t=>t});function M(t){return A?.createHTML(t)??t}function x(t){var r=v("template");return r.innerHTML=M(t.replaceAll("<!>","<!---->")),r.content}function n(t,r){var e=l;e.nodes===null&&(e.nodes={start:t,end:r,a:null,t:null})}function b(t,r){var e=(r&p)!==0,f=(r&h)!==0,a,_=!t.startsWith("<!>");return()=>{if(i)return n(s,null),s;a===void 0&&(a=x(_?t:"<!>"+t),e||(a=u(a)));var o=f||T?document.importNode(a,!0):a.cloneNode(!0);if(e){var c=u(o),m=o.lastChild;n(c,m)}else n(o,o);return o}}function C(t=""){if(!i){var r=d(t+"");return n(r,r),r}var e=s;return e.nodeType!==g?(e.before(e=d()),w(e)):N(e),n(e,e),e}function O(){if(i)return n(s,null),s;var t=document.createDocumentFragment(),r=document.createComment(""),e=d();return t.append(r,e),n(r,e),t}function P(t,r){if(i){var e=l;((e.f&E)===0||e.nodes.end===null)&&(e.nodes.end=s),y();return}t!==null&&t.before(r)}const L="5";typeof window<"u"&&((window.__svelte??={}).v??=new Set).add(L);export{P as a,n as b,O as c,b as f,C as t};

backend/static/export-viewer/_app/immutable/entry/start.YjNZv4co.js

@@ -1 +0,0 @@
-import{l as o,a as r}from"../chunks/eAGLaJx1.js";export{o as load_css,r as start};

backend/static/export-viewer/_app/immutable/nodes/0.DLesTSIe.js

@@ -1 +0,0 @@
-import{c as s,a as c}from"../chunks/RsTAN2PN.js";import{b as l,E as p,t as i}from"../chunks/CcONa1Mr.js";import{B as m}from"../chunks/BRDva_z9.js";function u(n,r,...e){var o=new m(n);l(()=>{const t=r()??null;o.ensure(t,t&&(a=>t(a,...e)))},p)}const f=!0,_=!1,g=Object.freeze(Object.defineProperty({__proto__:null,prerender:f,ssr:_},Symbol.toStringTag,{value:"Module"}));function h(n,r){var e=s(),o=i(e);u(o,()=>r.children),c(n,e)}export{h as component,g as universal};

backend/static/export-viewer/_app/immutable/nodes/1.D6Kk4lDA.js

@@ -1 +0,0 @@
-import{a as i,f as h}from"../chunks/RsTAN2PN.js";import{q as g,t as v,v as d,w as l,x as s,y as a,z as x}from"../chunks/CcONa1Mr.js";import{s as o}from"../chunks/Bb9JxzU7.js";import{s as _,p}from"../chunks/eAGLaJx1.js";const $={get error(){return p.error},get status(){return p.status}};_.updated.check;const m=$;var k=h("<h1> </h1> <p> </p>",1);function z(c,f){g(f,!0);var t=k(),r=v(t),n=s(r,!0);a(r);var e=x(r,2),u=s(e,!0);a(e),d(()=>{o(n,m.status),o(u,m.error?.message)}),i(c,t),l()}export{z as component};

backend/static/export-viewer/_app/version.json

@@ -1 +0,0 @@
-{"version":"1778876725548"}

backend/tests/common/mod.rs

@@ -255,3 +255,91 @@ pub async fn downloadable(pool: &PgPool, event_id: Uuid, export_type: &str) -> O
     .expect("downloadable")
     .flatten()
 }
+
+/// Insert an upload of `size` bytes, optionally already soft-deleted.
+pub async fn seed_upload(
+    pool: &PgPool,
+    event_id: Uuid,
+    user_id: Uuid,
+    size: i64,
+    deleted: bool,
+) -> Uuid {
+    sqlx::query_scalar(
+        "INSERT INTO upload (event_id, user_id, original_path, mime_type,
+                             original_size_bytes, deleted_at)
+         VALUES ($1, $2, 'originals/x.jpg', 'image/jpeg', $3,
+                 CASE WHEN $4 THEN NOW() ELSE NULL END)
+         RETURNING id",
+    )
+    .bind(event_id)
+    .bind(user_id)
+    .bind(size)
+    .bind(deleted)
+    .fetch_one(pool)
+    .await
+    .expect("seed upload")
+}
+
+/// Flip the moderation flags a ban sets.
+pub async fn set_user_moderation(pool: &PgPool, user_id: Uuid, banned: bool, hidden: bool) {
+    sqlx::query("UPDATE \"user\" SET is_banned = $2, uploads_hidden = $3 WHERE id = $1")
+        .bind(user_id)
+        .bind(banned)
+        .bind(hidden)
+        .execute(pool)
+        .await
+        .expect("set moderation");
+}
+
+/// SRC: `services/export.rs::query_uploads` — the visibility filter, verbatim, projected down to
+/// `(id, original_size_bytes)`. This is the row set that ACTUALLY lands in the archives.
+///
+/// Production builds this WHERE from `export_visibility_where!()`, shared with
+/// `estimate_export_bytes`. A copy here can pin the behaviour but CANNOT detect production moving
+/// away from it — that is what sharing the fragment is for, not this.
+pub async fn export_visible_uploads(pool: &PgPool, event_id: Uuid) -> Vec<(Uuid, i64)> {
+    sqlx::query_as(
+        "SELECT u.id, u.original_size_bytes
+         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
+         GROUP BY u.id, usr.display_name
+         ORDER BY u.created_at ASC",
+    )
+    .bind(event_id)
+    .fetch_all(pool)
+    .await
+    .expect("export_visible_uploads")
+}
+
+/// SRC: `services/export.rs::estimate_export_bytes` — verbatim. Same caveat as above: production
+/// shares its WHERE with `query_uploads` via `export_visibility_where!()`, so these two copies
+/// agreeing proves the behaviour, not the absence of drift.
+pub async fn estimate_export_bytes(pool: &PgPool, event_id: Uuid) -> i64 {
+    let (bytes,): (i64,) = sqlx::query_as(
+        "SELECT COALESCE(SUM(u.original_size_bytes), 0)::bigint
+           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_one(pool)
+    .await
+    .expect("estimate_export_bytes");
+    bytes
+}
+
+/// SRC: `services/export.rs::ensure_export_space` — the armed-job count, verbatim.
+pub async fn armed_job_count(pool: &PgPool, event_id: Uuid) -> i64 {
+    let (n,): (i64,) = sqlx::query_as(
+        "SELECT COUNT(*) FROM export_job
+          WHERE event_id = $1 AND status IN ('pending', 'running')",
+    )
+    .bind(event_id)
+    .fetch_one(pool)
+    .await
+    .expect("armed_job_count");
+    n
+}

backend/tests/export_preflight.rs

@@ -0,0 +1,163 @@
+//! DB-backed tests for the export disk preflight.
+//!
+//! The keepsake used to be built with NO free-space check at all, and the failure that produced was
+//! not "the export failed" but "the deliverable is stuck and the escape hatch needs the space that
+//! isn't there":
+//!
+//!   1. A takedown bumps the epoch and re-arms both halves.
+//!   2. The ZIP hits ENOSPC partway through a multi-GB write.
+//!   3. The job row is now `failed` at the CURRENT epoch, so readiness
+//!      (`epoch = event.export_epoch AND status = 'done'`) is false and `GET /export/zip` 404s —
+//!      while the last good archive sits on disk, unreferenced and unreachable.
+//!   4. `POST /host/export/rebuild` re-arms the same doomed write.
+//!
+//! Two changes close it: reclaim the superseded generation BEFORE building (so peak usage is one
+//! generation, not two) and refuse up front with a number the host can act on.
+//!
+//! What these tests pin is the ESTIMATE — the part that decides. The arithmetic on top of it lives
+//! in `services/export.rs`'s unit tests; the filesystem selection lives in `is_superseded_archive`.
+//!
+//! ON DRIFT, precisely, because it is easy to overclaim here. The hazard is that `query_uploads`
+//! (which selects the rows the archives are built from) and `estimate_export_bytes` (which sizes
+//! them) could disagree — and an estimate missing rows the archive writes UNDER-reserves, the one
+//! direction that reintroduces the ENOSPC. **These tests cannot catch that**, and neither can any
+//! test in this harness: both sides here are `SRC:`-marked hand-copies in `tests/common/mod.rs`,
+//! so if production moved and the copies didn't, they would sit still and keep passing.
+//!
+//! That is fixed where it can be — the two queries now share one `export_visibility_where!()`
+//! fragment in `services/export.rs`, so they cannot diverge by construction. What is left for
+//! these tests is what the convention is genuinely good at: pinning the BEHAVIOUR, so a change
+//! that deliberately alters the filter has to come here and say so.
+
+mod common;
+
+use common::*;
+use sqlx::PgPool;
+
+/// The estimate must equal the sum over EXACTLY the rows `query_uploads` returns — computed from
+/// that row set, not from a restatement of its WHERE clause.
+///
+/// PINS: which uploads the preflight is allowed to count. Each excluded row below is excluded by a
+/// DIFFERENT predicate, so a change that drops or weakens any one of them fails here and has to be
+/// argued for. (It does not detect production drifting away from these copies — see the file
+/// header; `export_visibility_where!()` is what makes that impossible.)
+#[sqlx::test]
+async fn the_estimate_sums_exactly_the_rows_the_archive_will_contain(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+
+    let visible = seed_user(&pool, event_id, "Anna").await;
+    let banned = seed_user(&pool, event_id, "Ben").await;
+    let hidden = seed_user(&pool, event_id, "Cara").await;
+
+    seed_upload(&pool, event_id, visible, 1_000, false).await;
+    seed_upload(&pool, event_id, visible, 2_500, false).await;
+    // Each of these is excluded from the archive by a DIFFERENT predicate.
+    seed_upload(&pool, event_id, visible, 9_000, true).await; // soft-deleted
+    seed_upload(&pool, event_id, banned, 9_000, false).await; // uploader banned
+    seed_upload(&pool, event_id, hidden, 9_000, false).await; // uploads hidden
+
+    set_user_moderation(&pool, banned, true, true).await;
+    set_user_moderation(&pool, hidden, false, true).await;
+
+    let rows = export_visible_uploads(&pool, event_id).await;
+    let expected: i64 = rows.iter().map(|(_, bytes)| bytes).sum();
+
+    assert_eq!(rows.len(), 2, "only Anna's two live uploads are archived");
+    assert_eq!(
+        estimate_export_bytes(&pool, event_id).await,
+        expected,
+        "the preflight must size the gallery the export will actually write"
+    );
+    assert_eq!(expected, 3_500);
+}
+
+/// An event with nothing to archive estimates zero rather than NULL.
+///
+/// PREVENTS: `SUM()` over no rows returning NULL and the decode blowing up — which would abort the
+/// export with a type error instead of building an (entirely legitimate) empty keepsake.
+#[sqlx::test]
+async fn an_empty_gallery_estimates_zero_not_null(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    assert_eq!(estimate_export_bytes(&pool, event_id).await, 0);
+
+    // And with a user who has uploaded nothing.
+    seed_user(&pool, event_id, "Anna").await;
+    assert_eq!(estimate_export_bytes(&pool, event_id).await, 0);
+}
+
+/// A release arms both halves, so the preflight sees a count of 2 and reserves for the pair.
+///
+/// PREVENTS: the concurrency under-reservation. `spawn_export_jobs` starts the ZIP and HTML workers
+/// at the same instant, and BOTH are gallery-sized (`Memories.zip` streams the original for every
+/// video and every image at or under 5 MB, all `Compression::Stored`). A worker reserving only for
+/// itself would see "it fits", its sibling would independently see the same, and together they
+/// would ENOSPC — which is why `required_free_bytes` multiplies by this count.
+#[sqlx::test]
+async fn a_release_arms_both_halves_so_the_preflight_reserves_for_two(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let user = seed_user(&pool, event_id, "Anna").await;
+    seed_upload(&pool, event_id, user, 1_000, false).await;
+
+    assert_eq!(
+        armed_job_count(&pool, event_id).await,
+        0,
+        "nothing is armed before the release"
+    );
+
+    let epoch = release_gallery(&pool, "wedding").await.expect("released");
+    assert_eq!(
+        armed_job_count(&pool, event_id).await,
+        2,
+        "a release arms zip AND html — both compete for the same disk"
+    );
+
+    // A worker that has claimed its half is still competing; `running` must keep counting.
+    assert!(claim_job(&pool, event_id, "zip", epoch).await);
+    assert_eq!(
+        armed_job_count(&pool, event_id).await,
+        2,
+        "claiming moves pending -> running, which must not drop out of the reservation"
+    );
+
+    // Only a FINISHED half stops competing.
+    assert!(finalize_job(&pool, event_id, "zip", epoch, "exports/Gallery.zip").await);
+    assert_eq!(
+        armed_job_count(&pool, event_id).await,
+        1,
+        "a done half no longer needs space reserved for it"
+    );
+}
+
+/// A ViewerOnly regeneration re-arms only the HTML half, so the preflight reserves for one.
+///
+/// PREVENTS: over-reservation refusing a rebuild that fits perfectly well. Moderating a comment
+/// carries the finished ZIP forward untouched; demanding room for a second copy of it would fail
+/// the one operation that needs no new gallery-sized write at all.
+#[sqlx::test]
+async fn a_viewer_only_regeneration_reserves_for_one_half(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let user = seed_user(&pool, event_id, "Anna").await;
+    seed_upload(&pool, event_id, user, 1_000, false).await;
+
+    let epoch = release_gallery(&pool, "wedding").await.expect("released");
+    for t in ["zip", "html"] {
+        assert!(claim_job(&pool, event_id, t, epoch).await);
+        assert!(finalize_job(&pool, event_id, t, epoch, &format!("exports/{t}")).await);
+    }
+    assert_eq!(armed_job_count(&pool, event_id).await, 0);
+
+    // A moderated comment: bump the epoch, carry the ZIP forward, re-arm only the viewer.
+    let (_, _, next) = bump_epoch(&pool, "wedding").await.expect("bumped");
+    assert!(
+        carry_zip_forward(&pool, event_id, next).await,
+        "the finished ZIP is re-stamped, not rebuilt"
+    );
+    let mut conn = pool.acquire().await.expect("acquire");
+    enqueue_types_at_epoch(&mut conn, event_id, next, &["html"]).await;
+
+    assert_eq!(
+        armed_job_count(&pool, event_id).await,
+        1,
+        "only the viewer is being rebuilt, so only one archive's worth of space is needed"
+    );
+}

backend/tests/failed_original_sweep.rs

@@ -0,0 +1,352 @@
+//! DB-backed tests for the deleted-media sweep (`services/maintenance.rs`).
+//!
+//! Context, in two halves.
+//!
+//! The compression worker deliberately no longer deletes an upload's original when its transcode
+//! fails — a transient ENOSPC or a codec panic must never destroy the only copy of a photo a guest
+//! cannot retake. But the row is soft-deleted and the uploader's quota IS refunded, so those bytes
+//! become invisible, unowned and free.
+//!
+//! The SAME hole was reachable by the ordinary path, and that one is not an edge case at all:
+//! `soft_delete_in_event` refunds `total_upload_bytes` on every guest or host delete and nothing
+//! removed the files, so the quota stopped bounding the disk. Upload 500 MB, delete, quota back to
+//! zero, upload another 500 MB — a guest curating their camera roll, which is what people do. The
+//! sweep used to reach only `compression_status = 'failed'`, so it never touched this case; the
+//! test below that now asserts an owner-deleted upload IS reclaimed is the one that used to assert
+//! the opposite.
+//!
+//! Two windows, because the two deletes mean different things: 14 days for a failure an operator
+//! may want to investigate, 24 hours for a removal someone asked for (14 days outlives the whole
+//! event, so a deliberate delete would never reclaim anything while it mattered).
+//!
+//! The selection predicate is the whole safety argument — it must reach both leftovers and never a
+//! live upload — so that is what these pin, following the same "reproduce the SQL verbatim" pattern
+//! as `upload_concurrency.rs`. `#[sqlx::test]` gives each test a fresh, migrated database.
+
+mod common;
+
+use common::*;
+use sqlx::PgPool;
+use uuid::Uuid;
+
+const FAILED_DAYS: i64 = 14;
+const DELETED_HOURS: i64 = 24;
+
+/// SRC: `services/maintenance.rs::cleanup_deleted_media` — the selection, verbatim.
+async fn sweep_selects(pool: &PgPool, failed_days: i64, deleted_hours: i64) -> Vec<Uuid> {
+    type Row = (Uuid, String, Option<String>, Option<String>, Option<String>);
+    sqlx::query_as::<_, Row>(
+        "SELECT id, original_path, preview_path, display_path, thumbnail_path FROM upload
+         WHERE deleted_at IS NOT NULL
+           AND CASE WHEN compression_status = 'failed'
+                    THEN deleted_at < NOW() - ($1 || ' days')::interval
+                    ELSE deleted_at < NOW() - ($2 || ' hours')::interval
+               END
+           AND (original_path <> '' OR preview_path IS NOT NULL
+                OR display_path IS NOT NULL OR thumbnail_path IS NOT NULL)",
+    )
+    .bind(failed_days.to_string())
+    .bind(deleted_hours.to_string())
+    .fetch_all(pool)
+    .await
+    .expect("sweep query")
+    .into_iter()
+    .map(|(id, ..)| id)
+    .collect()
+}
+
+/// Seed an upload aged `deleted_hours_ago` (None = live), with optional derivative paths.
+async fn seed_aged_upload(
+    pool: &PgPool,
+    event_id: Uuid,
+    user_id: Uuid,
+    status: &str,
+    deleted_hours_ago: Option<i64>,
+    original_path: &str,
+    derivatives: bool,
+) -> Uuid {
+    sqlx::query_scalar(
+        "INSERT INTO upload (event_id, user_id, original_path, mime_type, original_size_bytes,
+                             compression_status, deleted_at,
+                             preview_path, display_path, thumbnail_path)
+         VALUES ($1, $2, $3, 'image/jpeg', 1000, $4,
+                 CASE WHEN $5::bigint IS NULL THEN NULL
+                      ELSE NOW() - ($5::text || ' hours')::interval END,
+                 CASE WHEN $6 THEN 'previews/p.jpg' END,
+                 CASE WHEN $6 THEN 'displays/d.jpg' END,
+                 CASE WHEN $6 THEN 'thumbs/t.jpg' END)
+         RETURNING id",
+    )
+    .bind(event_id)
+    .bind(user_id)
+    .bind(original_path)
+    .bind(status)
+    .bind(deleted_hours_ago)
+    .bind(derivatives)
+    .fetch_one(pool)
+    .await
+    .expect("seed upload")
+}
+
+/// A live upload is untouchable no matter how the windows are configured.
+///
+/// PREVENTS: the catastrophic loosening. Everything else here is about reclaiming more; this is the
+/// one assertion that must never bend.
+#[sqlx::test]
+async fn a_live_upload_is_never_selected(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-live").await;
+    let user_id = seed_user(&pool, event_id, "Sweeper").await;
+
+    for status in ["done", "failed", "processing", "pending"] {
+        let live = seed_aged_upload(
+            &pool,
+            event_id,
+            user_id,
+            status,
+            None,
+            "originals/e/live.jpg",
+            true,
+        )
+        .await;
+        assert!(
+            !sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS)
+                .await
+                .contains(&live),
+            "a non-deleted upload with status {status} must never be swept"
+        );
+    }
+}
+
+/// THE FIX. An upload a guest or host deliberately deleted is reclaimed once past 24 hours.
+///
+/// PREVENTS: the regression back to a sweep scoped to `compression_status = 'failed'`, which is
+/// what let the quota stop bounding the disk. This assertion is the inverse of the one this file
+/// used to make.
+#[sqlx::test]
+async fn a_deliberately_deleted_upload_is_reclaimed_after_a_day(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-deleted").await;
+    let user_id = seed_user(&pool, event_id, "Curator").await;
+
+    let deleted = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "done",
+        Some(48),
+        "originals/e/owner.jpg",
+        true,
+    )
+    .await;
+    // Still inside the window — a mis-tap is recoverable for a day.
+    let recent = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "done",
+        Some(2),
+        "originals/e/recent.jpg",
+        true,
+    )
+    .await;
+
+    let selected = sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS).await;
+    assert!(
+        selected.contains(&deleted),
+        "a deliberate delete past the window must be reclaimed — this is the leak"
+    );
+    assert!(
+        !selected.contains(&recent),
+        "a delete inside the window keeps its recovery grace"
+    );
+}
+
+/// The two windows are independent: a failure is retained far longer than a deliberate delete.
+///
+/// PREVENTS: collapsing them into one. Applying 24h to failures would destroy the recovery window
+/// the retained-original fix exists to provide; applying 14 days to deliberate deletes would mean
+/// nothing is ever reclaimed during an event.
+#[sqlx::test]
+async fn the_two_retention_windows_do_not_bleed_into_each_other(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-windows").await;
+    let user_id = seed_user(&pool, event_id, "Windows").await;
+
+    // 48h old: past the deliberate window, nowhere near the failure window.
+    let failed_recent = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "failed",
+        Some(48),
+        "originals/e/f-recent.jpg",
+        false,
+    )
+    .await;
+    let deleted_same_age = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "done",
+        Some(48),
+        "originals/e/d-same.jpg",
+        false,
+    )
+    .await;
+    // 30 days old: past both.
+    let failed_old = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "failed",
+        Some(30 * 24),
+        "originals/e/f-old.jpg",
+        false,
+    )
+    .await;
+
+    let selected = sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS).await;
+    assert!(
+        !selected.contains(&failed_recent),
+        "a 2-day-old compression failure is still inside its 14-day recovery window"
+    );
+    assert!(
+        selected.contains(&deleted_same_age),
+        "a deliberate delete of the same age is past its 24-hour window"
+    );
+    assert!(
+        selected.contains(&failed_old),
+        "a 30-day-old failure is past both windows"
+    );
+}
+
+/// Boundary behaviour on both windows.
+#[sqlx::test]
+async fn retention_windows_are_honoured_at_the_boundary(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-boundary").await;
+    let user_id = seed_user(&pool, event_id, "Boundary").await;
+
+    let cases = [
+        ("failed", 13 * 24, false, "13 days"),
+        ("failed", 15 * 24, true, "15 days"),
+        ("done", 23, false, "23 hours"),
+        ("done", 25, true, "25 hours"),
+    ];
+    for (status, hours, expected, label) in cases {
+        let id = seed_aged_upload(
+            &pool,
+            event_id,
+            user_id,
+            status,
+            Some(hours),
+            "originals/e/b.jpg",
+            false,
+        )
+        .await;
+        assert_eq!(
+            sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS)
+                .await
+                .contains(&id),
+            expected,
+            "a {status} upload deleted {label} ago: expected swept={expected}"
+        );
+        sqlx::query("DELETE FROM upload WHERE id = $1")
+            .bind(id)
+            .execute(&pool)
+            .await
+            .expect("clean up");
+    }
+}
+
+/// A row is re-selected until EVERY one of its paths is cleared.
+///
+/// PREVENTS: two failures at once. The sweep used to clear `original_path` alone, which was right
+/// for its only case (a failed compression produces no derivatives) but leaves preview, display and
+/// thumbnail on disk the moment it reaches a successfully processed upload — three files per
+/// upload, none of them counted in `original_size_bytes`, that nothing else ever removes. And a row
+/// whose paths are all cleared must stop coming back, or every hourly tick logs a phantom reclaim
+/// forever.
+#[sqlx::test]
+async fn a_row_is_reselected_until_every_path_is_cleared(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-idempotent").await;
+    let user_id = seed_user(&pool, event_id, "Idem").await;
+    let id = seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "done",
+        Some(48),
+        "originals/e/once.jpg",
+        true,
+    )
+    .await;
+
+    assert_eq!(sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS).await, [id]);
+
+    // Clearing only the original is NOT enough — the derivatives are still on disk.
+    sqlx::query("UPDATE upload SET original_path = '' WHERE id = $1")
+        .bind(id)
+        .execute(&pool)
+        .await
+        .expect("clear original");
+    assert_eq!(
+        sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS).await,
+        [id],
+        "derivatives left behind must keep the row selected"
+    );
+
+    sqlx::query(
+        "UPDATE upload SET preview_path = NULL, display_path = NULL, thumbnail_path = NULL
+         WHERE id = $1",
+    )
+    .bind(id)
+    .execute(&pool)
+    .await
+    .expect("clear derivatives");
+    assert!(
+        sweep_selects(&pool, FAILED_DAYS, DELETED_HOURS)
+            .await
+            .is_empty(),
+        "a fully swept row must not come back"
+    );
+}
+
+/// The derivative backfill must never resurrect what the sweep just reclaimed.
+///
+/// PREVENTS: an interaction, not a bug in either piece. The sweep nulls `preview_path`, and
+/// `backfill_stale_derivatives` selects on `display_path IS NULL AND preview_path IS NOT NULL` —
+/// close enough that a future edit to either could have the backfill re-decode an original that is
+/// no longer on disk, on every boot. `deleted_at IS NULL` is what keeps them apart.
+#[sqlx::test]
+async fn the_backfill_ignores_swept_rows(pool: PgPool) {
+    let event_id = seed_event(&pool, "sweep-backfill").await;
+    let user_id = seed_user(&pool, event_id, "Backfill").await;
+    seed_aged_upload(
+        &pool,
+        event_id,
+        user_id,
+        "done",
+        Some(48),
+        "originals/e/gone.jpg",
+        true,
+    )
+    .await;
+
+    // SRC: `services/compression.rs::backfill_stale_derivatives` — the selection, verbatim.
+    let backfilled: Vec<(Uuid, String, String)> = sqlx::query_as(
+        "SELECT id, original_path, mime_type FROM upload
+             WHERE deleted_at IS NULL AND mime_type LIKE 'image/%'
+               AND original_path IS NOT NULL
+               AND (
+                     (display_path IS NULL AND preview_path IS NOT NULL)
+                  OR derivatives_rev < $1
+               )",
+    )
+    .bind(1i16)
+    .fetch_all(&pool)
+    .await
+    .expect("backfill query");
+
+    assert!(
+        backfilled.is_empty(),
+        "a soft-deleted row must be invisible to the backfill, before or after sweeping"
+    );
+}

docker-compose.dev.yml

@@ -11,3 +11,31 @@ services:
     # is tolerated (warned) rather than rejected.
     environment:
       APP_ENV: development
+      # `.env` sets DATABASE_URL to @localhost for the run-backend-natively workflow
+      # (the db port is published above for that). When the app runs IN a container,
+      # localhost is the app itself — point it at the `db` service instead. Creds are
+      # interpolated from .env so nothing is hardcoded.
+      DATABASE_URL: postgres://${POSTGRES_USER}:${POSTGRES_PASSWORD}@db:5432/${POSTGRES_DB}
+      # `.env` sets MEDIA_PATH to a HOST path (/home/fabi/EventSnap/media) for the
+      # run-backend-natively workflow. In a container that path doesn't exist and the
+      # app user can't create it from `/`, so every upload 500s with EACCES. The media
+      # volume is mounted at /media (see docker-compose.yml) — point the app there.
+      MEDIA_PATH: /media
+      # Recent Docker Compose interpolates env_file values, so the `$` segments of the
+      # bcrypt ADMIN_PASSWORD_HASH in .env get eaten (the salt reads as an unset var) —
+      # every admin login then 401s. Re-supply it here with `$` doubled to `$$` so Compose
+      # passes the literal hash. NOTE: production (docker-compose.yml + .env) has the SAME
+      # bug — escape the hash as `$$` in .env, or set it via `environment:` there too.
+      ADMIN_PASSWORD_HASH: "$$2b$$12$$PAteqCNpsbm6d0HTJcywfOaUovjAU.iNVlsL7EDYaRC/z4P/xv7ye"
+      # Smoke-testing the comment kill-switch: boot-time flag, so it needs a restart
+      # (not an admin-UI toggle). Backend rejects new comments (403) and the frontend
+      # hides the whole comment UI. Flip back to true (or drop this line) to restore.
+      COMMENTS_ENABLED: "false"
+
+  caddy:
+    # The prod caddy service has no env_file, so the Caddyfile's `{$DOMAIN}` expands
+    # to empty and the site block collapses into a malformed global block. Supply it
+    # for local dev (from .env → localhost, which Caddy serves with a local self-signed
+    # cert). NOTE: the prod compose likely needs DOMAIN wired to caddy too.
+    environment:
+      DOMAIN: ${DOMAIN}

docker-compose.yml

@@ -17,7 +17,15 @@ services:
     deploy:
       resources:
         limits:
-          memory: 512M
+          # 1G, not 512M. DATABASE_MAX_CONNECTIONS defaults to 30 for a ~100-guest event
+          # (feed polling + SSE + uploads at once), and 30 backends plus Postgres 16's
+          # default shared_buffers leaves very little headroom at 512M. An OOM here does
+          # not degrade one feature — it takes the event down, because every request
+          # path touches the database. Memory is the cheaper knob than shrinking the
+          # pool back and reintroducing the queueing it was raised to fix.
+          #
+          # Raising DATABASE_MAX_CONNECTIONS further means raising this too.
+          memory: 1G
 
   app:
     build:
@@ -29,6 +37,12 @@ services:
       # Activates the production secret guard in config.rs — refuses to boot with
       # placeholder JWT_SECRET / ADMIN_PASSWORD_HASH.
       APP_ENV: production
+      # The media volume is mounted at /media (below), so the app MUST write there.
+      # Pin it here rather than trusting .env: if MEDIA_PATH in .env points elsewhere
+      # (e.g. a host path used for running the backend natively) the container can't
+      # create it and every upload 500s with EACCES. `environment` overrides `env_file`,
+      # so this is authoritative for the container.
+      MEDIA_PATH: /media
     depends_on:
       db:
         condition: service_healthy
@@ -40,7 +54,11 @@ services:
     expose:
       - "3000"
     healthcheck:
-      test: ["CMD-SHELL", "wget -q -O- http://localhost:3000/health || exit 1"]
+      # Use 127.0.0.1, NOT localhost: the app binds IPv4 (0.0.0.0) but `localhost`
+      # resolves to ::1 (IPv6) first inside the container, so a localhost probe gets
+      # "connection refused" and the container never turns healthy — which would leave
+      # Caddy (gated on `condition: service_healthy` below) blocked forever on boot.
+      test: ["CMD-SHELL", "wget -q -O- http://127.0.0.1:3000/health || exit 1"]
       interval: 10s
       timeout: 5s
       retries: 5
@@ -67,7 +85,9 @@ services:
     expose:
       - "3001"
     healthcheck:
-      test: ["CMD-SHELL", "wget -q -O- http://localhost:3001/ >/dev/null 2>&1 || exit 1"]
+      # 127.0.0.1, not localhost — see the app healthcheck note above (IPv4 bind vs
+      # ::1 resolution would leave this container permanently unhealthy).
+      test: ["CMD-SHELL", "wget -q -O- http://127.0.0.1:3001/ >/dev/null 2>&1 || exit 1"]
       interval: 10s
       timeout: 5s
       retries: 5
@@ -80,6 +100,12 @@ services:
   caddy:
     image: caddy:2-alpine
     restart: unless-stopped
+    environment:
+      # The Caddyfile's site address is `{$DOMAIN}`, read from THIS container's env.
+      # Without it, `{$DOMAIN}` expands to empty, the site block collapses, and Caddy
+      # serves nothing / fails to obtain a TLS cert. `env_file` alone wouldn't help —
+      # Caddy needs it in `environment`, and this keeps the Caddyfile the single source.
+      DOMAIN: ${DOMAIN}
     ports:
       - "80:80"
       - "443:443"

e2e/Caddyfile.test

@@ -12,10 +12,17 @@
     # Mirror prod's security headers (minus HSTS, which is HTTPS-only).
     header {
         X-Content-Type-Options "nosniff"
-        X-Frame-Options "DENY"
         Referrer-Policy "strict-origin-when-cross-origin"
     }
 
+    # Mirror prod's export carve-out: the keepsake download targets a hidden
+    # same-origin iframe, and WebKit enforces XFO before Content-Disposition.
+    # Two disjoint matchers, not an override — see the comment in ../Caddyfile.
+    @framable path /api/v1/export/zip /api/v1/export/html
+    @not_framable not path /api/v1/export/zip /api/v1/export/html
+    header @framable X-Frame-Options "SAMEORIGIN"
+    header @not_framable X-Frame-Options "DENY"
+
     reverse_proxy /api/* app:3000
     reverse_proxy /media/* app:3000
     reverse_proxy /health app:3000

e2e/docker-compose.test.yml

@@ -42,11 +42,29 @@ services:
       EVENT_NAME: E2E Test Event
       APP_PORT: '3000'
       MEDIA_PATH: /media
+      # Exports MUST live outside MEDIA_PATH — see the note on the volume below and
+      # config.rs::validate. Omitting this left exports on the container's writable
+      # layer at the /exports default, so the test stack diverged from the prod layout
+      # it claims to mirror, and export-leak/export-video wrote real archives into
+      # ephemeral storage.
+      EXPORT_PATH: /exports
       SESSION_EXPIRY_DAYS: '30'
       EVENTSNAP_TEST_MODE: '1' # ENABLES /admin/__truncate — never set in prod
       RUST_LOG: eventsnap_backend=info,tower_http=warn
     volumes:
       - media_data:/media
+      # Separate volume, exactly as in production: a keepsake archive contains every
+      # photo in the event, so it is kept off the media tree.
+      - exports_data:/exports
+    # Mirror production's cap (docker-compose.yml). The test stack having NO memory limit is
+    # why an unbounded image decode was invisible here: a 99 MP upload that would OOM-kill the
+    # 1 GiB production container simply succeeded in CI. A test environment more generous than
+    # production cannot catch a resource bug — the same shape as WebKit being absent from CI
+    # and /health existing only in Caddyfile.test.
+    deploy:
+      resources:
+        limits:
+          memory: 1G
     expose:
       - '3000'
 
@@ -75,3 +93,4 @@ services:
 
 volumes:
   media_data:
+  exports_data:

e2e/fixtures/db.ts

@@ -54,6 +54,27 @@ export const db = {
     );
   },
 
+  async compressionStatus(uploadId: string): Promise<string | null> {
+    return withClient(async (c) => {
+      const r = await c.query<{ compression_status: string }>(
+        `SELECT compression_status FROM upload WHERE id = $1`,
+        [uploadId]
+      );
+      return r.rows[0]?.compression_status ?? null;
+    });
+  },
+
+  /** Which revision of the derivative pipeline produced this row's preview/display. */
+  async derivativesRev(uploadId: string): Promise<number | null> {
+    return withClient(async (c) => {
+      const r = await c.query<{ derivatives_rev: number }>(
+        `SELECT derivatives_rev FROM upload WHERE id = $1`,
+        [uploadId]
+      );
+      return r.rows[0]?.derivatives_rev ?? null;
+    });
+  },
+
   async countUploadsForUser(userId: string): Promise<number> {
     return withClient(async (c) => {
       const r = await c.query<{ count: string }>(
@@ -84,6 +105,20 @@ export const db = {
     });
   },
 
+  /**
+   * Overstate an upload's recorded size.
+   *
+   * The keepsake size estimate and the low-disk threshold are pure SQL over
+   * `original_size_bytes` — no file is read — so this is the lever for driving "the keepsake
+   * would not fit" without a genuinely full disk. The bytes on disk are unchanged; only the
+   * accounting the warning reads from moves.
+   */
+  async setUploadSizeBytes(uploadId: string, bytes: number) {
+    await withClient((c) =>
+      c.query(`UPDATE upload SET original_size_bytes = $2 WHERE id = $1`, [uploadId, bytes])
+    );
+  },
+
   async setExportReleased(slug: string, released: boolean) {
     await withClient((c) =>
       c.query(`UPDATE event SET export_released_at = $2 WHERE slug = $1`, [
@@ -121,7 +156,8 @@ export const db = {
   async fakeExportJob(
     eventSlug: string,
     type: 'zip' | 'html',
-    status: 'pending' | 'running' | 'done'
+    status: 'pending' | 'running' | 'done' | 'failed',
+    errorMessage: string | null = null
   ) {
     await withClient(async (c) => {
       const ev = await c.query<{ id: string; export_epoch: string }>(
@@ -130,11 +166,12 @@ export const db = {
       );
       if (ev.rows.length === 0) throw new Error(`No event with slug ${eventSlug}`);
       await c.query(
-        `INSERT INTO export_job (event_id, type, status, progress_pct, completed_at, epoch)
-         VALUES ($1, $2::export_type, $3::export_status, $4, $5, $6)
+        `INSERT INTO export_job (event_id, type, status, progress_pct, completed_at, epoch,
+                                 error_message)
+         VALUES ($1, $2::export_type, $3::export_status, $4, $5, $6, $7)
          ON CONFLICT (event_id, type) DO UPDATE
            SET status = EXCLUDED.status, progress_pct = EXCLUDED.progress_pct,
-               epoch = EXCLUDED.epoch`,
+               epoch = EXCLUDED.epoch, error_message = EXCLUDED.error_message`,
         [
           ev.rows[0].id,
           type,
@@ -142,6 +179,7 @@ export const db = {
           status === 'done' ? 100 : 0,
           status === 'done' ? new Date() : null,
           ev.rows[0].export_epoch,
+          errorMessage,
         ]
       );
     });

e2e/helpers/webkit.ts

@@ -0,0 +1,29 @@
+import { test } from '@playwright/test';
+
+/**
+ * Skip a test that depends on persisting a Blob/File in IndexedDB when running on
+ * Playwright's WebKit.
+ *
+ * The client upload queue (`frontend/src/lib/upload-queue.ts`) stores the file itself in
+ * IndexedDB so a backgrounded or reloaded phone can resume the upload. Playwright's Linux
+ * WebKit build cannot store Blobs in IndexedDB at all — `put()` fails with
+ * "UnknownError: Error preparing Blob/File data to be stored in object store". Verified to
+ * be the harness, not the app: a Blob constructed in-page with `new Blob([bytes])` fails
+ * exactly the same way, while Chromium stores both that and a `setInputFiles` File fine.
+ * Real iOS Safari supports Blobs in IndexedDB, so this is NOT evidence of a bug on the
+ * platform these tests exist to protect.
+ *
+ * Any test that drives the composer (FAB → UploadSheet → /upload → submit) hits this,
+ * because `handleSubmit` awaits `addToQueue`, which throws before it can navigate.
+ *
+ * This is deliberately narrow. WebKit still runs every API-driven upload test, the whole of
+ * 01-auth, 03-feed and 06-export — including the keepsake download, which only WebKit can
+ * meaningfully verify. If Playwright's WebKit ever gains IndexedDB Blob support, delete this
+ * helper and the four call sites.
+ */
+export function skipIfNoIdbBlobs(browserName: string) {
+  test.skip(
+    browserName === 'webkit',
+    "Playwright's Linux WebKit cannot store Blobs in IndexedDB (harness limitation, not an iOS one) — the client upload queue can't be exercised there"
+  );
+}

e2e/loadtest/.gitignore

@@ -0,0 +1,4 @@
+results/
+__pycache__/
+*.pyc
+*.log

e2e/loadtest/README.md

@@ -0,0 +1,112 @@
+# EventSnap load / stress test
+
+Simulates a real event: **~100 guests** joining and uploading **~1000 images** in
+bursts (10–20 at a time) spread across a compressed time window, a pool of
+**viewers** holding live SSE connections, and **one real browser** on `/diashow`
+acting as the showcase display.
+
+## Goal (this harness is tuned for it)
+
+**Validate the shipping config.** We run at the real production defaults —
+compression concurrency (`COMPRESSION_WORKER_CONCURRENCY`, default **2**), DB
+pool (default **10**), quotas **on** — and answer: _does the app survive the
+event, and how far behind real-time does the diashow fall?_
+
+The headline metric is **pipeline latency**: time from an upload succeeding to
+its preview being ready (`upload-processed` SSE event) — i.e. _how long until the
+photo appears on the diashow_. A backlog that builds is fine; a backlog that
+**never drains** is a fail for a live event.
+
+## Methodology: what we change vs. shipping
+
+We **only disable rate limits**. They're per-IP / per-user anti-abuse guards; a
+synthetic test from one IP trips them in a way real guests (distinct IPs, phones)
+never would — leaving them on would measure the limiter, not the pipeline.
+Everything else (compression concurrency, DB pool, quotas) stays at the real
+default so the result is honest.
+
+> **Standalone finding to remember:** the shipping `upload_rate_per_hour` default
+> is **10**. A real guest uploading a burst of 10–20 photos would be throttled by
+> the shipping config too. That's a genuine event-day issue worth surfacing
+> separately from this pipeline test.
+
+## Prereqs
+
+- The isolated test stack up: `cd e2e && npm run stack:up` (Caddy on `:3101`,
+  `EVENTSNAP_TEST_MODE=1`, `/admin/__truncate` live).
+- Node 24+ (global `fetch`/`FormData`/`Blob`), Python 3 + Pillow, Docker CLI
+  access (used for `docker stats` + `docker exec psql` ground-truth sampling).
+- `@playwright/test` (already an e2e dep) for the diashow watcher.
+
+## 1. Generate the image pool (once)
+
+Realistic phone-sized JPEGs (~2–4 MB, 12 MP, high entropy). The driver reuses
+this pool at random across all 1000 uploads — real load is byte size + decode
+cost, not file uniqueness.
+
+```bash
+python3 e2e/loadtest/gen-images.py 40      # → /tmp/eventsnap-loadtest/photos
+```
+
+~40 images ≈ 120 MB pool; projects to **~3–4 GB** of originals for 1000 uploads
+(previews/thumbnails add more). The generator prints the projection; check disk.
+
+## 2. Smoke run first (~1 min)
+
+Proves the wiring — join, upload, SSE correlation, drain, metrics — before the
+real thing:
+
+```bash
+LT_GUESTS=5 LT_IMAGES=50 LT_WINDOW_SEC=60 node e2e/loadtest/driver.mjs
+```
+
+## 3. Full run (~15 min + drain)
+
+Two terminals. Start the showcase display first, then the driver:
+
+```bash
+# terminal A — the showcase device
+node e2e/loadtest/diashow-watch.mjs
+
+# terminal B — 100 guests / 1000 images / 15-min window (defaults)
+node e2e/loadtest/driver.mjs
+```
+
+The driver truncates event data first (`LT_TRUNCATE=0` to keep), disables rate
+limits, joins guests, opens SSE, runs the burst schedule, then **waits for the
+compression backlog to drain** before reporting.
+
+## Output
+
+- Console: live progress every 10 s, then a RESULTS block with pass/fail flags.
+- `e2e/loadtest/results/run-<timestamp>.json`: full metrics — upload latency
+  percentiles, pipeline latency percentiles, drain time, per-status counts, SSE
+  reconnect/resync counts, and a `docker stats` + DB-connection time series.
+- `e2e/loadtest/results/diashow/`: periodic screenshots of the live display.
+
+## What the flags mean
+
+| Flag                      | Meaning                                                                      |
+| ------------------------- | ---------------------------------------------------------------------------- |
+| `✗ 5xx`                   | server errored under load — hard fail                                        |
+| `✗ 507`                   | quota rejected uploads — disk/quota misconfig for the event size             |
+| `✗ backlog did not drain` | compression can't keep up even after uploads stop — diashow never catches up |
+| `⚠ pipeline p95 > 60s`    | photos take >1 min to appear on the diashow at peak                          |
+| `⚠ SSE resyncs`           | live consumers lagged the broadcast channel                                  |
+
+## Knobs
+
+All via env (see header of `driver.mjs`): `LT_GUESTS`, `LT_IMAGES`,
+`LT_WINDOW_SEC`, `LT_BURST_MIN/MAX`, `LT_BURST_CONC`, `LT_VIEWERS`,
+`LT_TRUNCATE`, `LT_DRAIN_TIMEOUT_SEC`, `LT_KEEP_RATELIMITS`, `LT_BASE`,
+`LT_APP_CONTAINER`, `LT_DB_CONTAINER`.
+
+To later answer _"what config should I deploy?"_, re-run with a rebuilt stack
+that sets `COMPRESSION_WORKER_CONCURRENCY` higher (boot-time env var in
+`docker-compose.test.yml`) and compare the pipeline-latency / drain numbers.
+
+## Teardown
+
+```bash
+cd e2e && npm run stack:down     # wipes volumes (media + db)
+```

e2e/loadtest/confirm-diashow-fix.mjs

@@ -0,0 +1,109 @@
+// End-to-end confirmation of the diashow SSE fix, reproducing the ORIGINAL failure:
+// kiosk opens /diashow directly BEFORE any photos exist, then a guest uploads.
+// Pre-fix: stream never opens, display stuck on "Noch keine Beiträge" forever.
+// Post-fix: stream opens on mount, the uploaded photo appears live.
+import { chromium } from '@playwright/test';
+import { readFileSync } from 'node:fs';
+
+const BASE = 'http://localhost:3101';
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+const j = (r) => r.json();
+
+const adminLogin = () =>
+  fetch(`${BASE}/api/v1/admin/login`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ password: 'admin-test-pw' }),
+  })
+    .then(j)
+    .then((b) => b.jwt);
+const join = (name) =>
+  fetch(`${BASE}/api/v1/join`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ display_name: name }),
+  }).then(j);
+async function truncate(admin) {
+  await fetch(`${BASE}/api/v1/admin/__truncate`, {
+    method: 'POST',
+    headers: { Authorization: `Bearer ${admin}` },
+  });
+}
+async function upload(jwt) {
+  const form = new FormData();
+  form.append(
+    'file',
+    new Blob([readFileSync('/tmp/eventsnap-loadtest/photos/photo_000.jpg')], {
+      type: 'image/jpeg',
+    }),
+    'live.jpg'
+  );
+  form.append('caption', 'LIVE-PROBE');
+  const r = await fetch(`${BASE}/api/v1/upload`, {
+    method: 'POST',
+    headers: { Authorization: `Bearer ${jwt}` },
+    body: form,
+  });
+  return (await r.json()).id;
+}
+
+// Reproduce the failing scenario: empty event, then open /diashow directly.
+let admin = await adminLogin();
+await truncate(admin);
+admin = await adminLogin();
+const showcase = await join('Showcase Display');
+const guest = await join('Uploading Guest');
+
+const browser = await chromium.launch();
+const ctx = await browser.newContext({ viewport: { width: 1280, height: 800 } });
+const page = await ctx.newPage();
+const streamReqs = [];
+page.on('request', (req) => {
+  if (req.url().includes('/stream')) streamReqs.push(req.url().replace(BASE, ''));
+});
+
+await page.goto(`${BASE}/join`, { waitUntil: 'domcontentloaded' });
+await page.evaluate((g) => {
+  localStorage.setItem('eventsnap_jwt', g.jwt);
+  localStorage.setItem('eventsnap_pin', g.pin);
+  localStorage.setItem('eventsnap_user_id', g.user_id);
+  localStorage.setItem('eventsnap_display_name', 'Showcase');
+  localStorage.setItem('eventsnap_guide_seen', '1');
+}, showcase);
+
+// Open /diashow DIRECTLY (never via /feed) on an EMPTY event.
+await page.goto(`${BASE}/diashow`, { waitUntil: 'domcontentloaded' });
+await sleep(2500);
+const emptyBefore = (await page.locator('text=Noch keine Beiträge').count()) > 0;
+const streamOpened = streamReqs.length > 0;
+console.log(`\n1) direct /diashow on empty event:`);
+console.log(`   "Noch keine Beiträge" shown: ${emptyBefore}  (expected: true)`);
+console.log(
+  `   SSE stream opened: ${streamOpened}  ${streamOpened ? '(' + streamReqs.join(', ') + ')' : ''}  (expected: true — this is the fix)`
+);
+
+// Now a guest uploads a photo while the display is open.
+console.log(`\n2) guest uploads a photo (display already open)…`);
+await upload(guest.jwt);
+
+// Wait for compression → upload-processed SSE → debounced refresh → slide appears.
+let appeared = false;
+for (let i = 0; i < 15; i++) {
+  await sleep(1000);
+  const stillEmpty = (await page.locator('text=Noch keine Beiträge').count()) > 0;
+  const imgs = await page.locator('img').count();
+  if (!stillEmpty && imgs > 0) {
+    appeared = true;
+    console.log(`   photo appeared live after ~${i + 1}s (img rendered, placeholder gone)`);
+    break;
+  }
+}
+if (!appeared) console.log(`   ✗ photo did NOT appear within 15s`);
+
+await page.screenshot({ path: 'results/diashow-fix-confirm.png' });
+await browser.close();
+
+console.log(`\n════ VERDICT ════`);
+console.log(`SSE opens on direct /diashow: ${streamOpened ? 'YES ✓' : 'NO ✗'}`);
+console.log(`Live photo appears on showcase: ${appeared ? 'YES ✓' : 'NO ✗'}`);
+console.log(streamOpened && appeared ? 'FIX CONFIRMED' : 'FIX NOT confirmed');

e2e/loadtest/diashow-watch.mjs

@@ -0,0 +1,105 @@
+#!/usr/bin/env node
+/**
+ * The showcase display. Opens ONE real Chromium browser on /diashow (as a
+ * logged-in guest) for the duration of a load run, so we validate the real
+ * SSE → render path a projector/TV would use — not just the protocol.
+ *
+ * Run it alongside driver.mjs (separate terminal), started first:
+ *     node diashow-watch.mjs
+ *     # then in another terminal:
+ *     node driver.mjs
+ *
+ * It captures:
+ *   - periodic screenshots (so you can eyeball that new photos actually appear)
+ *   - browser console errors / page crashes / SSE disconnects surfaced in console
+ *   - a final count of slides rendered
+ *
+ * Env:
+ *   LT_BASE            http://localhost:3101
+ *   LT_WATCH_SEC       960              how long to keep the display open
+ *   LT_SHOT_EVERY_SEC  30               screenshot cadence
+ *   LT_OUT_DIR         ./results/diashow
+ */
+
+import { chromium, devices } from '@playwright/test';
+import { mkdirSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+import { dirname, join } from 'node:path';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const BASE = process.env.LT_BASE ?? 'http://localhost:3101';
+const WATCH_SEC = parseInt(process.env.LT_WATCH_SEC ?? '960', 10);
+const SHOT_EVERY = parseInt(process.env.LT_SHOT_EVERY_SEC ?? '30', 10);
+const OUT = process.env.LT_OUT_DIR ?? join(__dirname, 'results', 'diashow');
+
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+
+async function joinGuest(name) {
+  const res = await fetch(`${BASE}/api/v1/join`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ display_name: name }),
+  });
+  if (res.status !== 201) throw new Error(`join failed ${res.status}`);
+  return res.json();
+}
+
+async function main() {
+  mkdirSync(OUT, { recursive: true });
+  const guest = await joinGuest('Showcase Display');
+  console.log('[diashow] joined showcase guest, launching browser…');
+
+  const browser = await chromium.launch();
+  // A TV/projector is landscape; use a desktop-ish large viewport.
+  const ctx = await browser.newContext({ viewport: { width: 1920, height: 1080 } });
+  const page = await ctx.newPage();
+
+  let consoleErrors = 0;
+  page.on('console', (msg) => {
+    if (msg.type() === 'error') {
+      consoleErrors++;
+      console.log('[diashow][console.error]', msg.text().slice(0, 200));
+    }
+  });
+  page.on('pageerror', (e) => console.log('[diashow][pageerror]', String(e).slice(0, 200)));
+  page.on('crash', () => console.log('[diashow][CRASH] page crashed'));
+
+  // Seed auth in localStorage on the origin, then open /diashow.
+  await page.goto(`${BASE}/join`, { waitUntil: 'domcontentloaded' });
+  await page.evaluate((g) => {
+    localStorage.setItem('eventsnap_theme', 'dark');
+    localStorage.setItem('eventsnap_jwt', g.jwt);
+    localStorage.setItem('eventsnap_pin', g.pin);
+    localStorage.setItem('eventsnap_user_id', g.user_id);
+    localStorage.setItem('eventsnap_display_name', 'Showcase Display');
+    localStorage.setItem('eventsnap_guide_seen', '1');
+  }, guest);
+  await page.goto(`${BASE}/diashow`, { waitUntil: 'domcontentloaded' });
+  console.log(`[diashow] on /diashow, watching for ${WATCH_SEC}s (shots every ${SHOT_EVERY}s)`);
+
+  const start = Date.now();
+  let shot = 0;
+  while ((Date.now() - start) / 1000 < WATCH_SEC) {
+    await sleep(SHOT_EVERY * 1000);
+    const elapsed = Math.round((Date.now() - start) / 1000);
+    // best-effort slide count (diashow renders <img>; adjust selector if markup changes)
+    let imgs = -1;
+    try {
+      imgs = await page.locator('img').count();
+    } catch {
+      /* ignore */
+    }
+    const path = join(OUT, `diashow-t${String(elapsed).padStart(4, '0')}.png`);
+    await page.screenshot({ path }).catch(() => {});
+    console.log(`[diashow][t+${elapsed}s] imgs≈${imgs} consoleErrors=${consoleErrors} → ${path}`);
+    shot++;
+  }
+
+  console.log(`[diashow] done. ${shot} screenshots, ${consoleErrors} console errors total.`);
+  await browser.close();
+}
+
+main().catch((e) => {
+  console.error('[diashow] failed:', e);
+  process.exit(1);
+});

e2e/loadtest/driver.mjs

@@ -0,0 +1,654 @@
+#!/usr/bin/env node
+/**
+ * EventSnap load / stress driver.
+ *
+ * Simulates ~100 guests joining an event and uploading ~1000 images in bursts
+ * (10-20 at a time) spread across a compressed time window, plus a pool of
+ * viewers holding live SSE connections (like phones with the feed open) and one
+ * "diashow" connection (the showcase display). Measures the metrics that matter
+ * for a live event — especially the *pipeline backlog*: how long between an
+ * upload succeeding and its preview being ready (SSE `upload-processed`), which
+ * is exactly "how long until the photo shows up on the diashow".
+ *
+ * This is an HTTP-level driver on purpose: 100 real browsers would bottleneck
+ * the test box, not the server. One real browser watches /diashow separately
+ * (see diashow-watch.mjs).
+ *
+ * METHODOLOGY NOTE — what we change vs. the shipping config:
+ *   We ONLY disable rate limits. They are per-IP/per-user anti-abuse guards; a
+ *   synthetic test from one IP would trip them in a way real guests (distinct
+ *   IPs, phones) never would, so leaving them on would measure the rate limiter
+ *   instead of the pipeline. We DELIBERATELY leave compression concurrency,
+ *   DB pool size and quotas at their real defaults — validating those is the
+ *   whole point. (Runtime can't change compression concurrency anyway; it's a
+ *   boot-time env var.)
+ *
+ *   Related real-world finding to keep in mind: the default upload_rate_per_hour
+ *   is 10, so a real guest uploading a burst of 10-20 would be throttled by the
+ *   SHIPPING config too. That's a genuine event-day issue worth its own report,
+ *   independent of this pipeline test.
+ *
+ * Usage:
+ *   node driver.mjs                      # full run (100 guests / 1000 imgs / 15 min)
+ *   LT_GUESTS=5 LT_IMAGES=50 LT_WINDOW_SEC=60 node driver.mjs   # smoke
+ *
+ * Env knobs (all optional; defaults target the full run):
+ *   LT_BASE            http://localhost:3101   frontend/caddy base URL
+ *   LT_GUESTS          100                     number of virtual guests
+ *   LT_IMAGES          1000                    total uploads to perform
+ *   LT_WINDOW_SEC      900                     spread uploads over this window
+ *   LT_BURST_MIN/MAX   10 / 20                 images per burst
+ *   LT_BURST_CONC      3                       parallel uploads within one burst (phone-like)
+ *   LT_VIEWERS         20                      extra guests holding SSE + polling feed
+ *   LT_PHOTOS_DIR      /tmp/eventsnap-loadtest/photos
+ *   LT_TRUNCATE        1                       wipe event data before the run
+ *   LT_DRAIN_TIMEOUT_SEC 600                   max wait for compression backlog to drain
+ *   LT_APP_CONTAINER   e2e-app-1               docker container for CPU/mem sampling
+ *   LT_DB_CONTAINER    e2e-db-1                docker container for psql ground-truth
+ *   LT_ADMIN_PW        admin-test-pw
+ *   LT_KEEP_RATELIMITS 0                       set 1 to NOT disable rate limits
+ *   LT_OUT_DIR         ./results
+ */
+
+import { readFileSync, readdirSync, writeFileSync, mkdirSync, statSync } from 'node:fs';
+import { execFile } from 'node:child_process';
+import { promisify } from 'node:util';
+import { fileURLToPath } from 'node:url';
+import { dirname, join } from 'node:path';
+
+const execFileAsync = promisify(execFile);
+const __dirname = dirname(fileURLToPath(import.meta.url));
+
+// ── Config ──────────────────────────────────────────────────────────────────
+const cfg = {
+  base: process.env.LT_BASE ?? 'http://localhost:3101',
+  guests: int('LT_GUESTS', 100),
+  images: int('LT_IMAGES', 1000),
+  windowSec: int('LT_WINDOW_SEC', 900),
+  burstMin: int('LT_BURST_MIN', 10),
+  burstMax: int('LT_BURST_MAX', 20),
+  burstConc: int('LT_BURST_CONC', 3),
+  viewers: int('LT_VIEWERS', 20),
+  photosDir: process.env.LT_PHOTOS_DIR ?? '/tmp/eventsnap-loadtest/photos',
+  truncate: process.env.LT_TRUNCATE !== '0',
+  drainTimeoutSec: int('LT_DRAIN_TIMEOUT_SEC', 600),
+  appContainer: process.env.LT_APP_CONTAINER ?? 'e2e-app-1',
+  dbContainer: process.env.LT_DB_CONTAINER ?? 'e2e-db-1',
+  adminPw: process.env.LT_ADMIN_PW ?? 'admin-test-pw',
+  keepRateLimits: process.env.LT_KEEP_RATELIMITS === '1',
+  outDir: process.env.LT_OUT_DIR ?? join(__dirname, 'results'),
+};
+
+function int(name, def) {
+  const v = process.env[name];
+  return v === undefined ? def : parseInt(v, 10);
+}
+
+const API = `${cfg.base}/api/v1`;
+const now = () => Date.now();
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+const rand = (min, max) => min + Math.floor(Math.random() * (max - min + 1));
+const pick = (arr) => arr[Math.floor(Math.random() * arr.length)];
+
+// ── HTTP helpers ──────────────────────────────────────────────────────────────
+async function api(path, { method = 'GET', token, json, expect } = {}) {
+  const headers = {};
+  if (token) headers.Authorization = `Bearer ${token}`;
+  if (json !== undefined) headers['Content-Type'] = 'application/json';
+  const res = await fetch(`${API}${path}`, {
+    method,
+    headers,
+    body: json !== undefined ? JSON.stringify(json) : undefined,
+  });
+  let body;
+  if (res.status !== 204) {
+    const text = await res.text();
+    try {
+      body = text.length ? JSON.parse(text) : undefined;
+    } catch {
+      body = text;
+    }
+  }
+  if (expect && !expect.includes(res.status)) {
+    throw new Error(`${method} ${path} → ${res.status}: ${JSON.stringify(body)}`);
+  }
+  return { status: res.status, body };
+}
+
+const adminLogin = () =>
+  api('/admin/login', { method: 'POST', json: { password: cfg.adminPw }, expect: [200] }).then(
+    (r) => r.body.jwt
+  );
+
+const joinGuest = (name) =>
+  api('/join', { method: 'POST', json: { display_name: name }, expect: [201] }).then((r) => r.body);
+
+const patchConfig = (adminJwt, patch) =>
+  api('/admin/config', { method: 'PATCH', token: adminJwt, json: patch, expect: [204] });
+
+const getConfig = (adminJwt) => api('/admin/config', { token: adminJwt }).then((r) => r.body);
+
+const truncate = (adminJwt) =>
+  api('/admin/__truncate', { method: 'POST', token: adminJwt, expect: [204] });
+
+const CAPTIONS = [
+  'Was für ein magischer Tag 💍',
+  'Der erste Tanz 🕺',
+  'Prost! 🥂',
+  'Die Torte 🍰',
+  'Feuerwerk 🎆',
+  'Beste Freunde 💕',
+  'Was für eine Stimmung! 🎉',
+  'Details 🌸',
+  'Sonnenuntergang 🌅',
+  'Tanzfläche brennt 🔥',
+  null,
+  null,
+  null,
+];
+const TAGS = ['hochzeit', 'liebe', 'party', 'tanzen', 'natur', 'feier', 'freunde', 'dessert'];
+
+async function uploadPhoto(jwt, file, buf) {
+  const form = new FormData();
+  form.append('file', new Blob([buf], { type: 'image/jpeg' }), 'photo.jpg');
+  const cap = pick(CAPTIONS);
+  if (cap) form.append('caption', cap);
+  form.append('hashtags', `${pick(TAGS)},${pick(TAGS)}`);
+  const t0 = now();
+  const res = await fetch(`${API}/upload`, {
+    method: 'POST',
+    headers: { Authorization: `Bearer ${jwt}` },
+    body: form,
+  });
+  const t1 = now();
+  let id, errText;
+  if (res.status === 201) {
+    id = (await res.json()).id;
+  } else {
+    errText = (await res.text()).slice(0, 200);
+  }
+  return { status: res.status, id, ms: t1 - t0, endTs: t1, bytes: buf.length, errText };
+}
+
+// ── SSE client (auto-reconnecting) ────────────────────────────────────────────
+class SseClient {
+  constructor(jwt, label, onEvent) {
+    this.jwt = jwt;
+    this.label = label;
+    this.onEvent = onEvent;
+    this.stop = false;
+    this.reconnects = 0;
+    this.resyncs = 0;
+    this.controller = null;
+  }
+  start() {
+    this._loop();
+    return this;
+  }
+  async _loop() {
+    while (!this.stop) {
+      try {
+        const tkt = await api('/stream/ticket', { method: 'POST', token: this.jwt, expect: [200] });
+        this.controller = new AbortController();
+        const res = await fetch(`${API}/stream?ticket=${tkt.body.ticket}`, {
+          headers: { Accept: 'text/event-stream' },
+          signal: this.controller.signal,
+        });
+        if (!res.ok || !res.body) throw new Error(`stream ${res.status}`);
+        const reader = res.body.getReader();
+        const dec = new TextDecoder();
+        let buf = '';
+        while (!this.stop) {
+          const { value, done } = await reader.read();
+          if (done) break;
+          buf += dec.decode(value, { stream: true });
+          let idx;
+          while ((idx = buf.indexOf('\n\n')) !== -1) {
+            const frame = buf.slice(0, idx);
+            buf = buf.slice(idx + 2);
+            this._parseFrame(frame);
+          }
+        }
+      } catch (e) {
+        if (this.stop) return;
+        this.reconnects++;
+        await sleep(500 + Math.random() * 500);
+      }
+    }
+  }
+  _parseFrame(frame) {
+    let event = 'message';
+    let data = '';
+    for (const line of frame.split('\n')) {
+      if (line.startsWith('event:')) event = line.slice(6).trim();
+      else if (line.startsWith('data:')) data += line.slice(5).trim();
+    }
+    if (event === 'resync') this.resyncs++;
+    if (!data) return;
+    let payload;
+    try {
+      payload = JSON.parse(data);
+    } catch {
+      payload = data;
+    }
+    this.onEvent(event, payload, this.label);
+  }
+  close() {
+    this.stop = true;
+    try {
+      this.controller?.abort();
+    } catch {
+      /* noop */
+    }
+  }
+}
+
+// ── Resource sampler (docker stats + psql ground truth) ───────────────────────
+async function sampleResources() {
+  const out = { ts: now() };
+  try {
+    const { stdout } = await execFileAsync('docker', [
+      'stats',
+      '--no-stream',
+      '--format',
+      '{{.Name}}|{{.CPUPerc}}|{{.MemUsage}}',
+      cfg.appContainer,
+      cfg.dbContainer,
+    ]);
+    out.docker = stdout.trim();
+  } catch (e) {
+    out.dockerErr = String(e).slice(0, 120);
+  }
+  try {
+    const { stdout } = await psql(
+      `select count(*) from pg_stat_activity where datname='eventsnap_test'`
+    );
+    out.dbConns = parseInt(stdout.trim(), 10);
+  } catch {
+    /* ignore */
+  }
+  return out;
+}
+
+function psql(sql) {
+  return execFileAsync('docker', [
+    'exec',
+    cfg.dbContainer,
+    'psql',
+    '-U',
+    'eventsnap_test',
+    '-d',
+    'eventsnap_test',
+    '-tAc',
+    sql,
+  ]);
+}
+
+async function compressionCounts() {
+  try {
+    const { stdout } = await psql(
+      `select compression_status, count(*) from upload where deleted_at is null group by 1`
+    );
+    const map = {};
+    for (const line of stdout.trim().split('\n')) {
+      if (!line) continue;
+      const [status, n] = line.split('|');
+      map[status] = parseInt(n, 10);
+    }
+    return map;
+  } catch (e) {
+    return { error: String(e).slice(0, 120) };
+  }
+}
+
+// ── Stats helpers ─────────────────────────────────────────────────────────────
+function pct(sorted, p) {
+  if (!sorted.length) return null;
+  const i = Math.min(sorted.length - 1, Math.floor((p / 100) * sorted.length));
+  return sorted[i];
+}
+function summarize(nums) {
+  if (!nums.length) return null;
+  const s = [...nums].sort((a, b) => a - b);
+  const sum = s.reduce((a, b) => a + b, 0);
+  return {
+    n: s.length,
+    min: s[0],
+    max: s[s.length - 1],
+    mean: Math.round(sum / s.length),
+    p50: pct(s, 50),
+    p95: pct(s, 95),
+    p99: pct(s, 99),
+  };
+}
+
+// ── Image pool ────────────────────────────────────────────────────────────────
+function loadPool() {
+  let files;
+  try {
+    files = readdirSync(cfg.photosDir).filter((f) => f.endsWith('.jpg'));
+  } catch {
+    files = [];
+  }
+  if (!files.length) {
+    console.error(
+      `\n✗ No images in ${cfg.photosDir}. Run first:\n` +
+        `    LT_PHOTOS_DIR=${cfg.photosDir} python3 ${join(__dirname, 'gen-images.py')}\n`
+    );
+    process.exit(1);
+  }
+  const pool = files.map((f) => {
+    const p = join(cfg.photosDir, f);
+    return { buf: readFileSync(p), size: statSync(p).size, name: f };
+  });
+  return pool;
+}
+
+// ── Burst schedule ────────────────────────────────────────────────────────────
+// Build bursts until we reach the image target, assign each to a random guest at
+// a random time in the window. Naturally gives some guests several bursts and
+// some none — like a real event. Guests all join before their first burst.
+function buildSchedule() {
+  const bursts = [];
+  let remaining = cfg.images;
+  while (remaining > 0) {
+    const size = Math.min(remaining, rand(cfg.burstMin, cfg.burstMax));
+    bursts.push({
+      guest: rand(0, cfg.guests - 1),
+      atMs: Math.floor(Math.random() * cfg.windowSec * 1000),
+      size,
+    });
+    remaining -= size;
+  }
+  bursts.sort((a, b) => a.atMs - b.atMs);
+  return bursts;
+}
+
+// ── Main ──────────────────────────────────────────────────────────────────────
+async function main() {
+  console.log('━'.repeat(72));
+  console.log('EventSnap load driver');
+  console.log(
+    `  target: ${cfg.guests} guests, ${cfg.images} images, ` +
+      `bursts ${cfg.burstMin}-${cfg.burstMax}, window ${cfg.windowSec}s, ${cfg.viewers} viewers`
+  );
+  console.log(`  base: ${cfg.base}`);
+  console.log('━'.repeat(72));
+
+  const pool = loadPool();
+  const avgMb = pool.reduce((a, p) => a + p.size, 0) / pool.length / 1e6;
+  console.log(
+    `[pool] ${pool.length} images, avg ${avgMb.toFixed(2)} MB, ` +
+      `projected originals ~${((avgMb * cfg.images) / 1000).toFixed(1)} GB`
+  );
+
+  // Preflight: disk headroom
+  try {
+    const { stdout } = await execFileAsync('df', ['-BG', '--output=avail', '/']);
+    console.log(`[preflight] disk avail:${stdout.trim().split('\n').pop().trim()}`);
+  } catch {
+    /* ignore */
+  }
+
+  // Admin: reset + config
+  const admin = await adminLogin();
+  const cfgBefore = await getConfig(admin);
+  if (cfg.truncate) {
+    console.log('[setup] truncating event data…');
+    await truncate(admin);
+  }
+  const admin2 = await adminLogin();
+  if (!cfg.keepRateLimits) {
+    console.log('[setup] disabling rate limits (methodology: isolate pipeline, not limiter)');
+    await patchConfig(admin2, {
+      rate_limits_enabled: 'false',
+      upload_rate_enabled: 'false',
+      feed_rate_enabled: 'false',
+      join_rate_enabled: 'false',
+      recover_rate_enabled: 'false',
+    });
+  }
+  console.log(
+    `[setup] compression concurrency / quotas left at SHIPPING defaults ` +
+      `(compression_worker_concurrency is a boot env var, not runtime)`
+  );
+
+  // Metrics stores
+  const uploads = []; // {status, ms, endTs, bytes, id, guest}
+  const processedAt = new Map(); // upload_id -> ts of upload-processed
+  const uploadEndTs = new Map(); // upload_id -> endTs
+  const errorEvents = []; // upload-error payloads
+  const resources = [];
+  let newUploadEvents = 0;
+
+  // Join guests (staggered, small concurrency)
+  console.log(`[join] joining ${cfg.guests} guests…`);
+  const accounts = new Array(cfg.guests);
+  const joinConc = 10;
+  for (let i = 0; i < cfg.guests; i += joinConc) {
+    await Promise.all(
+      Array.from({ length: Math.min(joinConc, cfg.guests - i) }, (_, k) =>
+        joinGuest(`LoadGuest ${i + k}`).then((a) => (accounts[i + k] = a))
+      )
+    );
+  }
+  console.log('[join] done');
+
+  // Live connections: 1 diashow + N viewers
+  const onEvent = (event, payload) => {
+    if (event === 'new-upload') newUploadEvents++;
+    else if (event === 'upload-processed' && payload?.upload_id) {
+      if (!processedAt.has(payload.upload_id)) processedAt.set(payload.upload_id, now());
+    } else if (event === 'upload-error' && payload?.upload_id) {
+      errorEvents.push(payload);
+    }
+  };
+  const sseClients = [];
+  sseClients.push(new SseClient(accounts[0].jwt, 'diashow', onEvent).start());
+  for (let i = 0; i < Math.min(cfg.viewers, cfg.guests); i++) {
+    sseClients.push(new SseClient(accounts[i].jwt, `viewer${i}`, onEvent).start());
+  }
+  console.log(`[sse] opened ${sseClients.length} live connections (1 diashow + viewers)`);
+
+  // Viewers also poll the feed periodically (viewing load)
+  let feedPolls = 0;
+  const feedPoller = setInterval(async () => {
+    const g = accounts[rand(0, Math.min(cfg.viewers, cfg.guests) - 1)];
+    try {
+      await api('/feed', { token: g.jwt });
+      feedPolls++;
+    } catch {
+      /* ignore */
+    }
+  }, 1500);
+
+  // Resource sampler
+  const sampler = setInterval(async () => resources.push(await sampleResources()), 5000);
+  resources.push(await sampleResources());
+
+  // Run the burst schedule
+  const schedule = buildSchedule();
+  console.log(
+    `[run] ${schedule.length} bursts scheduled over ${cfg.windowSec}s ` +
+      `(≈${(cfg.images / (cfg.windowSec / 60)).toFixed(0)} img/min avg). Starting…`
+  );
+  const startTs = now();
+  let done = 0;
+
+  const runBurst = async (burst) => {
+    const jwt = accounts[burst.guest].jwt;
+    const items = Array.from({ length: burst.size }, () => pick(pool));
+    // upload with phone-like small concurrency inside the burst
+    for (let i = 0; i < items.length; i += cfg.burstConc) {
+      const chunk = items.slice(i, i + cfg.burstConc);
+      const results = await Promise.all(chunk.map((it) => uploadPhoto(jwt, it.name, it.buf)));
+      for (const r of results) {
+        uploads.push({ ...r, guest: burst.guest });
+        if (r.id) uploadEndTs.set(r.id, r.endTs);
+        done++;
+      }
+    }
+  };
+
+  const timers = [];
+  const burstPromises = [];
+  for (const burst of schedule) {
+    timers.push(
+      setTimeout(() => {
+        burstPromises.push(runBurst(burst));
+      }, burst.atMs)
+    );
+  }
+
+  // progress ticker
+  const ticker = setInterval(() => {
+    const elapsed = ((now() - startTs) / 1000).toFixed(0);
+    const ok = uploads.filter((u) => u.status === 201).length;
+    console.log(
+      `[t+${elapsed}s] uploads ${done}/${cfg.images} (ok ${ok}), ` +
+        `processed ${processedAt.size}, new-upload evts ${newUploadEvents}, ` +
+        `feedPolls ${feedPolls}`
+    );
+  }, 10000);
+
+  // wait for the window to elapse, then for all scheduled bursts to finish
+  await sleep(cfg.windowSec * 1000 + 500);
+  await Promise.all(burstPromises);
+  clearInterval(ticker);
+  console.log(
+    `[run] all bursts issued. uploaded ${done}, ok ${uploads.filter((u) => u.status === 201).length}`
+  );
+
+  // Drain: wait for compression backlog to clear (SSE processed ⊇ successful ids)
+  console.log('[drain] waiting for compression backlog to clear…');
+  const drainStart = now();
+  const successIds = new Set(uploads.filter((u) => u.id).map((u) => u.id));
+  let lastLog = 0;
+  let drainReason = 'timeout';
+  while (now() - drainStart < cfg.drainTimeoutSec * 1000) {
+    // SSE view (what the diashow actually "sees")
+    const pendingSse = [...successIds].filter((id) => !processedAt.has(id)).length;
+    if (pendingSse === 0) {
+      console.log('[drain] backlog cleared (all upload-processed events received)');
+      drainReason = 'sse-complete';
+      break;
+    }
+    // DB ground truth — authoritative even if an SSE reconnect dropped events
+    const counts = await compressionCounts();
+    const dbPending = Object.entries(counts)
+      .filter(([s]) => s !== 'done' && s !== 'error')
+      .reduce((a, [, n]) => a + n, 0);
+    if (!counts.error && dbPending === 0) {
+      console.log(`[drain] backlog cleared per DB (db status: ${JSON.stringify(counts)})`);
+      drainReason = 'db-complete';
+      break;
+    }
+    if (now() - lastLog > 5000) {
+      console.log(
+        `[drain] pending(sse) ${pendingSse}, pending(db) ${dbPending} — db: ${JSON.stringify(counts)}`
+      );
+      lastLog = now();
+    }
+    await sleep(1000);
+  }
+  const drainMs = now() - drainStart;
+
+  // Stop background work
+  clearInterval(sampler);
+  clearInterval(feedPoller);
+  timers.forEach(clearTimeout);
+  resources.push(await sampleResources());
+  const finalCounts = await compressionCounts();
+  await sleep(200);
+  sseClients.forEach((c) => c.close());
+
+  // ── Build report ────────────────────────────────────────────────────────────
+  const byStatus = {};
+  for (const u of uploads) byStatus[u.status] = (byStatus[u.status] ?? 0) + 1;
+  const okUploads = uploads.filter((u) => u.status === 201);
+  const uploadLatency = summarize(okUploads.map((u) => u.ms));
+  const pipelineLatency = summarize(
+    [...processedAt.entries()]
+      .filter(([id]) => uploadEndTs.has(id))
+      .map(([id, ts]) => ts - uploadEndTs.get(id))
+  );
+  const totalReconnects = sseClients.reduce((a, c) => a + c.reconnects, 0);
+  const totalResyncs = sseClients.reduce((a, c) => a + c.resyncs, 0);
+
+  const report = {
+    config: cfg,
+    startedAt: new Date(startTs).toISOString(),
+    durationSec: Math.round((now() - startTs) / 1000),
+    totals: {
+      uploadsAttempted: uploads.length,
+      uploadsOk: okUploads.length,
+      byStatus,
+      newUploadEvents,
+      processedEvents: processedAt.size,
+      uploadErrorEvents: errorEvents.length,
+      feedPolls,
+    },
+    uploadLatencyMs: uploadLatency,
+    pipelineLatencyMs: pipelineLatency,
+    drain: {
+      ms: drainMs,
+      cleared: drainReason !== 'timeout',
+      reason: drainReason,
+      ssePending: [...successIds].filter((id) => !processedAt.has(id)).length,
+      finalDbCounts: finalCounts,
+    },
+    sse: {
+      connections: sseClients.length,
+      reconnects: totalReconnects,
+      resyncs: totalResyncs,
+    },
+    resources,
+    rateLimitsDisabled: !cfg.keepRateLimits,
+    configBefore: cfgBefore,
+  };
+
+  mkdirSync(cfg.outDir, { recursive: true });
+  const stamp = new Date(startTs).toISOString().replace(/[:.]/g, '-');
+  const outPath = join(cfg.outDir, `run-${stamp}.json`);
+  writeFileSync(outPath, JSON.stringify(report, null, 2));
+
+  // ── Print verdict ─────────────────────────────────────────────────────────
+  console.log('\n' + '━'.repeat(72));
+  console.log('RESULTS');
+  console.log('━'.repeat(72));
+  console.log(
+    `uploads: ${okUploads.length}/${uploads.length} ok — byStatus ${JSON.stringify(byStatus)}`
+  );
+  console.log(`upload latency ms: ${JSON.stringify(uploadLatency)}`);
+  console.log(`pipeline latency ms (upload→preview ready): ${JSON.stringify(pipelineLatency)}`);
+  console.log(`backlog drain: ${(drainMs / 1000).toFixed(1)}s, cleared=${report.drain.cleared}`);
+  console.log(`final db compression status: ${JSON.stringify(finalCounts)}`);
+  console.log(
+    `sse: ${sseClients.length} conns, ${totalReconnects} reconnects, ${totalResyncs} resyncs`
+  );
+  console.log(`\nfull report → ${outPath}`);
+
+  // Heuristic pass/fail flags (validate shipping config)
+  const flags = [];
+  const err5xx = Object.entries(byStatus)
+    .filter(([s]) => +s >= 500)
+    .reduce((a, [, n]) => a + n, 0);
+  if (err5xx > 0) flags.push(`✗ ${err5xx} server errors (5xx)`);
+  if (byStatus['507']) flags.push(`✗ ${byStatus['507']} quota rejections (507)`);
+  if (byStatus['413']) flags.push(`⚠ ${byStatus['413']} too-large (413)`);
+  if (byStatus['429'])
+    flags.push(`⚠ ${byStatus['429']} rate-limited (429) — unexpected with limits off`);
+  if (!report.drain.cleared) flags.push(`✗ backlog did NOT drain within ${cfg.drainTimeoutSec}s`);
+  if (totalResyncs > sseClients.length) flags.push(`⚠ ${totalResyncs} SSE resyncs (consumer lag)`);
+  if (pipelineLatency && pipelineLatency.p95 > 60000)
+    flags.push(`⚠ pipeline p95 ${(pipelineLatency.p95 / 1000).toFixed(0)}s (diashow lags >1min)`);
+  console.log('\nflags:');
+  if (flags.length) flags.forEach((f) => console.log('  ' + f));
+  else console.log('  ✓ no red flags — default config handled the load');
+  console.log('━'.repeat(72));
+}
+
+main().catch((e) => {
+  console.error('\n✗ driver failed:', e);
+  process.exit(1);
+});

e2e/loadtest/gen-images.py

@@ -0,0 +1,146 @@
+#!/usr/bin/env python3
+"""
+Generate a pool of realistic phone-sized JPEGs for the EventSnap load test.
+
+The stress test uploads ~1000 images, but they don't need to be 1000 unique
+files — real load comes from realistic *byte size* and *decode cost*, which
+drive bandwidth, the compression/preview pipeline (decode + 800x800 resize),
+disk usage and the dynamic storage quota. So we generate a modest POOL of
+distinct, high-entropy images (~2-4 MB, 12 MP, like a phone camera) and the
+driver reuses them at random across the 1000 uploads.
+
+High entropy matters: a flat gradient compresses to almost nothing and would
+under-stress both the network and the JPEG decoder. We blend random noise over
+a colorful gradient + big shapes so the files land in a realistic size band,
+then tune JPEG quality per-image to hit the target size.
+
+Output: $LT_PHOTOS_DIR (default /tmp/eventsnap-loadtest/photos)
+Usage:  python3 gen-images.py [COUNT]     (default 40)
+"""
+
+import os
+import sys
+import math
+import random
+from PIL import Image, ImageDraw, ImageFont
+
+OUT_DIR = os.environ.get("LT_PHOTOS_DIR", "/tmp/eventsnap-loadtest/photos")
+COUNT = int(sys.argv[1]) if len(sys.argv) > 1 else 40
+
+# Target JPEG size band (bytes). Typical modern phone photo.
+TARGET_MIN = 2_000_000
+TARGET_MAX = 4_500_000
+
+# 12 MP-ish, both orientations (phones shoot portrait and landscape).
+SIZES = [(4032, 3024), (3024, 4032)]
+
+PALETTES = [
+    [(250, 245, 235), (212, 175, 55), (120, 90, 30)],   # champagne / gold
+    [(245, 244, 242), (190, 190, 198), (90, 92, 100)],   # silver / pearl
+    [(255, 250, 240), (240, 200, 160), (170, 110, 70)],  # warm sunset
+    [(235, 240, 248), (140, 170, 210), (40, 70, 120)],   # cool blue hour
+    [(248, 240, 245), (210, 150, 180), (110, 50, 90)],   # rose dusk
+    [(240, 248, 242), (150, 200, 170), (40, 110, 80)],   # garden green
+]
+
+
+def lerp(a, b, t):
+    return tuple(int(a[i] + (b[i] - a[i]) * t) for i in range(3))
+
+
+def gradient(w, h, palette, rng):
+    """Diagonal 3-stop gradient base."""
+    base = Image.new("RGB", (w, h))
+    px = base.load()
+    ang = rng.uniform(0, math.pi)
+    dx, dy = math.cos(ang), math.sin(ang)
+    # precompute per-column/row projection for speed
+    maxproj = abs(dx) * w + abs(dy) * h
+    for y in range(h):
+        for x in range(0, w, 4):  # step 4 then fill — good enough, much faster
+            t = (dx * x + dy * y) / maxproj
+            t = min(1.0, max(0.0, t + rng.uniform(-0.02, 0.02)))
+            if t < 0.5:
+                c = lerp(palette[0], palette[1], t * 2)
+            else:
+                c = lerp(palette[1], palette[2], (t - 0.5) * 2)
+            for k in range(4):
+                if x + k < w:
+                    px[x + k, y] = c
+    return base
+
+
+def add_shapes(img, rng):
+    d = ImageDraw.Draw(img, "RGBA")
+    w, h = img.size
+    for _ in range(rng.randint(6, 14)):
+        x0 = rng.randint(-w // 5, w)
+        y0 = rng.randint(-h // 5, h)
+        r = rng.randint(w // 12, w // 3)
+        col = (rng.randint(0, 255), rng.randint(0, 255), rng.randint(0, 255), rng.randint(20, 90))
+        if rng.random() < 0.5:
+            d.ellipse([x0, y0, x0 + r, y0 + r], fill=col)
+        else:
+            d.rectangle([x0, y0, x0 + r, y0 + int(r * rng.uniform(0.4, 1.6))], fill=col)
+    return img
+
+
+def noisy(w, h, rng):
+    """Full-resolution RGB noise from urandom — maximum entropy."""
+    return Image.frombytes("RGB", (w, h), os.urandom(w * h * 3))
+
+
+def label(img, idx, rng):
+    d = ImageDraw.Draw(img)
+    txt = f"EventSnap load #{idx:03d}"
+    try:
+        font = ImageFont.load_default(size=64)
+    except TypeError:
+        font = ImageFont.load_default()
+    d.text((60, 60), txt, fill=(255, 255, 255), font=font)
+    d.text((62, 62), txt, fill=(0, 0, 0), font=font)  # cheap shadow offset
+
+
+def encode_to_band(img, path, rng):
+    """Try qualities high→low until the file lands under TARGET_MAX; keep the
+    first that also clears TARGET_MIN if possible."""
+    best = None
+    for q in (92, 88, 84, 80, 76, 72):
+        img.save(path, "JPEG", quality=q, optimize=False)
+        size = os.path.getsize(path)
+        best = (q, size)
+        if size <= TARGET_MAX:
+            if size >= TARGET_MIN:
+                return q, size
+            # under the band — noise alpha likely too low; accept anyway at high q
+            return q, size
+    return best  # even q72 too big; accept the smallest we made
+
+
+def main():
+    os.makedirs(OUT_DIR, exist_ok=True)
+    rng = random.Random(20260718)  # deterministic pool
+    total_bytes = 0
+    print(f"[gen] writing {COUNT} images to {OUT_DIR}")
+    for i in range(COUNT):
+        w, h = rng.choice(SIZES)
+        palette = rng.choice(PALETTES)
+        base = gradient(w, h, palette, rng)
+        base = add_shapes(base, rng)
+        # blend noise to inject entropy -> realistic JPEG size
+        alpha = rng.uniform(0.28, 0.42)
+        base = Image.blend(base, noisy(w, h, rng), alpha)
+        label(base, i, rng)
+        path = os.path.join(OUT_DIR, f"photo_{i:03d}.jpg")
+        q, size = encode_to_band(base, path, rng)
+        total_bytes += size
+        print(f"  photo_{i:03d}.jpg  {w}x{h}  q{q}  {size/1_000_000:.2f} MB")
+    avg = total_bytes / COUNT
+    print(f"[gen] done. {COUNT} images, avg {avg/1_000_000:.2f} MB, "
+          f"pool total {total_bytes/1_000_000:.1f} MB")
+    print(f"[gen] projected for 1000 uploads (originals only): "
+          f"~{avg*1000/1_000_000_000:.1f} GB")
+
+
+if __name__ == "__main__":
+    main()

e2e/page-objects/export-page.ts

@@ -37,12 +37,19 @@ export class ExportPage {
   /**
    * The "Download" button inside the card whose heading is `heading`.
    *
-   * Scoped to the card element (`div.rounded-xl`) rather than "any div containing the
-   * heading" — the latter also matches the page wrapper, which contains BOTH cards' buttons.
+   * Scoped to the card element rather than "any div containing the heading" — the latter
+   * also matches the page wrapper, which contains BOTH cards' buttons.
+   *
+   * The scope class is `div.card` (see the ZIP/HTML cards in
+   * frontend/src/routes/export/+page.svelte). It was previously `div.rounded-xl`, which
+   * matched NOTHING: `.card` is a Tailwind `@apply` component class
+   * (frontend/src/lib/styles/components.css) so the DOM only ever carries `class="card p-5"`
+   * — and the utility it applies is `rounded-2xl` anyway. Both card-scoped locators were
+   * therefore dead, which is why the "shows enabled download buttons" test was red.
    */
   private cardButton(heading: string): Locator {
     return this.page
-      .locator('div.rounded-xl')
+      .locator('div.card')
       .filter({ has: this.page.getByRole('heading', { name: heading, exact: true }) })
       .getByRole('button', { name: 'Download', exact: true });
   }

e2e/playwright.config.ts

@@ -146,8 +146,18 @@ export default defineConfig({
       // that on `@smoke` — which exists on exactly two specs — meant the entire iOS guarantee was
       // one happy path and one join test. Every other UA here is a secondary browser and a smoke
       // check is proportionate; WebKit is not. Give it the core journeys the guest actually walks:
-      // join/recover, upload, and browse the feed.
-      testMatch: ['**/__smoke/**', '**/01-auth/**', '**/02-upload/**', '**/03-feed/**'],
+      // join/recover, upload, browse the feed — and take the keepsake home.
+      //
+      // 06-export is here because WebKit is the ONLY engine that enforces X-Frame-Options on the
+      // hidden download iframe. Excluding it is what let a site-wide `XFO: DENY` ship a keepsake
+      // download that silently did nothing on iOS. See 06-export/download-iframe.spec.ts.
+      testMatch: [
+        '**/__smoke/**',
+        '**/01-auth/**',
+        '**/02-upload/**',
+        '**/03-feed/**',
+        '**/06-export/**',
+      ],
     },
     {
       name: 'firefox-android',

e2e/shots.mjs

@@ -0,0 +1,255 @@
+// One-off: seed a realistic feed, then capture mobile screenshots (light + dark).
+// Run from the e2e dir so @playwright/test and pg resolve.
+import { chromium, devices } from '@playwright/test';
+import { Client } from 'pg';
+import { readFileSync, mkdirSync } from 'node:fs';
+
+const BASE = 'http://localhost:3101';
+const PHOTOS = '/tmp/eventsnap-shots/photos';
+const OUT = '/tmp/eventsnap-shots';
+mkdirSync(OUT, { recursive: true });
+
+const api = (path, opts = {}) =>
+  fetch(`${BASE}/api/v1${path}`, opts).then(async (r) => ({
+    status: r.status,
+    body: await r.text().then((t) => {
+      try {
+        return JSON.parse(t);
+      } catch {
+        return t;
+      }
+    }),
+  }));
+
+const authHeaders = (jwt, json = true) => ({
+  Authorization: `Bearer ${jwt}`,
+  ...(json ? { 'Content-Type': 'application/json' } : {}),
+});
+
+async function adminLogin() {
+  const r = await api('/admin/login', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ password: 'admin-test-pw' }),
+  });
+  return r.body.jwt;
+}
+async function joinGuest(name) {
+  const r = await api('/join', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ display_name: name }),
+  });
+  if (r.status !== 201)
+    throw new Error('join failed ' + name + ' ' + r.status + ' ' + JSON.stringify(r.body));
+  return r.body; // {jwt,pin,user_id}
+}
+async function upload(jwt, file, caption, hashtags) {
+  const form = new FormData();
+  form.append('file', new Blob([readFileSync(file)], { type: 'image/jpeg' }), 'photo.jpg');
+  if (caption) form.append('caption', caption);
+  if (hashtags) form.append('hashtags', hashtags);
+  const r = await fetch(`${BASE}/api/v1/upload`, {
+    method: 'POST',
+    headers: authHeaders(jwt, false),
+    body: form,
+  });
+  if (r.status !== 201) throw new Error('upload failed ' + r.status + ' ' + (await r.text()));
+  return (await r.json()).id;
+}
+async function like(jwt, id) {
+  await fetch(`${BASE}/api/v1/upload/${id}/like`, { method: 'POST', headers: authHeaders(jwt) });
+}
+async function comment(jwt, id, body) {
+  await fetch(`${BASE}/api/v1/upload/${id}/comments`, {
+    method: 'POST',
+    headers: authHeaders(jwt),
+    body: JSON.stringify({ body }),
+  });
+}
+
+const pg = () =>
+  new Client({
+    host: 'localhost',
+    port: 55432,
+    user: 'eventsnap_test',
+    password: 'eventsnap_test',
+    database: 'eventsnap_test',
+  });
+
+async function truncate(adminJwt) {
+  await fetch(`${BASE}/api/v1/admin/__truncate`, {
+    method: 'POST',
+    headers: authHeaders(adminJwt),
+  });
+}
+async function patchConfig(adminJwt, patch) {
+  await fetch(`${BASE}/api/v1/admin/config`, {
+    method: 'PATCH',
+    headers: authHeaders(adminJwt),
+    body: JSON.stringify(patch),
+  });
+}
+
+// ---- SEED ----
+console.log('[seed] admin login + reset');
+let admin = await adminLogin();
+await truncate(admin);
+admin = await adminLogin();
+await patchConfig(admin, {
+  rate_limits_enabled: 'false',
+  upload_rate_enabled: 'false',
+  feed_rate_enabled: 'false',
+  export_rate_enabled: 'false',
+  join_rate_enabled: 'false',
+  quota_enabled: 'false',
+  storage_quota_enabled: 'false',
+  upload_count_quota_enabled: 'false',
+});
+
+const guests = [
+  'Anna Bauer',
+  'Lukas Weber',
+  'Mia Schulz',
+  'Jonas Fischer',
+  'Emma Wagner',
+  'Ben Hoffmann',
+  'Sophie Klein',
+  'Paul Richter',
+];
+const accounts = {};
+for (const g of guests) accounts[g] = await joinGuest(g);
+console.log('[seed] joined', guests.length, 'guests');
+
+const posts = [
+  ['Anna Bauer', 'photo_00.jpg', 'Was für ein magischer Tag 💍✨', 'hochzeit,liebe'],
+  ['Lukas Weber', 'photo_01.jpg', 'Der erste Tanz 🕺💃', 'party,tanzen'],
+  ['Mia Schulz', 'photo_02.jpg', 'Sonnenuntergang am See 🌅', 'natur,abend'],
+  ['Jonas Fischer', 'photo_03.jpg', 'Prost auf das Brautpaar! 🥂', 'feier,freunde'],
+  ['Emma Wagner', 'photo_04.jpg', 'Die Torte war ein Traum 🍰', 'dessert,liebe'],
+  ['Ben Hoffmann', 'photo_05.jpg', 'Feuerwerk zum Abschluss 🎆', 'party,abend'],
+  ['Sophie Klein', 'photo_06.jpg', 'Beste Freunde für immer 💕', 'freunde,feier'],
+  ['Paul Richter', 'photo_07.jpg', 'Was für eine Stimmung! 🎉', 'party'],
+  ['Anna Bauer', 'photo_08.jpg', 'Details, die zählen 🌸', 'hochzeit'],
+  ['Mia Schulz', 'photo_09.jpg', 'Tanzfläche brennt 🔥', 'tanzen,party'],
+];
+const ids = [];
+for (const [who, f, cap, tags] of posts) {
+  const id = await upload(accounts[who].jwt, `${PHOTOS}/${f}`, cap, tags);
+  ids.push(id);
+}
+console.log('[seed] uploaded', ids.length, 'photos');
+
+// Likes: distribute varied counts
+const likeMatrix = [7, 3, 12, 5, 9, 4, 6, 2, 8, 5];
+for (let i = 0; i < ids.length; i++) {
+  const n = Math.min(likeMatrix[i], guests.length);
+  for (let j = 0; j < n; j++) await like(accounts[guests[j]].jwt, ids[i]);
+}
+// Comments on a few
+await comment(accounts['Lukas Weber'].jwt, ids[0], 'Wunderschön! 😍');
+await comment(accounts['Mia Schulz'].jwt, ids[0], 'Der Moment war perfekt.');
+await comment(accounts['Anna Bauer'].jwt, ids[2], 'Traumhaft 🌅');
+await comment(accounts['Ben Hoffmann'].jwt, ids[1], 'Was ein Abend!');
+console.log('[seed] likes + comments done');
+
+// Make one guest a host so /host renders populated
+await fetch(`${BASE}/api/v1/host/users/${accounts['Anna Bauer'].user_id}/role`, {
+  method: 'PATCH',
+  headers: authHeaders(admin),
+  body: JSON.stringify({ role: 'host' }),
+});
+
+// Wait for compression to finish so previews render
+const c = pg();
+await c.connect();
+for (let t = 0; t < 40; t++) {
+  const r = await c.query(
+    `SELECT COUNT(*)::int AS n FROM upload WHERE compression_status <> 'done' AND deleted_at IS NULL`
+  );
+  if (r.rows[0].n === 0) {
+    console.log('[seed] compression done');
+    break;
+  }
+  await new Promise((res) => setTimeout(res, 500));
+}
+await c.end();
+
+// ---- SCREENSHOTS ----
+const device = devices['Pixel 7'];
+const anna = accounts['Anna Bauer']; // host
+const shot = async (label, theme, who, route, prep) => {
+  const ctx = await browser.newContext({ ...device });
+  const page = await ctx.newPage();
+  // Seed localStorage on the origin
+  await page.goto(`${BASE}/join`, { waitUntil: 'domcontentloaded' });
+  await page.evaluate(
+    ({ jwt, pin, uid, name, theme, mode }) => {
+      localStorage.setItem('eventsnap_theme', theme);
+      localStorage.setItem('eventsnap_data_mode', mode);
+      if (jwt) {
+        localStorage.setItem('eventsnap_jwt', jwt);
+        localStorage.setItem('eventsnap_pin', pin);
+        localStorage.setItem('eventsnap_user_id', uid);
+        localStorage.setItem('eventsnap_display_name', name);
+      }
+      localStorage.setItem('eventsnap_guide_seen', '1');
+    },
+    { jwt: who?.jwt, pin: who?.pin, uid: who?.user_id, name: who?.name, theme, mode: 'saver' }
+  );
+  await page.goto(`${BASE}${route}`, { waitUntil: 'domcontentloaded' });
+  await page.waitForTimeout(1200);
+  if (prep) await prep(page);
+  await page.waitForTimeout(600);
+  await page.screenshot({ path: `${OUT}/${label}-${theme}.png`, fullPage: false });
+  await ctx.close();
+  console.log('[shot]', label, theme);
+};
+
+const browser = await chromium.launch();
+const hostWho = { ...anna, name: 'Anna Bauer' };
+const adminWho = { jwt: admin, pin: '', user_id: '', name: 'Admin' };
+
+for (const theme of ['light', 'dark']) {
+  await shot('01-join', theme, null, '/join');
+  await shot('02-feed-list', theme, hostWho, '/feed');
+  await shot('03-feed-grid', theme, hostWho, '/feed', async (p) => {
+    await p
+      .getByLabel('Rasteransicht')
+      .click()
+      .catch(() => {});
+  });
+  await shot('04-lightbox', theme, hostWho, '/feed', async (p) => {
+    await p
+      .locator('img')
+      .first()
+      .click()
+      .catch(() => {});
+    await p.waitForTimeout(500);
+  });
+  await shot('05-account', theme, hostWho, '/account');
+  await shot('06-host', theme, hostWho, '/host');
+  await shot('07-admin', theme, adminWho, '/admin');
+  await shot('08-upload', theme, hostWho, '/upload');
+  await shot('09-diashow', theme, hostWho, '/diashow');
+}
+// Onboarding: fresh guest, guide not seen
+{
+  const ctx = await browser.newContext({ ...device });
+  const page = await ctx.newPage();
+  await page.goto(`${BASE}/join`, { waitUntil: 'domcontentloaded' });
+  await page.evaluate((w) => {
+    localStorage.setItem('eventsnap_theme', 'light');
+    localStorage.setItem('eventsnap_jwt', w.jwt);
+    localStorage.setItem('eventsnap_pin', w.pin);
+    localStorage.setItem('eventsnap_user_id', w.user_id);
+    localStorage.setItem('eventsnap_display_name', 'Emma Wagner');
+  }, accounts['Emma Wagner']);
+  await page.goto(`${BASE}/feed`, { waitUntil: 'domcontentloaded' });
+  await page.waitForTimeout(1500);
+  await page.screenshot({ path: `${OUT}/10-onboarding-light.png` });
+  await ctx.close();
+  console.log('[shot] onboarding');
+}
+await browser.close();
+console.log('DONE');

e2e/specs/01-auth/join.spec.ts

@@ -13,7 +13,11 @@ test.describe('Auth — join flow', () => {
     const join = new JoinPage(page);
     await join.goto();
 
-    await expect(page.getByRole('heading', { name: 'Willkommen!' })).toBeVisible();
+    // The join form's landing state. There is no "Willkommen!" heading — the wedding
+    // redesign (f243bfe) split it into a "Willkommen bei" lead-in plus the event name as
+    // the <h1>, and this assertion was never updated, so it had been failing since.
+    // Anchor on the testid the markup provides rather than on copy.
+    await expect(page.getByTestId('join-event-name')).toBeVisible();
 
     const { pin } = await join.joinAs('Alice');
     expect(pin).toMatch(/^\d{4}$/);

e2e/specs/01-auth/rate-limit-shared-nat.spec.ts

@@ -0,0 +1,206 @@
+/**
+ * Regression guard — the door must not close on a venue behind one NAT.
+ *
+ * `/join` was throttled 5 per 60s keyed purely on the client IP. Every guest at a venue
+ * arrives from the same public IP (that is what a NAT is), so the whole party shared one
+ * bucket: 12 guests scanning the QR code within a few seconds meant 5 got in and 7 were
+ * turned away — with no Retry-After to tell them when to try again. `/feed` (60/min) and
+ * `/export` (3/DAY) had the identical defect.
+ *
+ * These ran green for the same structural reason every time: the e2e reseed forces every
+ * limiter toggle OFF before each test, so nothing here was ever exercised. Enable them
+ * explicitly, exactly as 02-upload/rate-limit does.
+ */
+import { test, expect } from '../../fixtures/test';
+import { BASE } from '../../helpers/env';
+
+test.describe('Rate limits — guests behind a shared NAT', () => {
+  test('a dozen guests can all join from one IP, and 429s carry Retry-After', async ({
+    api,
+    adminToken,
+  }) => {
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      join_rate_enabled: 'true',
+    });
+
+    // Twelve DISTINCT guests, same source IP — the arrival burst at a real party.
+    const names = Array.from({ length: 12 }, (_, i) => `NatGuest${i}`);
+    const results = await Promise.all(
+      names.map((display_name) =>
+        fetch(`${BASE}/api/v1/join`, {
+          method: 'POST',
+          headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify({ display_name }),
+        })
+      )
+    );
+
+    const rejected = results.filter((r) => r.status === 429);
+    expect(
+      rejected.length,
+      `all 12 guests must get in from one IP; ${rejected.length} were turned away`
+    ).toBe(0);
+    expect(results.every((r) => r.status === 201)).toBe(true);
+  });
+
+  test('one guest retrying their own name is still throttled, and told for how long', async ({
+    api,
+    adminToken,
+  }) => {
+    // The per-name bucket must still bite — otherwise the NAT fix would have simply
+    // removed the anti-spam limit rather than re-keyed it.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      join_rate_enabled: 'true',
+    });
+
+    const attempt = () =>
+      fetch(`${BASE}/api/v1/join`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ display_name: 'RepeatOffender' }),
+      });
+
+    // 5 per 60s for the same (ip, name): the first succeeds (201), the next four collide
+    // with the taken name (409), and the sixth exhausts the bucket.
+    const codes: number[] = [];
+    for (let i = 0; i < 6; i++) codes.push((await attempt()).status);
+
+    expect(codes[0], 'the first join should succeed').toBe(201);
+    expect(codes.at(-1), 'the 6th attempt on one name must be throttled').toBe(429);
+
+    const throttled = await attempt();
+    expect(throttled.status).toBe(429);
+    const retryAfter = throttled.headers.get('retry-after');
+    expect(retryAfter, '429 must tell the client when to come back').toBeTruthy();
+    expect(Number(retryAfter)).toBeGreaterThan(0);
+    expect(Number(retryAfter)).toBeLessThanOrEqual(60);
+  });
+
+  test('the feed limit is per-user, not per-IP', async ({ api, adminToken, guest }) => {
+    // Two guests, one IP. With a limit of 3/min an IP key would let the first guest's
+    // three reads starve the second entirely.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      feed_rate_enabled: 'true',
+      feed_rate_per_min: '3',
+    });
+
+    const a = await guest('FeedHog');
+    const b = await guest('FeedVictim');
+    const read = (jwt: string) =>
+      fetch(`${BASE}/api/v1/feed`, { headers: { Authorization: `Bearer ${jwt}` } });
+
+    // Guest A burns their whole allowance.
+    for (let i = 0; i < 3; i++) expect((await read(a.jwt)).status).toBe(200);
+    expect((await read(a.jwt)).status, "A's own 4th read is throttled").toBe(429);
+
+    // Guest B must be entirely unaffected.
+    expect((await read(b.jwt)).status, 'B must not inherit A’s exhausted bucket').toBe(200);
+  });
+
+  test('the export limit is per-user — one guest cannot spend the whole venue’s quota', async ({
+    api,
+    adminToken,
+    guest,
+    host,
+    db,
+  }) => {
+    // The sharpest case: 3 downloads per DAY on an IP key meant the 4th guest to fetch
+    // their keepsake was locked out until tomorrow.
+    await db.setExportReleased('e2e-test-event', true);
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      export_rate_enabled: 'true',
+      export_rate_per_day: '1',
+    });
+
+    const mintAndFetch = async (jwt: string) => {
+      const res = await fetch(`${BASE}/api/v1/export/ticket`, {
+        method: 'POST',
+        headers: { Authorization: `Bearer ${jwt}` },
+      });
+      const { ticket } = await res.json();
+      return fetch(`${BASE}/api/v1/export/zip?ticket=${encodeURIComponent(ticket)}`);
+    };
+
+    const a = await guest('ExportFirst');
+    const b = await guest('ExportSecond');
+
+    // A spends their single daily allowance. The archive itself may not exist (404) —
+    // what matters is that the limiter admitted the request rather than 429ing it.
+    expect((await mintAndFetch(a.jwt)).status).not.toBe(429);
+    expect((await mintAndFetch(a.jwt)).status, 'A’s second download is throttled').toBe(429);
+
+    // B shares A's IP and must still get their keepsake.
+    expect((await mintAndFetch(b.jwt)).status, 'B must not be locked out by A’s download').not.toBe(
+      429
+    );
+
+    // And the host too, for good measure.
+    expect((await mintAndFetch(host.jwt)).status).not.toBe(429);
+  });
+});
+
+test.describe('Rate limits — /recover name cycling', () => {
+  test('cycling names from one IP hits the ceiling, while one name is still throttled', async ({
+    api,
+    adminToken,
+  }) => {
+    // /recover is keyed `recover:{ip}:{name}` — right for its job (stopping someone who
+    // knows a display name from burning the victim's 3-strike PIN counter), but the name is
+    // ATTACKER-CHOSEN, so cycling names minted a fresh bucket every time. Behind it sits a
+    // cost-12 bcrypt verify, including an unconditional throwaway one for unknown names, so
+    // a name generator was the cheapest way to make the server hash forever.
+    //
+    // Squeeze the ceiling so the flood is reproducible without firing 30+ requests.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      recover_rate_enabled: 'true',
+      recover_ip_rate_per_min: '5',
+    });
+
+    const attempt = (name: string) =>
+      fetch(`${BASE}/api/v1/recover`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ display_name: name, pin: '0000' }),
+      });
+
+    // Every name is distinct, so the per-name bucket can never fire — only the ceiling can.
+    const codes: number[] = [];
+    for (let i = 0; i < 12; i++) codes.push((await attempt(`Unbekannt${i}_${Date.now()}`)).status);
+
+    expect(
+      codes.filter((c) => c === 429).length,
+      'name cycling must be capped by the per-IP ceiling'
+    ).toBeGreaterThan(0);
+
+    const throttled = await attempt(`Unbekannt99_${Date.now()}`);
+    expect(throttled.status).toBe(429);
+    expect(Number(throttled.headers.get('retry-after'))).toBeGreaterThan(0);
+  });
+
+  test('the per-name bucket still protects a real account', async ({ api, adminToken, guest }) => {
+    // The ceiling must not have REPLACED the anti-guessing control. With a generous ceiling,
+    // repeated wrong PINs against ONE name must still be shut down by the per-name bucket.
+    const victim = await guest('PinVictim');
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      recover_rate_enabled: 'true',
+      recover_ip_rate_per_min: '1000',
+    });
+
+    const attempt = () =>
+      fetch(`${BASE}/api/v1/recover`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ display_name: victim.displayName, pin: '9999' }),
+      });
+
+    const codes: number[] = [];
+    for (let i = 0; i < 7; i++) codes.push((await attempt()).status);
+    expect(codes.at(-1), 'guessing one name must still be throttled').toBe(429);
+  });
+});

e2e/specs/02-upload/burst-queue.spec.ts

@@ -0,0 +1,219 @@
+/**
+ * Client upload-queue under a realistic burst — the scenario an event actually
+ * produces (a guest multi-selects 10-20 photos at once) and the one the
+ * server-side load test could NOT cover, because that test hit POST /upload
+ * directly and bypassed the browser queue entirely.
+ *
+ * Drives the REAL client path (UploadSheet → /upload → addToQueue →
+ * processQueue → XHR) and asserts the four properties that matter for not
+ * losing a guest's photos:
+ *
+ *   1. SERIAL drain      — the queue uploads ONE file at a time per device
+ *                          (processQueue's find-next-pending loop), never a
+ *                          parallel fan-out. Proven by counting how many upload
+ *                          requests sit in the intercept handler at once.
+ *   2. PERSISTENCE       — every staged file is written to IndexedDB with its
+ *                          blob before it's sent, and the blob is dropped only
+ *                          after the upload succeeds. Read straight out of IDB
+ *                          mid-burst.
+ *   3. ALL LAND          — every file in the burst is created server-side.
+ *   4. RESUME ON RELOAD  — a hard reload mid-burst (tab closed / PWA killed)
+ *                          resumes the remaining uploads from IndexedDB via
+ *                          loadQueue(), losing nothing.
+ *
+ * A tiny per-upload latency is injected via route interception so the serial
+ * drain is observable and there's a window to reload mid-burst — no need for
+ * large fixture files.
+ */
+import { test, expect } from '../../fixtures/test';
+import { skipIfNoIdbBlobs } from '../../helpers/webkit';
+import { FeedPage, UploadSheet } from '../../page-objects';
+import { mkdtempSync, copyFileSync, rmSync } from 'node:fs';
+import { join } from 'node:path';
+import { tmpdir } from 'node:os';
+import type { Page } from '@playwright/test';
+
+const SAMPLE_JPG = join(process.cwd(), 'fixtures', 'media', 'sample.jpg');
+const BURST = 16; // in the 10-20 "multi-select" range
+
+// Make BURST distinct files. The queue dedupes on name+size+lastModified, so
+// distinct NAMES are enough to keep them from collapsing into one item — content
+// can be identical (we only assert rows are created, not what they decode to).
+function makeBurstFiles(): { dir: string; paths: string[] } {
+  const dir = mkdtempSync(join(tmpdir(), 'eventsnap-burst-'));
+  const paths = Array.from({ length: BURST }, (_, i) => {
+    const p = join(dir, `burst_${String(i).padStart(2, '0')}.jpg`);
+    copyFileSync(SAMPLE_JPG, p);
+    return p;
+  });
+  return { dir, paths };
+}
+
+// White-box: read the queue rows straight from IndexedDB, including whether the
+// blob is still attached — so we can prove blobs are kept until upload and
+// dropped after. Mirrors the reader in offline-resume.spec.
+async function queueRows(page: Page): Promise<Array<{ status: string; hasBlob: boolean }>> {
+  return page.evaluate(async () => {
+    return new Promise<Array<{ status: string; hasBlob: boolean }>>((resolve, reject) => {
+      const req = indexedDB.open('eventsnap-uploads', 3);
+      req.onerror = () => reject(req.error);
+      req.onsuccess = () => {
+        const dbh = req.result;
+        const tx = dbh.transaction('queue', 'readonly');
+        const all = tx.objectStore('queue').getAll();
+        all.onsuccess = () =>
+          resolve(all.result.map((r: any) => ({ status: r.status, hasBlob: r.blob != null })));
+        all.onerror = () => reject(all.error);
+      };
+    });
+  });
+}
+
+/**
+ * Intercept POST /upload to (a) inject latency so the serial drain is observable
+ * and (b) count how many uploads are in the handler simultaneously. A serial
+ * client never has more than one in flight; a parallel fan-out would spike.
+ * Returns a `peak()` accessor for the max concurrency seen.
+ */
+async function instrumentUploads(page: Page, delayMs: number) {
+  let active = 0;
+  let peak = 0;
+  await page.route('**/api/v1/upload', async (route) => {
+    active++;
+    peak = Math.max(peak, active);
+    await new Promise((r) => setTimeout(r, delayMs));
+    active--;
+    await route.continue();
+  });
+  return { peak: () => peak };
+}
+
+async function warmUploadChunk(page: Page) {
+  // Load the code-split /upload route while online so a later reload/navigation
+  // doesn't fetch the chunk at a bad moment (mirrors offline-resume.spec).
+  await page.goto('/upload');
+  await page.goto('/feed');
+}
+
+test.describe('Upload — client queue under a burst', () => {
+  test('a 16-file burst drains serially, persists to IndexedDB, and all land', async ({
+    page,
+    guest,
+    signIn,
+    db,
+    browserName,
+  }) => {
+    skipIfNoIdbBlobs(browserName);
+    const g = await guest('BurstSerial');
+    await signIn(page, g);
+    await warmUploadChunk(page);
+    const uploads = await instrumentUploads(page, 200);
+
+    // Stage the whole burst through the real UI.
+    const { dir, paths } = makeBurstFiles();
+    try {
+      const feed = new FeedPage(page);
+      const sheet = new UploadSheet(page);
+      await feed.openUploadSheet();
+      await sheet.stageFiles(paths);
+      await sheet.captionInput.waitFor({ state: 'visible', timeout: 10_000 });
+      await sheet.fillCaption('burst of 16 #hochzeit');
+      await sheet.submit();
+      await page.waitForURL('**/feed', { timeout: 15_000 });
+
+      // (2) PERSISTENCE: all 16 are written to IndexedDB with blobs essentially
+      // immediately — before most have been sent. Catch the burst while the
+      // queue still holds most of them.
+      await expect
+        .poll(async () => (await queueRows(page)).length, { timeout: 10_000 })
+        .toBe(BURST);
+
+      // While draining, pending rows keep their blob; done rows have dropped it.
+      // Poll for a mid-burst moment that shows both invariants at once.
+      await expect
+        .poll(
+          async () => {
+            const rows = await queueRows(page);
+            const pendingKeepBlob = rows
+              .filter((r) => r.status === 'pending' || r.status === 'uploading')
+              .every((r) => r.hasBlob);
+            const doneDropBlob = rows.filter((r) => r.status === 'done').every((r) => !r.hasBlob);
+            return pendingKeepBlob && doneDropBlob;
+          },
+          { timeout: 10_000 }
+        )
+        .toBe(true);
+
+      // (3) ALL LAND: every file is created server-side.
+      await expect.poll(() => db.countUploadsForUser(g.userId), { timeout: 30_000 }).toBe(BURST);
+
+      // (1) SERIAL: never more than one upload in flight at a time.
+      expect(uploads.peak()).toBe(1);
+
+      // Clean end — the queue settles all items to done (no stuck error/blocked).
+      await expect
+        .poll(async () => (await queueRows(page)).every((r) => r.status === 'done'), {
+          timeout: 10_000,
+        })
+        .toBe(true);
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+
+  test('a hard reload mid-burst resumes the remaining uploads — nothing lost', async ({
+    page,
+    guest,
+    signIn,
+    db,
+    browserName,
+  }) => {
+    skipIfNoIdbBlobs(browserName);
+    const g = await guest('BurstResume');
+    await signIn(page, g);
+    await warmUploadChunk(page);
+    // Bigger delay → a wide, reliable mid-burst window to reload inside. (We don't
+    // assert seriality here — test 1 already proves it, and a reload aborts the
+    // in-flight request mid-intercept, which would overcount concurrency.)
+    await instrumentUploads(page, 300);
+
+    const { dir, paths } = makeBurstFiles();
+    try {
+      const feed = new FeedPage(page);
+      const sheet = new UploadSheet(page);
+      await feed.openUploadSheet();
+      await sheet.stageFiles(paths);
+      await sheet.captionInput.waitFor({ state: 'visible', timeout: 10_000 });
+      await sheet.fillCaption('burst then reload');
+      await sheet.submit();
+      await page.waitForURL('**/feed', { timeout: 15_000 });
+
+      // Wait until we're genuinely mid-burst: a few landed, but far from all.
+      await expect
+        .poll(() => db.countUploadsForUser(g.userId), { timeout: 20_000 })
+        .toBeGreaterThanOrEqual(3);
+      const landedBeforeReload = await db.countUploadsForUser(g.userId);
+      expect(landedBeforeReload).toBeLessThan(BURST);
+
+      // Hard reload — wipes the JS module (and its in-flight drain), exactly like
+      // a closed tab / killed PWA. The remaining pending items live only in
+      // IndexedDB now.
+      await page.reload();
+      // The queue only resumes where loadQueue() runs — the /upload route's
+      // onMount. Navigating there is the "reopen the composer" recovery path.
+      await page.goto('/upload');
+
+      // (4) RESUME: every file ends up server-side without re-staging anything.
+      // `>=` not `===`: the only imperfection possible is a DUPLICATE (an upload
+      // that succeeded server-side in the ~1ms between the XHR load event and the
+      // IndexedDB 'done' write, caught by the reload, then re-sent on resume).
+      // That's at worst one extra row, never a lost photo — the property we care
+      // about. A shortfall (< BURST) would be a real data-loss regression.
+      await expect
+        .poll(() => db.countUploadsForUser(g.userId), { timeout: 30_000 })
+        .toBeGreaterThanOrEqual(BURST);
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});

e2e/specs/02-upload/exif-orientation.spec.ts

@@ -0,0 +1,80 @@
+/**
+ * Regression guard — EXIF orientation must be applied when generating derivatives.
+ *
+ * Phones do not rotate sensor data. They shoot in the sensor's native landscape and record
+ * how the camera was held in an EXIF `Orientation` tag. `image`'s `decode()` returns the raw
+ * pixels and ignores that tag, and the JPEG re-encode writes no EXIF at all — so every
+ * portrait photo was stored SIDEWAYS in the 800px feed preview, the 2048px diashow display
+ * and the keepsake, while "Original anzeigen" still rendered it upright (the original keeps
+ * its tag). That asymmetry is why it reads as a viewer bug instead of a pipeline one.
+ *
+ * The fixture is 40x20 landscape pixels tagged Orientation=6 ("rotate 90° CW to display"),
+ * so a correctly-processed derivative is PORTRAIT (20x40). Asserting on the aspect ratio
+ * rather than the bytes keeps this robust across encoder changes.
+ */
+import { test, expect } from '../../fixtures/test';
+import { uploadRaw } from '../../helpers/upload-client';
+import { BASE } from '../../helpers/env';
+import { readFileSync } from 'node:fs';
+import { join } from 'node:path';
+
+const EXIF_FIXTURE = join(process.cwd(), 'fixtures', 'media', 'portrait-exif6.jpg');
+
+/**
+ * Read a baseline/progressive JPEG's pixel dimensions from its SOF marker.
+ * Avoids pulling an image dependency into the suite for one assertion.
+ */
+function jpegSize(buf: Buffer): { width: number; height: number } {
+  let i = 2; // skip SOI
+  while (i < buf.length) {
+    if (buf[i] !== 0xff) {
+      i++;
+      continue;
+    }
+    const marker = buf[i + 1];
+    // SOF0..SOF15, excluding DHT (c4), JPGA (c8) and DAC (cc)
+    if (marker >= 0xc0 && marker <= 0xcf && marker !== 0xc4 && marker !== 0xc8 && marker !== 0xcc) {
+      return { height: buf.readUInt16BE(i + 5), width: buf.readUInt16BE(i + 7) };
+    }
+    i += 2 + buf.readUInt16BE(i + 2);
+  }
+  throw new Error('no SOF marker found — not a JPEG?');
+}
+
+test.describe('Upload — EXIF orientation', () => {
+  test('a rotated photo is upright in the preview and the display derivative', async ({
+    guest,
+    db,
+  }) => {
+    const g = await guest('SidewaysShooter');
+
+    const res = await uploadRaw(g.jwt, readFileSync(EXIF_FIXTURE), {
+      filename: 'portrait-exif6.jpg',
+      contentType: 'image/jpeg',
+      caption: 'hochkant',
+    });
+    expect(res.status).toBe(201);
+    const { id } = (await res.json()) as { id: string };
+
+    // Sanity: the SOURCE really is stored landscape with the tag, otherwise this test
+    // could pass against a pipeline that does nothing.
+    const source = jpegSize(readFileSync(EXIF_FIXTURE));
+    expect(source.width).toBeGreaterThan(source.height);
+
+    await expect
+      .poll(() => db.compressionStatus(id), { timeout: 30_000, intervals: [250] })
+      .toBe('done');
+
+    for (const variant of ['preview', 'display'] as const) {
+      const r = await fetch(`${BASE}/api/v1/upload/${id}/${variant}`, {
+        headers: { Authorization: `Bearer ${g.jwt}` },
+      });
+      expect(r.status, `${variant} must be served`).toBe(200);
+      const { width, height } = jpegSize(Buffer.from(await r.arrayBuffer()));
+      expect(
+        height,
+        `${variant} must be portrait (${width}x${height}) — EXIF orientation was not applied`
+      ).toBeGreaterThan(width);
+    }
+  });
+});

e2e/specs/02-upload/gallery-path.spec.ts

@@ -4,6 +4,7 @@
  * IndexedDB queue resumption after refresh, and SSE `upload-processed`.
  */
 import { test, expect } from '../../fixtures/test';
+import { skipIfNoIdbBlobs } from '../../helpers/webkit';
 import { FeedPage, UploadSheet } from '../../page-objects';
 import { SseListener } from '../../helpers/sse-listener';
 import { join } from 'node:path';
@@ -49,7 +50,9 @@ test.describe('Upload — gallery path', () => {
     guest,
     signIn,
     db,
+    browserName,
   }) => {
+    skipIfNoIdbBlobs(browserName);
     // Previously fixme'd: the UI queue never fired a POST. Root cause was NOT a
     // navigation/blob timing quirk but an IndexedDB upgrade bug — the v1→v2
     // `upgrade` callback opened a *new* transaction, which throws during a

e2e/specs/02-upload/oversized-image.spec.ts

@@ -0,0 +1,100 @@
+/**
+ * Regression guard — an image that would blow the decode budget must be refused at the
+ * door, with a reason the guest can act on, and must never allocate.
+ *
+ * Two defects met here.
+ *
+ * 1. The budget was inert. `max_alloc = 256 MiB` was set, but reading the EXIF orientation
+ *    tag requires `ImageReader::into_decoder()`, which skips the
+ *    `limits.reserve(decoder.total_bytes())` that `decode()` performs — and nothing else
+ *    enforces it (the JPEG decoder's `set_limits` only checks support and dimensions). The
+ *    only real bound was the 12000px per-axis cap, leaving two concurrent decodes at
+ *    824 MiB against a 1 GiB container. This suite could not have caught it either, because
+ *    the e2e app container had NO memory limit while production is capped at 1 GiB; that cap
+ *    is now mirrored in docker-compose.test.yml so these assertions mean something.
+ *
+ * 2. Even with the budget restored, the upload was ACCEPTED with a 201 and then silently
+ *    soft-deleted minutes later when the worker gave up — the photo simply vanished, with at
+ *    best a vague "could not be processed". Admission now runs the same budget check against
+ *    the header, so the guest is told immediately and told why.
+ *
+ * Fixture: 11000x9000 = 99 MP, 568 KiB on disk. Deliberately UNDER the per-axis cap, so the
+ * axis check cannot be what rejects it — 283 MiB decoded against a 256 MiB budget. A fixture
+ * at 13000px would pass this test against a build with no budget at all.
+ */
+import { test, expect } from '../../fixtures/test';
+import { uploadRaw } from '../../helpers/upload-client';
+import { BASE } from '../../helpers/env';
+import { readFileSync } from 'node:fs';
+import { join } from 'node:path';
+
+const HUGE = join(process.cwd(), 'fixtures', 'media', 'huge-99mp.jpg');
+const SAMPLE = join(process.cwd(), 'fixtures', 'media', 'sample.jpg');
+
+test.describe('Upload — an oversized image is refused, not allocated', () => {
+  test('a 99 MP upload is rejected at admission with a readable reason', async ({ guest, db }) => {
+    test.setTimeout(60_000);
+    const g = await guest('BombThrower');
+    const before = await db.countUploadsForUser(g.userId);
+
+    const res = await uploadRaw(g.jwt, readFileSync(HUGE), {
+      filename: 'huge.jpg',
+      contentType: 'image/jpeg',
+      caption: 'zu gross',
+    });
+
+    // 4xx, not 201-then-vanish. The queue classifies this as terminal, so the guest gets the
+    // message rather than watching the photo disappear.
+    expect(res.status, 'an undecodable image must be refused at the door').toBe(400);
+    const body = (await res.json()) as { message?: string };
+    expect(body.message ?? '', 'the reason must be actionable, not generic').toMatch(/bildpunkte/i);
+    expect(body.message ?? '', 'and should name the size so it is obvious why').toMatch(/99/);
+
+    // Nothing was stored — no row to soft-delete later, no orphaned file to sweep.
+    expect(await db.countUploadsForUser(g.userId)).toBe(before);
+
+    // The backend never allocated: it is still alive and still doing useful work.
+    expect((await fetch(`${BASE}/health`)).status).toBe(200);
+    const ok = await uploadRaw(g.jwt, readFileSync(SAMPLE), {
+      filename: 'after.jpg',
+      contentType: 'image/jpeg',
+    });
+    expect(ok.status).toBe(201);
+    const after = (await ok.json()) as { id: string };
+    await expect.poll(() => db.compressionStatus(after.id), { timeout: 30_000 }).toBe('done');
+  });
+
+  test('a burst of oversized uploads leaves the container alive', async ({ guest }) => {
+    // The concurrent case is the one that OOM'd: `compression_concurrency` is 2, so decodes
+    // overlapped. Four at once is comfortably past that, and must still cost only header
+    // reads.
+    test.setTimeout(60_000);
+    const g = await guest('BombThrower2');
+    const bytes = readFileSync(HUGE);
+
+    const results = await Promise.all(
+      Array.from({ length: 4 }, (_, i) =>
+        uploadRaw(g.jwt, bytes, { filename: `huge-${i}.jpg`, contentType: 'image/jpeg' })
+      )
+    );
+    expect(results.map((r) => r.status)).toEqual([400, 400, 400, 400]);
+
+    expect(
+      (await fetch(`${BASE}/health`)).status,
+      'concurrent oversized uploads must not kill the backend'
+    ).toBe(200);
+  });
+
+  test('an ordinary photo is unaffected by the admission check', async ({ guest, db }) => {
+    // The mirror that keeps the check honest: a budget that rejected everything would pass
+    // both tests above.
+    const g = await guest('NormalShooter');
+    const res = await uploadRaw(g.jwt, readFileSync(SAMPLE), {
+      filename: 'normal.jpg',
+      contentType: 'image/jpeg',
+    });
+    expect(res.status).toBe(201);
+    const { id } = (await res.json()) as { id: string };
+    await expect.poll(() => db.compressionStatus(id), { timeout: 30_000 }).toBe('done');
+  });
+});

e2e/specs/02-upload/quota.spec.ts

@@ -56,14 +56,21 @@ function upload(jwt: string, name: string) {
 /**
  * Pick a `quota_tolerance` that makes the per-user ceiling land on `targetBytes`.
  * limit = floor(free_disk * tolerance / max(active, 1))  ⇒  tolerance = target * active / free.
+ *
+ * `staffJwt` reads the calibration inputs, `jwt` is the guest the limit is being aimed at.
+ * They must be different tokens: `free_disk_bytes` and `active_uploaders` are raw server
+ * telemetry and `/me/quota` zeroes both for non-staff (handlers/me.rs — "must never reach a
+ * guest"). Calibrating off the guest's own response divides by zero and yields a NaN
+ * tolerance, which is what silently broke this whole describe block.
  */
 async function setLimitTo(
   api: any,
   adminToken: string,
+  staffJwt: string,
   jwt: string,
   targetBytes: number
 ): Promise<number> {
-  const q = await quotaOf(jwt);
+  const q = await quotaOf(staffJwt);
   expect(
     q.free_disk_bytes,
     'the disk must be readable, else quota fails OPEN and proves nothing'
@@ -72,6 +79,7 @@ async function setLimitTo(
   const tolerance = (targetBytes * active) / (q.free_disk_bytes as number);
   await api.patchConfig(adminToken, { quota_tolerance: tolerance.toExponential(12) });
 
+  // Read back through the GUEST, whose ceiling is the one under test.
   const after = await quotaOf(jwt);
   expect(after.enabled).toBe(true);
   return after.limit_bytes as number;
@@ -89,10 +97,11 @@ test.describe('Upload — storage quota enforcement', () => {
     api,
     adminToken,
     guest,
+    host,
   }) => {
     const g = await guest('QuotaOver');
     // Ceiling below one file: the very first upload must be refused.
-    const limit = await setLimitTo(api, adminToken, g.jwt, Math.floor(SIZE / 2));
+    const limit = await setLimitTo(api, adminToken, host.jwt, g.jwt, Math.floor(SIZE / 2));
     expect(limit).toBeLessThan(SIZE);
 
     const res = await upload(g.jwt, 'too-big.jpg');
@@ -111,9 +120,10 @@ test.describe('Upload — storage quota enforcement', () => {
     api,
     adminToken,
     guest,
+    host,
   }) => {
     const g = await guest('QuotaUnder');
-    await setLimitTo(api, adminToken, g.jwt, SIZE * 4);
+    await setLimitTo(api, adminToken, host.jwt, g.jwt, SIZE * 4);
 
     expect((await upload(g.jwt, 'fine.jpg')).status).toBe(201);
     expect((await quotaOf(g.jwt)).used_bytes).toBe(SIZE);
@@ -123,11 +133,12 @@ test.describe('Upload — storage quota enforcement', () => {
     api,
     adminToken,
     guest,
+    host,
   }) => {
     const g = await guest('QuotaRacer');
 
     // Room for exactly ONE file.
-    const limit = await setLimitTo(api, adminToken, g.jwt, Math.floor(SIZE * 1.5));
+    const limit = await setLimitTo(api, adminToken, host.jwt, g.jwt, Math.floor(SIZE * 1.5));
     expect(limit).toBeGreaterThanOrEqual(SIZE);
     expect(limit).toBeLessThan(SIZE * 2);
 
@@ -170,10 +181,11 @@ test.describe('Upload — storage quota enforcement', () => {
     api,
     adminToken,
     guest,
+    host,
   }) => {
     // Zero test hits before this — and it is the source of the "X von Y MB genutzt" widget.
     const g = await guest('QuotaWidget');
-    await setLimitTo(api, adminToken, g.jwt, SIZE * 10);
+    await setLimitTo(api, adminToken, host.jwt, g.jwt, SIZE * 10);
 
     const before = await quotaOf(g.jwt);
     expect(before.enabled).toBe(true);

e2e/specs/02-upload/rejection-visible.spec.ts

@@ -0,0 +1,87 @@
+/**
+ * Regression guard — a rejected upload must tell the user something.
+ *
+ * `UploadQueue.svelte` was 162 lines of complete, working UI — the only renderer of an
+ * item's error text, the only "Erneut" retry button, the only rate-limit countdown — and it
+ * was never imported anywhere, so `retryItem`, `removeItem` and `clearCompleted` were all
+ * unreachable at runtime. On a terminal rejection the store dropped the blob, wrote a clear
+ * German reason into `entry.error` with the comment "so the UI shows a clear reason", and
+ * there was no such UI.
+ *
+ * Meanwhile the FAB badge counted only pending/uploading, so a rejected photo decremented it
+ * exactly as if it had succeeded. Net effect: the photo silently vanished — no toast, no
+ * queue row, no error text, and it never appeared in the feed.
+ */
+import { test, expect } from '../../fixtures/test';
+import { skipIfNoIdbBlobs } from '../../helpers/webkit';
+import { FeedPage, UploadSheet } from '../../page-objects';
+import { join } from 'node:path';
+
+const SAMPLE_JPG = join(process.cwd(), 'fixtures', 'media', 'sample.jpg');
+
+test.describe('Upload — a rejected upload is surfaced', () => {
+  test('a terminally rejected upload toasts, and stays visible in the queue', async ({
+    page,
+    api,
+    host,
+    guest,
+    signIn,
+    browserName,
+  }) => {
+    skipIfNoIdbBlobs(browserName);
+    const g = await guest('RejectedUploader');
+    await signIn(page, g);
+
+    const feed = new FeedPage(page);
+    const sheet = new UploadSheet(page);
+    await feed.openUploadSheet();
+    await sheet.stageFiles([SAMPLE_JPG]);
+    await sheet.captionInput.waitFor({ state: 'visible', timeout: 10_000 });
+
+    // Ban the uploader between staging and sending, so the POST comes back 403 — a
+    // terminal 4xx the server will keep rejecting, which is the path that purges the blob.
+    await api.banUser(host.jwt, g.userId);
+
+    await sheet.submit();
+
+    // 1. The user is told, wherever they are (the flow lands them on /feed).
+    const toast = page.getByRole('region', { name: 'Benachrichtigungen' });
+    await expect(toast).toContainText(/sample\.jpg/i, { timeout: 15_000 });
+
+    // 2. The queue row survives with its reason and is reachable on /upload — this is what
+    //    the orphaned component made impossible.
+    await page.goto('/upload');
+    const queue = page.getByText('Upload-Warteschlange');
+    await expect(queue, 'the upload queue must be rendered somewhere').toBeVisible({
+      timeout: 10_000,
+    });
+    // Both the status chip ("Gesperrt") and the server's reason ("Du bist gesperrt.") must
+    // render — the reason is the part that had no UI at all before.
+    await expect(page.getByText('Gesperrt', { exact: true })).toBeVisible();
+    await expect(page.getByText('Du bist gesperrt.')).toBeVisible();
+
+    // 3. The badge must not read as success. It counted only pending/uploading before, so a
+    //    rejected item dropped it to 0 — indistinguishable from a completed upload.
+    await expect
+      .poll(
+        () =>
+          page.evaluate(async () => {
+            return new Promise<number>((resolve, reject) => {
+              const req = indexedDB.open('eventsnap-uploads', 3);
+              req.onerror = () => reject(req.error);
+              req.onsuccess = () => {
+                const tx = req.result.transaction('queue', 'readonly');
+                const all = tx.objectStore('queue').getAll();
+                all.onsuccess = () =>
+                  resolve(
+                    all.result.filter((r: { status: string }) => r.status === 'blocked').length
+                  );
+                all.onerror = () => reject(all.error);
+              };
+            });
+          }),
+        { timeout: 10_000 }
+      )
+      .toBe(1);
+  });
+});

e2e/specs/03-feed/social-rate-limit.spec.ts

@@ -0,0 +1,136 @@
+/**
+ * Regression guard — likes, comments and comment deletions are rate limited.
+ *
+ * These were the only mutating endpoints in the app with no limit at all. Every other write path
+ * -- upload, join, recover, export, admin login -- carried one; `social.rs` carried none, so the
+ * coverage was asymmetric rather than deliberately open.
+ *
+ * Severity is genuinely low for an invited-guest event, and the amplification worry is contained:
+ * a like does fan an SSE broadcast to every connected client, but the export regeneration a
+ * comment deletion triggers is debounced (REGEN_DEBOUNCE 20s) and superseded workers are inert. So
+ * this closes the gap for symmetry, and the ceiling is set well above anything a real guest
+ * produces -- it bounds a script, not an enthusiastic double-tapper.
+ *
+ * The bucket is shared across all three actions on purpose: separate buckets would let a caller
+ * triple the aggregate write rate just by alternating between them. That is what the second test
+ * pins, and it is the part most likely to be lost in a refactor.
+ *
+ * Keyed per USER, not per IP — at a venue every guest is behind one NAT, so an IP key would hand
+ * the whole party one bucket. Third test.
+ */
+import { test, expect } from '../../fixtures/test';
+import { seedUpload } from '../../helpers/seed';
+import { BASE } from '../../helpers/env';
+
+const like = (jwt: string, uploadId: string) =>
+  fetch(`${BASE}/api/v1/upload/${uploadId}/like`, {
+    method: 'POST',
+    headers: { Authorization: `Bearer ${jwt}` },
+  });
+
+const comment = (jwt: string, uploadId: string, body: string) =>
+  fetch(`${BASE}/api/v1/upload/${uploadId}/comments`, {
+    method: 'POST',
+    headers: { Authorization: `Bearer ${jwt}`, 'Content-Type': 'application/json' },
+    body: JSON.stringify({ body }),
+  });
+
+test.describe('Social — rate limit', () => {
+  test('a burst of likes past the ceiling returns 429 with Retry-After', async ({
+    api,
+    adminToken,
+    guest,
+  }) => {
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      social_rate_enabled: 'true',
+      social_rate_per_min: '3',
+    });
+
+    const g = await guest('Tapper');
+    const uploadId = await seedUpload(g.jwt);
+
+    // Sequential, not parallel: a toggle flips state, so ordering matters for the assertion.
+    const statuses: number[] = [];
+    for (let i = 0; i < 5; i++) statuses.push((await like(g.jwt, uploadId)).status);
+
+    expect(statuses.slice(0, 3), 'the first three are within the ceiling').toEqual([200, 200, 200]);
+    expect(statuses.slice(3), 'everything past it is refused').toEqual([429, 429]);
+
+    const limited = await like(g.jwt, uploadId);
+    expect(limited.status).toBe(429);
+    expect(
+      limited.headers.get('retry-after'),
+      'a 429 without Retry-After tells the client nothing about when to come back'
+    ).toBeTruthy();
+  });
+
+  test('likes and comments share one bucket', async ({ api, adminToken, guest }) => {
+    // THE assertion. Per-action buckets would let a caller triple the aggregate write rate by
+    // alternating, which defeats the point of having a ceiling at all.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      social_rate_enabled: 'true',
+      social_rate_per_min: '2',
+    });
+
+    const g = await guest('Mixer');
+    const uploadId = await seedUpload(g.jwt);
+
+    expect((await like(g.jwt, uploadId)).status).toBe(200);
+    expect((await comment(g.jwt, uploadId, 'schön!')).status).toBe(201);
+    // Two writes spent, whichever endpoints they went to.
+    expect(
+      (await comment(g.jwt, uploadId, 'noch eins')).status,
+      'a comment must consume the same budget a like does'
+    ).toBe(429);
+    expect((await like(g.jwt, uploadId)).status).toBe(429);
+  });
+
+  test('one guest hitting the ceiling does not block another', async ({
+    api,
+    adminToken,
+    guest,
+  }) => {
+    // Keyed per user, not per IP. Every request in this suite comes from one address, which is
+    // exactly the venue-NAT shape that made the /join and /feed limits turn guests away.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      social_rate_enabled: 'true',
+      social_rate_per_min: '2',
+    });
+
+    const noisy = await guest('Noisy');
+    const quiet = await guest('Quiet');
+    const uploadId = await seedUpload(noisy.jwt);
+
+    for (let i = 0; i < 3; i++) await like(noisy.jwt, uploadId);
+    expect((await like(noisy.jwt, uploadId)).status).toBe(429);
+
+    expect(
+      (await like(quiet.jwt, uploadId)).status,
+      'a second guest behind the same IP must have their own budget'
+    ).toBe(200);
+  });
+
+  test('flipping social_rate_enabled off bypasses the limit', async ({
+    api,
+    adminToken,
+    guest,
+  }) => {
+    // The toggle has to actually be honoured, or the admin switch is decorative — the failure
+    // mode two other per-area toggles already shipped with.
+    await api.patchConfig(adminToken, {
+      rate_limits_enabled: 'true',
+      social_rate_enabled: 'false',
+      social_rate_per_min: '2',
+    });
+
+    const g = await guest('Unlimited');
+    const uploadId = await seedUpload(g.jwt);
+
+    const statuses: number[] = [];
+    for (let i = 0; i < 6; i++) statuses.push((await like(g.jwt, uploadId)).status);
+    expect(statuses.every((s) => s === 200)).toBe(true);
+  });
+});

e2e/specs/03-feed/video-playback.spec.ts

@@ -0,0 +1,181 @@
+/**
+ * Regression guard — videos must actually play.
+ *
+ * Two independent defects made every video unplayable, and nothing in the suite covered
+ * either one (no test anywhere played media or asserted a `<video>` src):
+ *
+ *  1. The lightbox fed `<video>` the URL from `pickMediaUrl`, which is mime-agnostic.
+ *     Compression only ever produces a *thumbnail* for a video — one ffmpeg frame — so in
+ *     the DEFAULT saver mode the element's src was `/api/v1/upload/{id}/thumbnail`: a JPEG,
+ *     served as image/jpeg with nosniff so the browser can't even sniff its way out.
+ *     Chromium reported DEMUXER_ERROR_COULD_NOT_OPEN.
+ *
+ *  2. `stream_media_file` ignored `Range` entirely — always 200 with the whole body, never
+ *     an Accept-Ranges or Content-Range. iOS Safari opens every `<video>` with a
+ *     `Range: bytes=0-1` probe and abandons the load without a 206, so video failed on the
+ *     app's primary platform even in `original` data mode.
+ *
+ * Fixing either alone still leaves video broken, so both are asserted here.
+ */
+import { test, expect } from '../../fixtures/test';
+import { uploadRaw } from '../../helpers/upload-client';
+import { BASE } from '../../helpers/env';
+import { readFileSync } from 'node:fs';
+import { join } from 'node:path';
+
+const SAMPLE_MP4 = join(process.cwd(), 'fixtures', 'media', 'sample.mp4');
+
+async function seedVideo(jwt: string): Promise<string> {
+  const res = await uploadRaw(jwt, readFileSync(SAMPLE_MP4), {
+    filename: 'clip.mp4',
+    contentType: 'video/mp4',
+    caption: 'ein Video',
+  });
+  if (res.status !== 201) throw new Error(`video seed failed: ${res.status}`);
+  return ((await res.json()) as { id: string }).id;
+}
+
+test.describe('Video — the lightbox plays it', () => {
+  test('the <video> src is the original, not the thumbnail JPEG', async ({
+    page,
+    guest,
+    signIn,
+    db,
+  }) => {
+    const g = await guest('VideoWatcher');
+    const id = await seedVideo(g.jwt);
+
+    // The poster assertion below needs the ffmpeg thumbnail to EXIST — the lightbox binds
+    // `poster={upload.thumbnail_url ?? undefined}`, so the attribute is simply absent until
+    // compression finishes. Without this wait the test races the worker and fails against a
+    // cold stack (first run after `stack:down -v`, cold ffmpeg), which is exactly when a suite
+    // is least likely to be believed. The `src` assertion is unconditional; only the poster
+    // needs the wait.
+    await expect.poll(() => db.compressionStatus(id), { timeout: 60_000 }).toBe('done');
+
+    await signIn(page, g);
+    await page.goto('/feed');
+
+    const card = page.locator('article').first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Bild vergrößern' }).click();
+
+    const video = page.locator('video');
+    await expect(video).toBeVisible({ timeout: 10_000 });
+
+    // The bug in one assertion: this was `/thumbnail` in the default data mode.
+    await expect(video).toHaveAttribute('src', `/api/v1/upload/${id}/original`);
+
+    // The poster SHOULD still be the thumbnail — that's what it's for.
+    await expect(video).toHaveAttribute('poster', `/api/v1/upload/${id}/thumbnail`);
+
+    // And the browser must accept the bytes as media. preload="none" means nothing is
+    // fetched until we ask, so drive a load explicitly and wait for metadata.
+    const readyState = await video.evaluate(async (el: HTMLVideoElement) => {
+      el.preload = 'metadata';
+      el.load();
+      await new Promise<void>((resolve) => {
+        if (el.readyState > 0) return resolve();
+        el.addEventListener('loadedmetadata', () => resolve(), { once: true });
+        el.addEventListener('error', () => resolve(), { once: true });
+        setTimeout(resolve, 15_000);
+      });
+      return { ready: el.readyState, err: el.error?.message ?? null };
+    });
+    expect(readyState.err, `the browser rejected the media: ${readyState.err}`).toBeNull();
+    expect(readyState.ready, 'video metadata must load').toBeGreaterThan(0);
+  });
+
+  test('the video body is not downloaded before the user presses play', async ({
+    page,
+    guest,
+    signIn,
+  }) => {
+    // saver mode exists to protect a guest's mobile data, and there is no smaller video
+    // derivative to fall back to — so opening the lightbox must not pull the file down.
+    //
+    // Asserting "no request at all" would be wrong: WebKit opens a connection for a
+    // preload="none" <video> and immediately ABORTS it (observed: GET with no Range,
+    // response status 0, nothing transferred), whereas Chromium issues nothing. The
+    // portable guarantee — and the one that actually protects the data plan — is that no
+    // response carrying the body ever completes. Dropping preload="none" fails this.
+    const g = await guest('VideoThrifty');
+    const id = await seedVideo(g.jwt);
+
+    await signIn(page, g);
+    const delivered: string[] = [];
+    page.on('response', (r) => {
+      if (!r.url().includes(`/upload/${id}/original`)) return;
+      // status 0 = aborted before any bytes landed.
+      if (r.status() === 200 || r.status() === 206) {
+        delivered.push(`${r.status()} len=${r.headers()['content-length'] ?? '?'}`);
+      }
+    });
+
+    await page.goto('/feed');
+    const card = page.locator('article').first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Bild vergrößern' }).click();
+    await expect(page.locator('video')).toBeVisible({ timeout: 10_000 });
+    await page.waitForTimeout(2000);
+
+    expect(delivered, 'no video bytes may be delivered before play').toEqual([]);
+  });
+});
+
+test.describe('Media — HTTP Range', () => {
+  test('a range request is answered 206 with the right slice', async ({ guest }) => {
+    const g = await guest('RangeReader');
+    const id = await seedVideo(g.jwt);
+    const url = `${BASE}/api/v1/upload/${id}/original`;
+
+    const full = await fetch(url);
+    expect(full.status).toBe(200);
+    expect(full.headers.get('accept-ranges'), 'clients must be told seeking works').toBe('bytes');
+    const total = Number(full.headers.get('content-length'));
+    expect(total).toBeGreaterThan(0);
+
+    // The exact probe iOS Safari opens a <video> with. Two bytes, inclusive.
+    const probe = await fetch(url, { headers: { Range: 'bytes=0-1' } });
+    expect(probe.status, 'iOS abandons the load without a 206').toBe(206);
+    expect(probe.headers.get('content-range')).toBe(`bytes 0-1/${total}`);
+    expect(Number(probe.headers.get('content-length'))).toBe(2);
+    expect((await probe.arrayBuffer()).byteLength).toBe(2);
+
+    // A mid-file seek must return the matching slice, not the whole body.
+    const mid = await fetch(url, { headers: { Range: 'bytes=10-19' } });
+    expect(mid.status).toBe(206);
+    expect(mid.headers.get('content-range')).toBe(`bytes 10-19/${total}`);
+    const midBytes = Buffer.from(await mid.arrayBuffer());
+    expect(midBytes.byteLength).toBe(10);
+    expect(midBytes).toEqual(Buffer.from(await full.arrayBuffer()).subarray(10, 20));
+
+    // Open-ended range runs to EOF.
+    const tail = await fetch(url, { headers: { Range: `bytes=${total - 5}-` } });
+    expect(tail.status).toBe(206);
+    expect(Number(tail.headers.get('content-length'))).toBe(5);
+
+    // Past EOF must be 416 — answering 200 makes a player re-request forever.
+    const bad = await fetch(url, { headers: { Range: `bytes=${total + 10}-` } });
+    expect(bad.status).toBe(416);
+    expect(bad.headers.get('content-range')).toBe(`bytes */${total}`);
+  });
+
+  test('image derivatives are range-capable too', async ({ guest, db }) => {
+    // Same helper serves all four media routes, so the guarantee is uniform.
+    const g = await guest('RangeImages');
+    const res = await uploadRaw(
+      g.jwt,
+      readFileSync(join(process.cwd(), 'fixtures', 'media', 'sample.jpg')),
+      { filename: 'r.jpg', contentType: 'image/jpeg' }
+    );
+    const { id } = (await res.json()) as { id: string };
+    await expect.poll(() => db.compressionStatus(id), { timeout: 30_000 }).toBe('done');
+
+    const preview = await fetch(`${BASE}/api/v1/upload/${id}/preview`, {
+      headers: { Range: 'bytes=0-9' },
+    });
+    expect(preview.status).toBe(206);
+    expect(Number(preview.headers.get('content-length'))).toBe(10);
+  });
+});

e2e/specs/04-host/low-disk-warning.spec.ts

@@ -0,0 +1,97 @@
+/**
+ * Regression guard — the host is warned about storage BEFORE it becomes unrecoverable.
+ *
+ * Storage visibility used to exist in exactly one place: a passive "Speicherauslastung" widget on
+ * the ADMIN dashboard. A host who isn't the admin had no view of it at all, and nothing anywhere
+ * warned anyone. README listed a low-disk alert under "Planned (v1.x)".
+ *
+ * Two things make that a safety net rather than a nice-to-have:
+ *
+ *  - `postgres_data`, `media_data` and `exports_data` are all Docker named volumes on ONE
+ *    filesystem. A full disk doesn't degrade a subsystem; Postgres stops being able to write and
+ *    the whole event goes down.
+ *  - The keepsake needs room for TWO gallery-sized archives (both write their media
+ *    `Compression::Stored`; `Memories.zip` streams the original for every video and every image
+ *    at or under 5 MB). The export preflight can refuse cleanly, but only AFTER the release —
+ *    when the event is over, the gallery is full, and every remedy is harder.
+ *
+ * So the threshold is deliberately NOT a fixed number alone. It fires on an absolute floor (10 GB,
+ * the figure the README always carried) OR on "you could not build the keepsake right now", which
+ * is the trigger a host can still act on.
+ *
+ * These drive it through `original_size_bytes` rather than a genuinely full disk: the estimate is
+ * pure SQL over that column, so overstating one row moves the accounting the warning reads without
+ * touching a byte on disk.
+ */
+import { test, expect } from '../../fixtures/test';
+import { seedUpload } from '../../helpers/seed';
+import { BASE } from '../../helpers/env';
+
+/** Comfortably larger than any disk this suite could run on. */
+const ABSURD_BYTES = 500_000_000_000_000;
+
+test.describe('Host — low-disk warning', () => {
+  test('a gallery too big to export warns the host, with the numbers', async ({
+    page,
+    host,
+    guest,
+    signIn,
+    db,
+  }) => {
+    const g = await guest('BigShooter');
+    const uploadId = await seedUpload(g.jwt);
+    await db.setUploadSizeBytes(uploadId, ABSURD_BYTES);
+
+    await signIn(page, host);
+    await page.goto('/host');
+
+    const warning = page.getByTestId('low-disk-warning');
+    await expect(warning, 'the host must be warned before releasing').toBeVisible({
+      timeout: 15_000,
+    });
+    // The actionable half: not just "low", but "the keepsake cannot be built".
+    await expect(warning).toContainText(/nicht.*erstellt werden/i);
+    // And the consequence that makes it urgent — the event, not just the download.
+    await expect(warning).toContainText(/gesamte Event/i);
+  });
+
+  test('the API reports the requirement and the verdict together', async ({ host, guest, db }) => {
+    const g = await guest('BigShooter2');
+    const uploadId = await seedUpload(g.jwt);
+    await db.setUploadSizeBytes(uploadId, ABSURD_BYTES);
+
+    const res = await fetch(`${BASE}/api/v1/host/event`, {
+      headers: { Authorization: `Bearer ${host.jwt}` },
+    });
+    expect(res.status).toBe(200);
+    const body = (await res.json()) as {
+      disk_low: boolean;
+      disk_free_bytes: number | null;
+      keepsake_required_bytes: number;
+    };
+
+    expect(body.disk_low).toBe(true);
+    expect(
+      body.keepsake_required_bytes,
+      'both halves are armed by a release, so the requirement covers two archives'
+    ).toBeGreaterThan(ABSURD_BYTES);
+    expect(body.disk_free_bytes).not.toBeNull();
+    expect(body.keepsake_required_bytes).toBeGreaterThan(body.disk_free_bytes!);
+  });
+
+  test('an ordinary gallery shows no warning at all', async ({ page, host, guest, signIn }) => {
+    // The mirror that keeps the above honest. A warning that is always on is a warning nobody
+    // reads — and it would sit at the very top of the dashboard, above the PIN-reset queue.
+    const g = await guest('NormalShooter');
+    await seedUpload(g.jwt);
+
+    await signIn(page, host);
+    await page.goto('/host');
+
+    // Wait for the dashboard to actually be loaded before asserting on an absence.
+    await expect(page.getByRole('heading', { name: 'Host-Dashboard' })).toBeVisible({
+      timeout: 15_000,
+    });
+    await expect(page.getByTestId('low-disk-warning')).toHaveCount(0);
+  });
+});

e2e/specs/04-host/moderation-ui.spec.ts

@@ -0,0 +1,149 @@
+/**
+ * Regression guard — a host must be able to remove a guest's content FROM THE UI.
+ *
+ * `DELETE /host/upload/{id}` and `DELETE /host/comment/{id}` were fully implemented,
+ * transactional, SSE-broadcasting, audit-logged — and had zero frontend callers. The feed's
+ * context sheet offered "Löschen" only when `target.user_id === myUserId`, so the only lever
+ * a host actually had against an unwanted photo was banning the uploader. That is both
+ * disproportionate and ineffective: a ban doesn't retract what was already posted, and
+ * because the ban check runs BEFORE the ownership check on the guest delete route, banning
+ * the author makes their abusive comment permanently undeletable by them too.
+ *
+ * The API side was already covered (04-host/moderation). What was missing is the wiring,
+ * so these tests drive the real UI.
+ */
+import { test, expect } from '../../fixtures/test';
+import { seedUpload, seedComment } from '../../helpers/seed';
+import { BASE } from '../../helpers/env';
+
+test.describe('Host — moderation from the UI', () => {
+  test("a host removes a guest's photo via the feed context sheet", async ({
+    page,
+    host,
+    guest,
+    signIn,
+  }) => {
+    const g = await guest('PhotoOffender');
+    const uploadId = await seedUpload(g.jwt);
+
+    await signIn(page, host);
+    await page.goto('/feed');
+
+    const card = page.locator('article').filter({ hasText: g.displayName }).first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+
+    await card.getByRole('button', { name: 'Mehr Aktionen' }).click();
+    const remove = page.getByRole('button', { name: /beitrag entfernen/i });
+    await expect(remove, 'a host must be offered a removal action on a guest post').toBeVisible();
+    await remove.click();
+
+    const sheet = page.getByTestId('confirm-sheet');
+    await expect(sheet).toBeVisible();
+    // Moderation copy, not "delete my post" copy.
+    await expect(sheet).toContainText(/beitrag entfernen/i);
+    await page.getByTestId('confirm-sheet-confirm').click();
+
+    await expect(card).not.toBeVisible({ timeout: 10_000 });
+
+    // And it is really gone server-side, not just dropped from the local list.
+    const res = await fetch(`${BASE}/api/v1/feed`, {
+      headers: { Authorization: `Bearer ${host.jwt}` },
+    });
+    const body = await res.json();
+    expect(body.uploads.some((u: { id: string }) => u.id === uploadId)).toBe(false);
+  });
+
+  test('a guest is NOT offered any delete action on someone else’s post', async ({
+    page,
+    guest,
+    signIn,
+  }) => {
+    // The mirror that makes the test above meaningful: if this affordance rendered for
+    // everyone, the host test would still pass on a build that shipped moderation to guests.
+    const author = await guest('SomeAuthor');
+    await seedUpload(author.jwt);
+    const viewer = await guest('NosyViewer');
+
+    await signIn(page, viewer);
+    await page.goto('/feed');
+
+    const card = page.locator('article').filter({ hasText: author.displayName }).first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Mehr Aktionen' }).click();
+
+    await expect(page.getByRole('button', { name: /beitrag entfernen/i })).toHaveCount(0);
+    await expect(page.getByRole('button', { name: /^löschen$/i })).toHaveCount(0);
+  });
+
+  test('a promoted guest gets host powers without signing out and back in', async ({
+    page,
+    api,
+    adminToken,
+    guest,
+    signIn,
+  }) => {
+    // The JWT is never reissued — the backend slides the session row forward and treats the
+    // DB row as authoritative. So the token of a promoted guest still claims `role: guest`
+    // for up to 30 days. The UI read that frozen claim, which meant a guest promoted at the
+    // party saw no Host-Dashboard and no moderation actions until they signed out and back
+    // in — while `/me/context` had been handing the client the real role all along.
+    const g = await guest('LatePromotion');
+    await signIn(page, g);
+
+    await page.goto('/account');
+    await expect(page.getByRole('link', { name: /host-dashboard/i })).toHaveCount(0);
+
+    // Promote mid-session. The token in localStorage is deliberately NOT refreshed.
+    await api.setRole(adminToken, g.userId, 'host');
+    const claim = JSON.parse(Buffer.from(g.jwt.split('.')[1], 'base64').toString());
+    expect(
+      claim.role,
+      'the token must still carry the stale claim for this to prove anything'
+    ).toBe('guest');
+
+    await page.reload();
+    await expect(
+      page.getByRole('link', { name: /host-dashboard/i }),
+      'the live role from /me/context must win over the frozen JWT claim'
+    ).toBeVisible({ timeout: 10_000 });
+  });
+
+  test('a host can remove the comment of a guest they have already banned', async ({
+    page,
+    api,
+    host,
+    guest,
+    signIn,
+  }) => {
+    // The deadlock this closes. Ban first, exactly as a host would react to abuse: from then
+    // on the author gets 403 on their own delete, so if the host has no removal affordance
+    // the comment is stuck on screen forever.
+    // The photo belongs to an innocent third party — a ban hides the banned user's OWN
+    // uploads, so if the comment sat on their own photo the whole card would vanish and
+    // there would be nothing left to moderate.
+    const victim = await guest('PhotoOwner');
+    const uploadId = await seedUpload(victim.jwt);
+    const author = await guest('CommentOffender');
+    const commentId = await seedComment(author.jwt, uploadId, 'unangebrachter Kommentar');
+    await api.banUser(host.jwt, author.userId);
+
+    // Confirm the deadlock really exists — the author cannot retract it themselves.
+    const selfDelete = await fetch(`${BASE}/api/v1/comment/${commentId}`, {
+      method: 'DELETE',
+      headers: { Authorization: `Bearer ${author.jwt}` },
+    });
+    expect(selfDelete.status, 'a banned author is blocked from their own delete').toBe(403);
+
+    await signIn(page, host);
+    await page.goto('/feed');
+
+    const card = page.locator('article').filter({ hasText: victim.displayName }).first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Bild vergrößern' }).click();
+
+    const comment = page.getByText('unangebrachter Kommentar');
+    await expect(comment).toBeVisible({ timeout: 10_000 });
+    await page.getByRole('button', { name: 'Kommentar entfernen' }).first().click();
+    await expect(comment).toHaveCount(0, { timeout: 10_000 });
+  });
+});

e2e/specs/04-host/role-identity-reset.spec.ts

@@ -0,0 +1,102 @@
+/**
+ * Regression guard — the role must follow the identity, not the tab.
+ *
+ * The `role` store is a module-level singleton seeded ONCE at import. `goto()` is a
+ * client-side navigation, so leaving and re-joining in the same tab re-imports nothing and
+ * re-runs no `onMount` — the previous user's role simply stayed. A host who left and a
+ * guest who then joined kept `isStaff === true` and were offered "🚫 Beitrag entfernen" on
+ * other people's photos. The backend 403s the delete, so it was a false affordance rather
+ * than a privilege escalation, but `/feed` never fetched `/me/context`, so it never
+ * self-corrected either — it survived until a hard reload.
+ *
+ * The mirror case matters just as much and is easier to forget: a guest who recovers into a
+ * host account must GAIN the affordance without a reload.
+ */
+import { test, expect } from '../../fixtures/test';
+import { seedUpload } from '../../helpers/seed';
+import { JoinPage } from '../../page-objects';
+
+const REMOVE = /beitrag entfernen/i;
+
+test.describe('Role — follows the identity across a same-tab switch', () => {
+  test('a guest joining after a host leaves does NOT inherit host actions', async ({
+    page,
+    host,
+    guest,
+    signIn,
+  }) => {
+    // Someone else's photo — the only kind the removal action is offered on.
+    const author = await guest('RoleAuthor');
+    await seedUpload(author.jwt);
+
+    // 1. Host is signed in and DOES see the moderation action. Establishing this first is
+    //    what makes the negative assertion below meaningful.
+    await signIn(page, host);
+    await page.goto('/feed');
+    const card = page.locator('article').filter({ hasText: author.displayName }).first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Mehr Aktionen' }).click();
+    await expect(page.getByRole('button', { name: REMOVE })).toBeVisible();
+    await page.keyboard.press('Escape');
+
+    // 2. Host leaves, in-app — no reload. This is the path "Event verlassen" takes.
+    await page.goto('/account');
+    await page.getByRole('button', { name: /event verlassen/i }).click();
+    const confirm = page.getByTestId('confirm-sheet-confirm');
+    if (await confirm.isVisible().catch(() => false)) await confirm.click();
+    await page.waitForURL('**/join', { timeout: 10_000 });
+
+    // 3. A brand-new guest joins in the same tab — the real flow, PIN modal and all.
+    const join = new JoinPage(page);
+    await join.joinAs(`Nachzuegler${Date.now() % 100000}`);
+    await join.continueToFeed();
+    await expect(page).toHaveURL(/\/feed$/, { timeout: 15_000 });
+
+    // 4. They must NOT be offered moderation on someone else's photo.
+    const card2 = page.locator('article').filter({ hasText: author.displayName }).first();
+    await expect(card2).toBeVisible({ timeout: 15_000 });
+    await card2.getByRole('button', { name: 'Mehr Aktionen' }).click();
+    await expect(
+      page.getByRole('button', { name: REMOVE }),
+      'a fresh guest must not inherit the previous user’s role'
+    ).toHaveCount(0);
+  });
+
+  test('a guest who recovers into a host account GAINS host actions without a reload', async ({
+    page,
+    api,
+    adminToken,
+    guest,
+    signIn,
+  }) => {
+    // The mirror. If the fix only cleared the role it would pass the test above and still
+    // leave a real host with no moderation until they reloaded.
+    const author = await guest('RoleAuthor2');
+    await seedUpload(author.jwt);
+
+    const futureHost = await guest('WillBeHost');
+    await signIn(page, futureHost);
+    await page.goto('/feed');
+    const card = page.locator('article').filter({ hasText: author.displayName }).first();
+    await expect(card).toBeVisible({ timeout: 15_000 });
+    await card.getByRole('button', { name: 'Mehr Aktionen' }).click();
+    await expect(page.getByRole('button', { name: REMOVE })).toHaveCount(0);
+    await page.keyboard.press('Escape');
+
+    // Promote them server-side. Their resident JWT still claims `role: guest`.
+    await api.setRole(adminToken, futureHost.userId, 'host');
+    const claim = JSON.parse(Buffer.from(futureHost.jwt.split('.')[1], 'base64').toString());
+    expect(claim.role, 'the token must still be stale for this to prove anything').toBe('guest');
+
+    // A plain in-app navigation back to the feed must pick up the live role.
+    await page.goto('/account');
+    await page.goto('/feed');
+    const card2 = page.locator('article').filter({ hasText: author.displayName }).first();
+    await expect(card2).toBeVisible({ timeout: 15_000 });
+    await card2.getByRole('button', { name: 'Mehr Aktionen' }).click();
+    await expect(
+      page.getByRole('button', { name: REMOVE }),
+      'the live role from /me/context must reach the feed'
+    ).toBeVisible({ timeout: 10_000 });
+  });
+});

e2e/specs/05-admin/config.spec.ts

@@ -68,6 +68,40 @@ test.describe('Admin — config API', () => {
     expect(cfg.privacy_note).toBe(note);
     await api.patchConfig(adminToken, { privacy_note: '' });
   });
+  test('quota_tolerance = 0 is rejected, with a pointer to the real off-switch', async ({
+    api,
+    adminToken,
+  }) => {
+    // Zero is inside the documented 0–1 range and catastrophic: the per-user limit is
+    // `free_disk * tolerance / active_uploaders`, so 0 refuses EVERY upload — mid-event, with
+    // "Du hast dein Upload-Limit für dieses Event erreicht", which names the wrong cause
+    // entirely. `storage_quota_enabled` is what an admin reaching for an off-switch wants.
+    const res = await fetch(
+      (process.env.E2E_FRONTEND_URL ?? 'http://localhost:3101') + '/api/v1/admin/config',
+      {
+        method: 'PATCH',
+        headers: { Authorization: `Bearer ${adminToken}`, 'Content-Type': 'application/json' },
+        body: JSON.stringify({ quota_tolerance: '0' }),
+      }
+    );
+    expect(res.status).toBe(400);
+    expect(
+      (await res.text()).toLowerCase(),
+      'the error must name the switch the admin actually wanted'
+    ).toContain('speicher-quote');
+
+    // The value is untouched — validation fully precedes any write.
+    expect((await api.getConfig(adminToken)).quota_tolerance).toBe('0.75');
+  });
+
+  test('a very small quota_tolerance is still accepted', async ({ api, adminToken }) => {
+    // The mirror. Rejecting 0 must not become a floor: small tolerances are how a large disk is
+    // throttled to a sensible per-guest ceiling, and how the quota specs steer it (~1e-5 on a
+    // 174 GB volume). A floor of 0.01 would forbid real configurations to prevent one typo.
+    await api.patchConfig(adminToken, { quota_tolerance: '0.00001' });
+    expect((await api.getConfig(adminToken)).quota_tolerance).toBe('0.00001');
+    await api.patchConfig(adminToken, { quota_tolerance: '0.75' });
+  });
 });
 
 test.describe('Admin — stats', () => {

e2e/specs/06-export/archive-permissions.spec.ts

@@ -0,0 +1,103 @@
+/**
+ * Regression guard — the keepsake extracts to files a guest can actually open.
+ *
+ * `ZipEntryBuilder::new` leaves the external file attribute at zero, and async_zip's host
+ * compatibility defaults to Unix — so every entry in BOTH archives was written with a stored mode
+ * of 0000. `unzip -Z` showed `?---------` on every line.
+ *
+ * Windows Explorer ignores Unix modes, which is exactly why this survived. On Linux and macOS,
+ * `unzip` faithfully applies what the archive asks for, and the guest gets a folder of photos none
+ * of which they can open — plus an index.html the browser refuses with ERR_ACCESS_DENIED.
+ *
+ * Unconditional: it affected every keepsake ever produced, no hostile input required. And it is
+ * invisible server-side — the export succeeds, the ZIP is well-formed, the job writes `done`,
+ * /export/status is green. The only way to see it is to extract the real artifact and try to read
+ * it, which is what this does.
+ *
+ * Found while chasing an unrelated ERR_ACCESS_DENIED that looked like a Playwright quirk.
+ */
+import { test, expect } from '../../fixtures/test';
+import { execFileSync } from 'node:child_process';
+import { mkdtempSync, writeFileSync, rmSync, readFileSync, statSync, readdirSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { seedUpload } from '../../helpers/seed';
+import { BASE } from '../../helpers/env';
+
+/** Walk every file under `dir`, ignoring the archives we dropped there ourselves. */
+function walk(dir: string, skip: string[] = []): string[] {
+  return readdirSync(dir, { withFileTypes: true }).flatMap((e) => {
+    const p = join(dir, e.name);
+    if (e.isDirectory()) return walk(p, skip);
+    return skip.includes(e.name) ? [] : [p];
+  });
+}
+
+test.describe('Export — the archives extract to readable files', () => {
+  test('every entry in both keepsake archives is owner-readable', async ({ host, guest, db }) => {
+    test.setTimeout(120_000);
+    const bearer = { Authorization: `Bearer ${host.jwt}` };
+
+    const g = await guest('Archivist');
+    const id = await seedUpload(g.jwt, { caption: 'ein Foto' });
+    await expect.poll(() => db.compressionStatus(id), { timeout: 30_000 }).toBe('done');
+
+    expect(
+      (await fetch(`${BASE}/api/v1/host/gallery/release`, { method: 'POST', headers: bearer }))
+        .status
+    ).toBe(204);
+
+    await expect
+      .poll(
+        async () => {
+          const res = await fetch(`${BASE}/api/v1/export/status`, { headers: bearer });
+          const s = await res.json();
+          return s.zip?.status === 'done' && s.html?.status === 'done';
+        },
+        { timeout: 90_000, intervals: [500] }
+      )
+      .toBe(true);
+
+    for (const kind of ['zip', 'html'] as const) {
+      const ticketRes = await fetch(`${BASE}/api/v1/export/ticket`, {
+        method: 'POST',
+        headers: bearer,
+      });
+      const { ticket } = (await ticketRes.json()) as { ticket: string };
+      const dl = await fetch(`${BASE}/api/v1/export/${kind}?ticket=${encodeURIComponent(ticket)}`);
+      expect(dl.status, `downloading the ${kind} archive`).toBe(200);
+
+      const dir = mkdtempSync(join(tmpdir(), `eventsnap-perms-${kind}-`));
+      try {
+        const zipPath = join(dir, 'archive.zip');
+        writeFileSync(zipPath, Buffer.from(await dl.arrayBuffer()));
+
+        // The mode as STORED in the archive — this is what a guest's unzip will apply. Reading it
+        // from the central directory catches the defect even on a filesystem that would mask it.
+        const listing = execFileSync('unzip', ['-Z', zipPath], { encoding: 'utf8' });
+        const modes = listing
+          .split('\n')
+          .filter((l) => /^[?d-][rwx-]{9}\s/.test(l))
+          .map((l) => l.slice(0, 10));
+        expect(modes.length, `${kind}: no entries listed`).toBeGreaterThan(0);
+        for (const m of modes) {
+          expect(m, `${kind}: an entry is stored mode ${m} — the guest cannot open it`).toMatch(
+            /^.r[w-]-/
+          );
+        }
+
+        // And extraction really does produce readable files.
+        execFileSync('unzip', ['-qo', zipPath, '-d', dir]);
+        const files = walk(dir, ['archive.zip']);
+        expect(files.length, `${kind}: nothing extracted`).toBeGreaterThan(0);
+        for (const f of files) {
+          expect(statSync(f).mode & 0o400, `${f} is not owner-readable`).toBeTruthy();
+          // The assertion that matters to a guest: the bytes actually come out.
+          expect(() => readFileSync(f)).not.toThrow();
+        }
+      } finally {
+        rmSync(dir, { recursive: true, force: true });
+      }
+    }
+  });
+});

e2e/specs/06-export/download-iframe.spec.ts

@@ -0,0 +1,103 @@
+/**
+ * Regression guard — the keepsake download must actually download, in WebKit.
+ *
+ * The bug this exists to catch: `/export` streams the archive by pointing a HIDDEN,
+ * SAME-ORIGIN iframe at `/api/v1/export/zip` (deliberately — a top-level navigation to a
+ * 404/429 would unload the PWA). Caddy stamped a site-wide `X-Frame-Options: DENY` that
+ * also covered `/api/*`. Blink hands a `Content-Disposition: attachment` response to the
+ * download manager at the network layer, so Chromium never noticed; WebKit enforces XFO on
+ * the frame navigation FIRST and aborts the load. Result: on iOS Safari — the app's primary
+ * platform — tapping Download did nothing, silently, with no error anywhere.
+ *
+ * Why the old suite was structurally blind to it:
+ *   - `06-export` ran on `chromium-desktop` only (webkit-iphone's testMatch excluded it),
+ *   - and no test in the entire suite ever CLICKED a download button; every archive
+ *     assertion used Node `fetch`, which has no frame and therefore no XFO enforcement.
+ *
+ * So this spec must keep both properties to be worth anything: a real click, in WebKit.
+ */
+import { test, expect } from '../../fixtures/test';
+import { ExportPage } from '../../page-objects';
+import { BASE } from '../../helpers/env';
+
+const SLUG = 'e2e-test-event';
+
+function post(path: string, jwt: string) {
+  return fetch(BASE + path, { method: 'POST', headers: { Authorization: `Bearer ${jwt}` } });
+}
+
+/** The real export job runs image processing; give it head-room over the tiny fixtures. */
+async function releaseAndWait(jwt: string) {
+  expect((await post('/api/v1/host/gallery/release', jwt)).status).toBe(204);
+  await expect
+    .poll(
+      async () => {
+        const res = await fetch(BASE + '/api/v1/export/status', {
+          headers: { Authorization: `Bearer ${jwt}` },
+        });
+        const s = await res.json();
+        return s.released === true && s.zip?.status === 'done';
+      },
+      { timeout: 60_000, intervals: [500] }
+    )
+    .toBe(true);
+}
+
+test.describe('Export — the download actually fires in the browser', () => {
+  test.slow();
+
+  test('clicking Download triggers a real download event', async ({ page, host, signIn, db }) => {
+    await db.setExportReleased(SLUG, false);
+    await releaseAndWait(host.jwt);
+
+    await signIn(page, host);
+    const exportPage = new ExportPage(page);
+    await exportPage.goto();
+    await expect(exportPage.zipDownloadButton).toBeEnabled({ timeout: 10_000 });
+
+    // Capture the frame-level refusal that XFO produces, so a failure reports the CAUSE
+    // rather than just a timeout. WebKit logs "Refused to display ... in a frame because it
+    // set 'X-Frame-Options'"; Chromium logs nothing here, which is the whole problem.
+    const refusals: string[] = [];
+    page.on('console', (m) => {
+      if (/X-Frame-Options|Refused to display/i.test(m.text())) refusals.push(m.text());
+    });
+
+    const downloadPromise = page.waitForEvent('download', { timeout: 30_000 });
+    await exportPage.zipDownloadButton.click();
+
+    const download = await downloadPromise.catch((err) => {
+      throw new Error(
+        `No download event fired after clicking the ZIP button.` +
+          (refusals.length
+            ? ` The browser refused the iframe navigation: ${refusals.join(' | ')}`
+            : ' No X-Frame-Options refusal was logged; check the ticket/readiness path.') +
+          `\n${err}`
+      );
+    });
+
+    expect(download.suggestedFilename()).toMatch(/\.zip$/i);
+    // The stream must produce real bytes, not a zero-length placeholder.
+    const path = await download.path();
+    expect(path).toBeTruthy();
+    expect(refusals, 'no frame should have been refused').toEqual([]);
+  });
+
+  test('the export endpoints are framable same-origin; everything else stays DENY', async () => {
+    // Locks the Caddy carve-out itself, independently of any browser. Cheap, and it fails
+    // loudly at the exact layer that regressed if someone reinstates a blanket DENY.
+    for (const path of ['/api/v1/export/zip', '/api/v1/export/html']) {
+      const res = await fetch(BASE + path);
+      expect(res.headers.get('x-frame-options')?.toUpperCase(), `${path} must be framable`).toBe(
+        'SAMEORIGIN'
+      );
+    }
+
+    for (const path of ['/', '/api/v1/feed', '/api/v1/event']) {
+      const res = await fetch(BASE + path);
+      expect(res.headers.get('x-frame-options')?.toUpperCase(), `${path} must stay DENY`).toBe(
+        'DENY'
+      );
+    }
+  });
+});

e2e/specs/06-export/exif-orientation.spec.ts

@@ -0,0 +1,117 @@
+/**
+ * Regression guard — the keepsake must not be sideways.
+ *
+ * Round 1 taught the compression worker to apply EXIF orientation, which fixed the live app
+ * (feed preview + diashow display). The export worker was missed: it does NOT reuse those
+ * derivatives — it re-decodes the originals itself with `image::open`, which ignores the
+ * orientation tag — and then re-encodes to JPEG, which drops the tag, so the viewer has no
+ * way to recover it.
+ *
+ * The resulting damage was oddly shaped, which is what made it read as a viewer bug:
+ *   - Gallery.zip originals            → correct (byte-copied, EXIF intact)
+ *   - Memories viewer grid thumbnails  → ALWAYS sideways
+ *   - Memories viewer full image >5 MB → sideways (re-encoded at 2000px)
+ *   - Memories viewer full image ≤5 MB → correct (streamed byte-for-byte)
+ *
+ * So clicking a small photo silently "fixed" it and a large one didn't. This pins the
+ * thumbnail, which is the path every photo takes.
+ */
+import { test, expect } from '../../fixtures/test';
+import { uploadRaw } from '../../helpers/upload-client';
+import { BASE } from '../../helpers/env';
+import { execFileSync } from 'node:child_process';
+import { mkdtempSync, readFileSync, writeFileSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+
+// 40x20 landscape pixels tagged Orientation=6 ("rotate 90° CW to display"), so anything
+// that honours the tag emits a PORTRAIT derivative.
+const EXIF_FIXTURE = join(process.cwd(), 'fixtures', 'media', 'portrait-exif6.jpg');
+
+/** Pixel dimensions from a JPEG's SOF marker — avoids an image dep for one assertion. */
+function jpegSize(buf: Buffer): { width: number; height: number } {
+  let i = 2;
+  while (i < buf.length) {
+    if (buf[i] !== 0xff) {
+      i++;
+      continue;
+    }
+    const marker = buf[i + 1];
+    if (marker >= 0xc0 && marker <= 0xcf && marker !== 0xc4 && marker !== 0xc8 && marker !== 0xcc) {
+      return { height: buf.readUInt16BE(i + 5), width: buf.readUInt16BE(i + 7) };
+    }
+    i += 2 + buf.readUInt16BE(i + 2);
+  }
+  throw new Error('no SOF marker found — not a JPEG?');
+}
+
+test.describe('Export — EXIF orientation in the keepsake', () => {
+  test('the Memories viewer thumbnail of a rotated photo is upright', async ({ host, db }) => {
+    test.setTimeout(90_000);
+    const bearer = { Authorization: `Bearer ${host.jwt}` };
+
+    const src = readFileSync(EXIF_FIXTURE);
+    // Sanity: the SOURCE really is stored landscape, or this test proves nothing.
+    const srcSize = jpegSize(src);
+    expect(srcSize.width).toBeGreaterThan(srcSize.height);
+
+    const up = await uploadRaw(host.jwt, src, {
+      filename: 'hochkant.jpg',
+      contentType: 'image/jpeg',
+      caption: 'hochkant',
+    });
+    expect(up.status).toBe(201);
+    const { id } = (await up.json()) as { id: string };
+    await expect.poll(() => db.compressionStatus(id), { timeout: 30_000 }).toBe('done');
+
+    const rel = await fetch(`${BASE}/api/v1/host/gallery/release`, {
+      method: 'POST',
+      headers: bearer,
+    });
+    expect(rel.status).toBe(204);
+
+    await expect
+      .poll(
+        async () => {
+          const res = await fetch(`${BASE}/api/v1/export/status`, { headers: bearer });
+          return (await res.json()).html?.status;
+        },
+        { timeout: 60_000, intervals: [500] }
+      )
+      .toBe('done');
+
+    const ticketRes = await fetch(`${BASE}/api/v1/export/ticket`, {
+      method: 'POST',
+      headers: bearer,
+    });
+    const { ticket } = (await ticketRes.json()) as { ticket: string };
+    const dl = await fetch(`${BASE}/api/v1/export/html?ticket=${encodeURIComponent(ticket)}`);
+    expect(dl.status).toBe(200);
+
+    const dir = mkdtempSync(join(tmpdir(), 'eventsnap-exif-'));
+    try {
+      const zipPath = join(dir, 'Memories.zip');
+      writeFileSync(zipPath, Buffer.from(await dl.arrayBuffer()));
+
+      const entries = execFileSync('unzip', ['-Z1', zipPath], { encoding: 'utf8' })
+        .split('\n')
+        .filter(Boolean);
+      const thumbEntry = entries.find((e) => e.includes(`${id}_thumb`));
+      expect(thumbEntry, `no thumbnail for ${id} in Memories.zip`).toBeTruthy();
+
+      // `-p` streams the entry to stdout. Extracting to disk instead fails with EACCES:
+      // the archive preserves the container's file mode, which the test user can't read.
+      const thumb = execFileSync('unzip', ['-p', zipPath, thumbEntry!], {
+        maxBuffer: 64 * 1024 * 1024,
+      });
+      const { width, height } = jpegSize(thumb);
+
+      expect(
+        height,
+        `the keepsake grid thumbnail is ${width}x${height} — EXIF orientation was not applied`
+      ).toBeGreaterThan(width);
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});

e2e/specs/06-export/failure-reason-visible.spec.ts

@@ -0,0 +1,95 @@
+/**
+ * Regression guard — when the keepsake fails to build, the HOST must be told why.
+ *
+ * `/export/status` reported `{status, progress_pct}` and nothing else, so the host dashboard could
+ * only ever render "Keepsake-Erstellung fehlgeschlagen." next to an "Erneut versuchen" button. The
+ * reason WAS being written — `mark_failed` stores it on the job row — but it surfaced solely in the
+ * admin dashboard's job list. The host is the person who releases the gallery, owns the retry
+ * button, and is standing at the venue; the admin may be someone else entirely, or the same person
+ * without the password to hand.
+ *
+ * That matters most for the failure this shipped alongside: the export disk preflight. Its message
+ * names the two numbers that decide what to do ("benötigt ca. X GB, frei sind Y GB"), and without
+ * it "Erneut versuchen" fails identically, forever, with no hint that the answer is free some space.
+ *
+ * These drive the real UI and the real endpoint — the plumbing is four hops (SQL → handler JSON →
+ * store type → Svelte branch) and any one of them dropping the field restores the silent version.
+ */
+import { test, expect } from '../../fixtures/test';
+import { BASE } from '../../helpers/env';
+
+const SLUG = 'e2e-test-event';
+const DISK_REASON =
+  'Nicht genug Speicherplatz für das Keepsake: benötigt ca. 42.0 GB, frei sind 3.0 GB. ' +
+  'Bitte Speicher freigeben und das Keepsake anschließend neu erstellen.';
+
+test.describe('Export — a failed keepsake explains itself to the host', () => {
+  test('the failure reason reaches /export/status', async ({ host, db }) => {
+    await db.setExportReleased(SLUG, true);
+    await db.fakeExportJob(SLUG, 'zip', 'failed', DISK_REASON);
+    await db.fakeExportJob(SLUG, 'html', 'failed', DISK_REASON);
+
+    const res = await fetch(`${BASE}/api/v1/export/status`, {
+      headers: { Authorization: `Bearer ${host.jwt}` },
+    });
+    expect(res.status).toBe(200);
+    const body = (await res.json()) as {
+      zip: { status: string; error_message: string | null };
+      html: { status: string; error_message: string | null };
+    };
+
+    expect(body.zip.status).toBe('failed');
+    expect(
+      body.zip.error_message,
+      'the reason must travel with the status, not live only in the admin job list'
+    ).toBe(DISK_REASON);
+    expect(body.html.error_message).toBe(DISK_REASON);
+  });
+
+  test('a succeeding export carries no stale reason', async ({ host, db }) => {
+    // The mirror that keeps the above honest: a handler that returned `error_message`
+    // unconditionally would pass the first test while showing an error next to a green
+    // "Keepsake ist bereit." Rows keep their last message until they are re-armed, so this is a
+    // real state, not a hypothetical one.
+    await db.setExportReleased(SLUG, true);
+    await db.fakeExportJob(SLUG, 'zip', 'failed', DISK_REASON);
+    await db.fakeExportJob(SLUG, 'zip', 'done', DISK_REASON);
+
+    const res = await fetch(`${BASE}/api/v1/export/status`, {
+      headers: { Authorization: `Bearer ${host.jwt}` },
+    });
+    const body = (await res.json()) as { zip: { status: string; error_message: string | null } };
+    expect(body.zip.status).toBe('done');
+    expect(
+      body.zip.error_message,
+      'a message left on a row that has since succeeded must not be shown'
+    ).toBeNull();
+  });
+
+  test('the host dashboard renders the reason under the failure', async ({
+    page,
+    host,
+    signIn,
+    db,
+  }) => {
+    await db.setExportReleased(SLUG, true);
+    await db.fakeExportJob(SLUG, 'zip', 'failed', DISK_REASON);
+    await db.fakeExportJob(SLUG, 'html', 'failed', DISK_REASON);
+
+    await signIn(page, host);
+    await page.goto('/host');
+
+    await expect(page.getByText(/Keepsake-Erstellung fehlgeschlagen/i)).toBeVisible({
+      timeout: 15_000,
+    });
+    // The actionable half — the numbers, not just the verdict.
+    await expect(
+      page.getByText(/Nicht genug Speicherplatz/i),
+      'the host must see WHY, next to the only button they have'
+    ).toBeVisible();
+    await expect(page.getByText(/3\.0 GB/)).toBeVisible();
+
+    // And the retry button is still mounted — it is deliberately outside the status branches.
+    await expect(page.getByTestId('export-rebuild')).toBeVisible();
+  });
+});

e2e/specs/06-export/viewer-caption-injection.spec.ts

@@ -0,0 +1,125 @@
+/**
+ * Regression guard — a guest-authored caption cannot brick the offline keepsake.
+ *
+ * The viewer's data is inlined as `<script>window.__EXPORT_DATA__={…};</script>` (it must be:
+ * guests open index.html over file://, where a cross-origin fetch of a sibling data.json is
+ * blocked). Captions and comments are guest text and land in that payload.
+ *
+ * The escape used to be `</` → `<\/`. Against XSS that holds — `</script><img src=x onerror=…>`
+ * round-trips inert. It does NOT stop the caption steering the HTML TOKENIZER: `<!--<script` with
+ * no later `-->` drives the parser into script-data-double-escaped state, where the template's own
+ * `</script>` steps back to script-data-escaped instead of closing the element. Everything after —
+ * including the viewer bundle — is swallowed as script data. Nothing executes and nothing leaks;
+ * `__EXPORT_DATA__` is never assigned and the keepsake renders blank.
+ *
+ * What makes it worth a browser-level test rather than a unit test alone: the failure is SILENT and
+ * POST-DISTRIBUTION. The export succeeds, the ZIP is well-formed, the job writes `done`,
+ * /export/status is green, and the host hands out a file that only fails when a guest
+ * double-clicks it — in every copy, unfixably. It is not visible by reading the escape. It is only
+ * visible by running a real parser over the real artifact, which is what this does: release, pull
+ * the actual Memories.zip, extract index.html, open it over file:// in Chromium, and assert the
+ * viewer actually booted.
+ *
+ * The near-miss worth recording: `<!--<script>alert(1)</script>-->` comes back CLEAN, because the
+ * trailing `-->` returns the parser to script-data state. A probe using the terminated form
+ * quietly repairs the very thing it is testing for. Only the unterminated variant exposes it.
+ */
+import { test, expect } from '../../fixtures/test';
+import { execFileSync } from 'node:child_process';
+import { mkdtempSync, writeFileSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { seedUpload } from '../../helpers/seed';
+import { BASE } from '../../helpers/env';
+
+/** Unterminated on purpose — see the header. The terminated form self-repairs. */
+const TOKENIZER_PAYLOAD = '<!--<script';
+/** The classic break-out. Already handled, kept so the fix can never regress on it. */
+const BREAKOUT_PAYLOAD = '</script><img src=x onerror=window.__XSS__=1>';
+
+test.describe('Export — a caption cannot brick the keepsake viewer', () => {
+  test('the exported viewer boots with a tokenizer-hostile caption in it', async ({
+    page,
+    host,
+    guest,
+    db,
+  }) => {
+    test.setTimeout(120_000);
+    const bearer = { Authorization: `Bearer ${host.jwt}` };
+
+    const g = await guest('Trickster');
+    const a = await seedUpload(g.jwt, { caption: TOKENIZER_PAYLOAD });
+    const b = await seedUpload(g.jwt, { caption: BREAKOUT_PAYLOAD });
+    for (const id of [a, b]) {
+      await expect.poll(() => db.compressionStatus(id), { timeout: 30_000 }).toBe('done');
+    }
+
+    expect(
+      (await fetch(`${BASE}/api/v1/host/gallery/release`, { method: 'POST', headers: bearer }))
+        .status
+    ).toBe(204);
+
+    await expect
+      .poll(
+        async () => {
+          const res = await fetch(`${BASE}/api/v1/export/status`, { headers: bearer });
+          return (await res.json()).html?.status;
+        },
+        { timeout: 90_000, intervals: [500] }
+      )
+      .toBe('done');
+
+    const ticketRes = await fetch(`${BASE}/api/v1/export/ticket`, {
+      method: 'POST',
+      headers: bearer,
+    });
+    const { ticket } = (await ticketRes.json()) as { ticket: string };
+    const dl = await fetch(`${BASE}/api/v1/export/html?ticket=${encodeURIComponent(ticket)}`);
+    expect(dl.status).toBe(200);
+
+    const dir = mkdtempSync(join(tmpdir(), 'eventsnap-viewer-'));
+    try {
+      const zipPath = join(dir, 'Memories.zip');
+      writeFileSync(zipPath, Buffer.from(await dl.arrayBuffer()));
+      // Extract the WHOLE archive: index.html pulls in the viewer's own JS/CSS, and the point of
+      // this test is that those later resources are still reachable by the parser.
+      execFileSync('unzip', ['-qo', zipPath, '-d', dir]);
+
+      // file://, not http://. That is how a guest actually opens the keepsake, and it is the
+      // whole reason the data is inlined rather than fetched from a sibling data.json.
+      let xss = false;
+      page.on('dialog', (d) => {
+        xss = true;
+        void d.dismiss();
+      });
+      await page.goto('file://' + join(dir, 'index.html'));
+
+      // 1. The payload was assigned at all. This is the assertion that fails on the old escape —
+      //    the second script block is never reached, so the global stays undefined.
+      const captions = await page.evaluate(() => {
+        const d = (window as unknown as { __EXPORT_DATA__?: { posts?: { caption?: string }[] } })
+          .__EXPORT_DATA__;
+        return d?.posts?.map((p) => p.caption ?? '') ?? null;
+      });
+      expect(captions, '__EXPORT_DATA__ was never assigned — the viewer is bricked').not.toBeNull();
+
+      // 2. The captions survived verbatim. The escape is a transport encoding, not a sanitiser:
+      //    a guest's text has to come back exactly, or we have silently rewritten their words.
+      expect(captions).toContain(TOKENIZER_PAYLOAD);
+      expect(captions).toContain(BREAKOUT_PAYLOAD);
+
+      // 3. And nothing executed.
+      expect(
+        await page.evaluate(() => (window as unknown as { __XSS__?: number }).__XSS__ === 1),
+        'the caption must be inert, not merely non-fatal'
+      ).toBe(false);
+      expect(xss).toBe(false);
+
+      // 4. The viewer actually rendered — the whole document parsed, not just the head. If the
+      //    tokenizer had swallowed the bundle, the body would be empty of viewer output.
+      await expect(page.locator('body')).not.toBeEmpty();
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});

e2e/specs/07-adversarial/ddos.spec.ts

@@ -15,7 +15,15 @@ test.describe('Adversarial — small-scale abuse', () => {
     await api.patchConfig(adminToken, { rate_limits_enabled: 'true', join_rate_enabled: 'true' });
   });
 
-  test('20 parallel /join from one IP — rate limiter catches the excess', async () => {
+  test('a /join flood from one IP is caught by the per-IP ceiling', async ({ api, adminToken }) => {
+    // This used to assert that 20 joins from one IP produced 429s under a 5/min per-IP
+    // bucket. That "protection" was the bug: at a venue every guest shares one public IP,
+    // so it turned real arriving guests away (see 01-auth/rate-limit-shared-nat). The
+    // anti-spam bucket is now per (ip, name); what remains per-IP is a loose ceiling whose
+    // job is only to bound raw volume. Squeeze the ceiling so a flood is reproducible here
+    // without firing 60+ requests.
+    await api.patchConfig(adminToken, { join_ip_rate_per_min: '5' });
+
     const requests = Array.from({ length: 20 }, (_, i) =>
       fetch(`${BASE}/api/v1/join`, {
         method: 'POST',
@@ -24,7 +32,7 @@ test.describe('Adversarial — small-scale abuse', () => {
       })
     );
     const statuses = (await Promise.all(requests)).map((r) => r.status);
-    // 5/min limit → at least some should be 429.
+    // Ceiling of 5 → the excess must be shed.
     expect(statuses.filter((s) => s === 429).length).toBeGreaterThan(0);
     // Server stays up — at least one succeeded.
     expect(statuses.some((s) => s === 201 || s === 409)).toBe(true);

e2e/specs/07-adversarial/media-gating.spec.ts

@@ -45,6 +45,23 @@ test.describe('Media gating — moderation revokes preview access (F2)', () => {
     const direct = await fetch(`${BASE}/media/previews/${id}.jpg`);
     expect(direct.status, 'direct /media/previews must be blocked').toBe(404);
 
+    // …and it must stay blocked under percent-encoding. The block used to be four
+    // `nest_service("/media/previews", 404)` route matches sitting above a `/media`
+    // ServeDir. axum routes on the RAW path while ServeDir percent-decodes afterwards, so
+    // ONE escaped byte (`%70` = `p`) missed every blocker, fell through to the ServeDir,
+    // and was decoded back to `previews/` on disk — serving the bytes unauthenticated.
+    // Asserting only the literal spelling is what let that sit here undetected.
+    for (const variant of [
+      `/media/%70reviews/${id}.jpg`, // p
+      `/media/p%72eviews/${id}.jpg`, // r — any position works
+      `/media/%64isplays/${id}.jpg`, // d
+      `/media/%74humbnails/${id}.jpg`, // t
+      `/media/%6Friginals/${id}.jpg`, // o
+    ]) {
+      const res = await fetch(`${BASE}${variant}`, { redirect: 'manual' });
+      expect(res.status, `${variant} must not bypass the media block`).toBe(404);
+    }
+
     // Host deletes the upload → the preview must stop being served.
     const del = await fetch(`${BASE}/api/v1/host/upload/${id}`, {
       method: 'DELETE',

frontend/export-viewer/index.html

@@ -0,0 +1,12 @@
+<!doctype html>
+<html lang="de">
+	<head>
+		<meta charset="utf-8" />
+		<meta name="viewport" content="width=device-width, initial-scale=1" />
+		<title>EventSnap — Galerie</title>
+	</head>
+	<body>
+		<div id="app"></div>
+		<script type="module" src="/src/standalone.ts"></script>
+	</body>
+</html>

frontend/export-viewer/package-lock.json

@@ -15,7 +15,8 @@
 				"svelte": "^5.54.0",
 				"tailwindcss": "^4.2.2",
 				"typescript": "^5.9.3",
-				"vite": "^7.3.1"
+				"vite": "^7.3.1",
+				"vite-plugin-singlefile": "^2.3.3"
 			}
 		},
 		"node_modules/@esbuild/aix-ppc64": {
@@ -1318,6 +1319,19 @@
 				"node": ">= 0.4"
 			}
 		},
+		"node_modules/braces": {
+			"version": "3.0.3",
+			"resolved": "https://registry.npmjs.org/braces/-/braces-3.0.3.tgz",
+			"integrity": "sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"fill-range": "^7.1.1"
+			},
+			"engines": {
+				"node": ">=8"
+			}
+		},
 		"node_modules/clsx": {
 			"version": "2.1.1",
 			"resolved": "https://registry.npmjs.org/clsx/-/clsx-2.1.1.tgz",
@@ -1457,6 +1471,19 @@
 				}
 			}
 		},
+		"node_modules/fill-range": {
+			"version": "7.1.1",
+			"resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.1.1.tgz",
+			"integrity": "sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"to-regex-range": "^5.0.1"
+			},
+			"engines": {
+				"node": ">=8"
+			}
+		},
 		"node_modules/fsevents": {
 			"version": "2.3.3",
 			"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz",
@@ -1479,6 +1506,16 @@
 			"dev": true,
 			"license": "ISC"
 		},
+		"node_modules/is-number": {
+			"version": "7.0.0",
+			"resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz",
+			"integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==",
+			"dev": true,
+			"license": "MIT",
+			"engines": {
+				"node": ">=0.12.0"
+			}
+		},
 		"node_modules/is-reference": {
 			"version": "3.0.3",
 			"resolved": "https://registry.npmjs.org/is-reference/-/is-reference-3.0.3.tgz",
@@ -1787,6 +1824,33 @@
 				"@jridgewell/sourcemap-codec": "^1.5.5"
 			}
 		},
+		"node_modules/micromatch": {
+			"version": "4.0.8",
+			"resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.8.tgz",
+			"integrity": "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"braces": "^3.0.3",
+				"picomatch": "^2.3.1"
+			},
+			"engines": {
+				"node": ">=8.6"
+			}
+		},
+		"node_modules/micromatch/node_modules/picomatch": {
+			"version": "2.3.2",
+			"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.2.tgz",
+			"integrity": "sha512-V7+vQEJ06Z+c5tSye8S+nHUfI51xoXIXjHQ99cQtKUkQqqO1kO/KCJUfZXuB47h/YBlDhah2H3hdUGXn8ie0oA==",
+			"dev": true,
+			"license": "MIT",
+			"engines": {
+				"node": ">=8.6"
+			},
+			"funding": {
+				"url": "https://github.com/sponsors/jonschlinkert"
+			}
+		},
 		"node_modules/mrmime": {
 			"version": "2.0.1",
 			"resolved": "https://registry.npmjs.org/mrmime/-/mrmime-2.0.1.tgz",
@@ -2021,6 +2085,19 @@
 				"url": "https://github.com/sponsors/SuperchupuDev"
 			}
 		},
+		"node_modules/to-regex-range": {
+			"version": "5.0.1",
+			"resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz",
+			"integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"is-number": "^7.0.0"
+			},
+			"engines": {
+				"node": ">=8.0"
+			}
+		},
 		"node_modules/totalist": {
 			"version": "3.0.1",
 			"resolved": "https://registry.npmjs.org/totalist/-/totalist-3.0.1.tgz",
@@ -2122,6 +2199,28 @@
 				}
 			}
 		},
+		"node_modules/vite-plugin-singlefile": {
+			"version": "2.3.3",
+			"resolved": "https://registry.npmjs.org/vite-plugin-singlefile/-/vite-plugin-singlefile-2.3.3.tgz",
+			"integrity": "sha512-XVnGH0QzbOa8fxRSsHdCarVN1BSBXNi7uLMQYlrGRN5apdHkk62XQWRJhVever0lnfuyBkwn+kvVChdm/OoOUg==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"micromatch": "^4.0.8"
+			},
+			"engines": {
+				"node": ">18.0.0"
+			},
+			"peerDependencies": {
+				"rollup": "^4.59.0",
+				"vite": "^5.4.21 || ^6.0.0 || ^7.0.0 || ^8.0.0"
+			},
+			"peerDependenciesMeta": {
+				"rollup": {
+					"optional": true
+				}
+			}
+		},
 		"node_modules/vitefu": {
 			"version": "1.1.3",
 			"resolved": "https://registry.npmjs.org/vitefu/-/vitefu-1.1.3.tgz",

frontend/export-viewer/package.json

@@ -5,7 +5,8 @@
 	"type": "module",
 	"scripts": {
 		"dev": "vite dev",
-		"build": "vite build",
+		"build": "vite build --config vite.standalone.config.js",
+		"build:sveltekit": "vite build",
 		"preview": "vite preview",
 		"prepare": "svelte-kit sync || echo ''"
 	},
@@ -17,6 +18,7 @@
 		"svelte": "^5.54.0",
 		"tailwindcss": "^4.2.2",
 		"typescript": "^5.9.3",
-		"vite": "^7.3.1"
+		"vite": "^7.3.1",
+		"vite-plugin-singlefile": "^2.3.3"
 	}
 }

frontend/export-viewer/src/lib/types.ts

@@ -2,6 +2,9 @@ export interface ViewerData {
 	event: {
 		name: string;
 		exported_at: string;
+		// Mirrors the live COMMENTS_ENABLED flag. Older exports predate this field, so
+		// treat a missing value as enabled (`?? true`) to preserve their comment UI.
+		comments_enabled?: boolean;
 	};
 	posts: ViewerPost[];
 }

frontend/export-viewer/src/routes/+page.svelte

@@ -31,6 +31,9 @@
 
 	let posts = $derived(data?.posts ?? []);
 
+	// Mirror the live COMMENTS_ENABLED flag. Missing on older exports → treat as enabled.
+	let commentsEnabled = $derived(data?.event.comments_enabled ?? true);
+
 	let allTags = $derived.by(() => {
 		// eslint-disable-next-line svelte/prefer-svelte-reactivity -- local throwaway counter inside a $derived.by; never stored in $state.
 		const freq = new Map<string, number>();
@@ -99,9 +102,18 @@
 
 	onMount(async () => {
 		try {
-			const res = await fetch('./data.json');
-			if (!res.ok) throw new Error(`HTTP ${res.status}`);
-			data = await res.json();
+			// The keepsake is opened by double-clicking index.html (file://), where a
+			// cross-origin `fetch()` is blocked. The export injects the data as a global
+			// so it's available without any network request; fall back to fetching
+			// data.json only when the viewer is actually served over http(s).
+			const injected = (globalThis as { __EXPORT_DATA__?: ViewerData }).__EXPORT_DATA__;
+			if (injected) {
+				data = injected;
+			} else {
+				const res = await fetch('./data.json');
+				if (!res.ok) throw new Error(`HTTP ${res.status}`);
+				data = await res.json();
+			}
 		} catch {
 			error =
 				'Daten konnten nicht geladen werden. Stelle sicher, dass data.json im selben Ordner liegt.';
@@ -541,22 +553,24 @@
 								</svg>
 								{post.likes}
 							</span>
-							<span class="flex items-center gap-1.5 text-sm font-medium text-gray-500">
-								<svg
-									class="h-5 w-5"
-									fill="none"
-									viewBox="0 0 24 24"
-									stroke="currentColor"
-									stroke-width="2"
-								>
-									<path
-										stroke-linecap="round"
-										stroke-linejoin="round"
-										d="M8 12h.01M12 12h.01M16 12h.01M21 12c0 4.418-4.03 8-9 8a9.863 9.863 0 01-4.255-.949L3 20l1.395-3.72C3.512 15.042 3 13.574 3 12c0-4.418 4.03-8 9-8s9 3.582 9 8z"
-									/>
-								</svg>
-								{post.comments.length}
-							</span>
+							{#if commentsEnabled}
+								<span class="flex items-center gap-1.5 text-sm font-medium text-gray-500">
+									<svg
+										class="h-5 w-5"
+										fill="none"
+										viewBox="0 0 24 24"
+										stroke="currentColor"
+										stroke-width="2"
+									>
+										<path
+											stroke-linecap="round"
+											stroke-linejoin="round"
+											d="M8 12h.01M12 12h.01M16 12h.01M21 12c0 4.418-4.03 8-9 8a9.863 9.863 0 01-4.255-.949L3 20l1.395-3.72C3.512 15.042 3 13.574 3 12c0-4.418 4.03-8 9-8s9 3.582 9 8z"
+										/>
+									</svg>
+									{post.comments.length}
+								</span>
+							{/if}
 						</div>
 
 						<!-- Caption -->
@@ -632,17 +646,24 @@
 										</svg>
 										{post.likes}
 									</span>
-									<span class="flex items-center gap-0.5">
-										<svg class="h-3.5 w-3.5" fill="none" viewBox="0 0 24 24" stroke="currentColor">
-											<path
-												stroke-linecap="round"
-												stroke-linejoin="round"
-												stroke-width="2"
-												d="M8 12h.01M12 12h.01M16 12h.01M21 12c0 4.418-4.03 8-9 8a9.863 9.863 0 01-4.255-.949L3 20l1.395-3.72C3.512 15.042 3 13.574 3 12c0-4.418 4.03-8 9-8s9 3.582 9 8z"
-											/>
-										</svg>
-										{post.comments.length}
-									</span>
+									{#if commentsEnabled}
+										<span class="flex items-center gap-0.5">
+											<svg
+												class="h-3.5 w-3.5"
+												fill="none"
+												viewBox="0 0 24 24"
+												stroke="currentColor"
+											>
+												<path
+													stroke-linecap="round"
+													stroke-linejoin="round"
+													stroke-width="2"
+													d="M8 12h.01M12 12h.01M16 12h.01M21 12c0 4.418-4.03 8-9 8a9.863 9.863 0 01-4.255-.949L3 20l1.395-3.72C3.512 15.042 3 13.574 3 12c0-4.418 4.03-8 9-8s9 3.582 9 8z"
+												/>
+											</svg>
+											{post.comments.length}
+										</span>
+									{/if}
 								</div>
 							</div>
 						</div>
@@ -775,23 +796,25 @@
 					</div>
 
 					<!-- Comments list -->
-					<div class="flex-1 overflow-y-auto p-3">
-						{#if selectedPost.comments.length === 0}
-							<p class="text-center text-sm text-gray-400">Keine Kommentare.</p>
-						{:else}
-							<div class="space-y-3">
-								{#each selectedPost.comments as comment, i (i)}
-									<div>
-										<span class="text-sm font-medium text-gray-900">{comment.author}</span>
-										<span class="ml-1 text-sm text-gray-700">{comment.text}</span>
-										<div class="mt-0.5 text-xs text-gray-400">
-											{formatShortDate(comment.timestamp)}
+					{#if commentsEnabled}
+						<div class="flex-1 overflow-y-auto p-3">
+							{#if selectedPost.comments.length === 0}
+								<p class="text-center text-sm text-gray-400">Keine Kommentare.</p>
+							{:else}
+								<div class="space-y-3">
+									{#each selectedPost.comments as comment, i (i)}
+										<div>
+											<span class="text-sm font-medium text-gray-900">{comment.author}</span>
+											<span class="ml-1 text-sm text-gray-700">{comment.text}</span>
+											<div class="mt-0.5 text-xs text-gray-400">
+												{formatShortDate(comment.timestamp)}
+											</div>
 										</div>
-									</div>
-								{/each}
-							</div>
-						{/if}
-					</div>
+									{/each}
+								</div>
+							{/if}
+						</div>
+					{/if}
 				</div>
 			</div>
 		</div>

frontend/export-viewer/src/standalone.ts

@@ -0,0 +1,8 @@
+// Standalone (non-SvelteKit) entry for the offline keepsake. Mounts the plain
+// Svelte viewer component into a single, self-contained index.html so it works
+// when opened by double-clicking from an extracted ZIP (file://).
+import './app.css';
+import { mount } from 'svelte';
+import App from './routes/+page.svelte';
+
+mount(App, { target: document.getElementById('app')! });

frontend/export-viewer/vite.config.js

@@ -0,0 +1,10 @@
+import { sveltekit } from '@sveltejs/kit/vite';
+import tailwindcss from '@tailwindcss/vite';
+import { defineConfig } from 'vite';
+
+// NOTE: the production keepsake is built with `vite.standalone.config.js`
+// (see `npm run build`), which inlines everything into a single, file://-safe
+// index.html. This SvelteKit config is kept only for `npm run dev`/`preview`.
+export default defineConfig({
+	plugins: [tailwindcss(), sveltekit()]
+});