Merge branch 'fix/prod-readiness-healthcheck-domain'

Two issues would each stop a clean production `docker compose up` for the event:

1. Healthchecks probed http://localhost:{3000,3001}, but the app and frontend
   bind IPv4 (0.0.0.0) while `localhost` resolves to ::1 (IPv6) first inside the
   container — so the probe got "connection refused" and neither container ever
   turned healthy. Caddy is gated on `condition: service_healthy` for both, so on
   a fresh boot it would block forever and nothing gets served. Switch both probes
   to 127.0.0.1. (Verified: both containers now report healthy.)

2. The prod caddy service never received DOMAIN, so the Caddyfile's `{$DOMAIN}`
   site address expanded to empty — malformed site block, no TLS, no serving. Add
   `environment: { DOMAIN: ${DOMAIN} }` to the caddy service.

Also make .env.example honest and event-ready:
- Add DATABASE_MAX_CONNECTIONS (real env lever; recommend 30 for ~100 guests).
- The DEFAULT_* upload/rate/capacity vars are NOT read from env — they are seeded
  into the DB config table and managed at runtime via the admin dashboard. Replace
  the misleading entries (e.g. upload rate showed 10; live value is 100 via
  migration 015) with a note pointing to the admin UI and the real seeded defaults.
- Document that raising COMPRESSION_WORKER_CONCURRENCY also needs the app memory
  limit raised (ffmpeg), so a video burst can't OOM the box.

Co-Authored-By: Claude Opus 4.8 <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

@@ -4,6 +4,10 @@ DOMAIN=my-event.example.com
 
 # ── App server ────────────────────────────────────────────────────────────────
 APP_PORT=3000
+# Set to `production` in real deployments. This activates the secret guard that
+# refuses to boot with placeholder JWT_SECRET / ADMIN_PASSWORD_HASH values.
+# (docker-compose.yml already sets APP_ENV=production for the app service.)
+APP_ENV=production
 
 # ── Database ──────────────────────────────────────────────────────────────────
 # Set a strong password and keep it in sync between DATABASE_URL and
@@ -12,6 +16,9 @@ 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.
+DATABASE_MAX_CONNECTIONS=30
 
 # ── Authentication ────────────────────────────────────────────────────────────
 # Generate with: openssl rand -hex 64
@@ -20,7 +27,11 @@ 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
@@ -28,20 +39,29 @@ EVENT_SLUG=max-maria-2026
 
 # ── Storage ───────────────────────────────────────────────────────────────────
 MEDIA_PATH=/media
+# Export archives (Gallery.zip / Memories.zip). MUST be outside MEDIA_PATH —
+# /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  (fraction of disk that triggers the low-storage warning)
+# Adjust these in the admin UI before the event if needed.
 
 # ── 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

.env.test

@@ -1,45 +0,0 @@
-# ── Domain ────────────────────────────────────────────────────────────────────
-# Public domain Caddy will serve and obtain a TLS certificate for.
-DOMAIN=my-event.example.com
-
-# ── App server ────────────────────────────────────────────────────────────────
-APP_PORT=3000
-
-# ── Database ──────────────────────────────────────────────────────────────────
-DATABASE_URL=postgres://eventsnap:secret@db:5432/eventsnap
-POSTGRES_USER=eventsnap
-POSTGRES_PASSWORD=secret
-POSTGRES_DB=eventsnap
-
-# ── Authentication ────────────────────────────────────────────────────────────
-# Generate with: openssl rand -hex 64
-JWT_SECRET=change_me_to_a_random_64_byte_hex_string
-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
-
-# ── Event ─────────────────────────────────────────────────────────────────────
-EVENT_NAME=Max & Maria's Wedding
-EVENT_SLUG=max-maria-2026
-
-# ── Storage ───────────────────────────────────────────────────────────────────
-MEDIA_PATH=/media
-
-# ── 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
-
-# ── Workers ───────────────────────────────────────────────────────────────────
-COMPRESSION_WORKER_CONCURRENCY=2

.github/workflows/audit.yml

@@ -0,0 +1,73 @@
+# Dependency advisory scan.
+#
+# Lives in .github/workflows/ because Gitea Actions scans BOTH .gitea/workflows and
+# .github/workflows, and e2e.yml already proves this instance resolves `actions/*` from GitHub
+# (DEFAULT_ACTIONS_URL). Keeping one directory avoids a split where half the CI is invisible
+# depending on which convention you look under.
+#
+# Unlike the GitHub-hosted runners this workflow does NOT assume a preinstalled Rust toolchain —
+# the common Gitea runner images (gitea/runner-images, catthehacker/ubuntu) ship Node and Docker
+# but not cargo. So we install it explicitly instead of relying on the ambient environment.
+name: Audit
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+  schedule:
+    # New advisories land against unchanged code, so a push-only trigger would never see them.
+    - cron: '0 6 * * 1'
+
+jobs:
+  cargo-audit:
+    name: cargo audit (backend)
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        run: |
+          if ! command -v cargo > /dev/null; then
+            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
+            echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
+          fi
+
+      - name: Cache cargo
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/bin
+          key: cargo-audit-${{ hashFiles('backend/Cargo.lock') }}
+          restore-keys: cargo-audit-
+
+      - name: Install cargo-audit
+        run: cargo install cargo-audit --locked || true
+
+      # `rsa` 0.9 (RUSTSEC-2023-0071, "Marvin") is a transitive dep of the SQLx MySQL driver that
+      # this app never exercises: auth is HS256 + bcrypt, and the only database is Postgres. There
+      # is no patched release, so failing the build on it would mean a permanently red pipeline
+      # that everyone learns to ignore — which is worse than not scanning at all. Ignore it
+      # SPECIFICALLY, so that any OTHER advisory still fails the job.
+      - name: Audit
+        working-directory: ./backend
+        run: cargo audit --deny warnings --ignore RUSTSEC-2023-0071
+
+  npm-audit:
+    name: npm audit (frontend)
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+      - name: Install deps
+        working-directory: ./frontend
+        run: npm install
+      # Production dependencies only: a dev-only advisory (build tooling, test runners) can't be
+      # reached by a guest at the party, and gating merges on it just trains people to skip the gate.
+      - name: Audit
+        working-directory: ./frontend
+        run: npm audit --omit=dev --audit-level=high

.github/workflows/checks.yml

@@ -0,0 +1,129 @@
+# The checks that were only ever running on a laptop.
+#
+# Before this file, CI ran Playwright (chromium-desktop) and the dependency audit — and nothing
+# else. `cargo test` (40 tests), the frontend vitest suite (5 files, including the offline
+# upload-queue and auth-token logic), svelte-check, and the e2e typecheck were all green on a
+# developer's machine and gated NOTHING. A check that only ever runs locally is not running.
+#
+# In .github/workflows/ because Gitea Actions scans it too (see audit.yml). Rust is installed
+# explicitly: the common Gitea runner images ship Node and Docker, not cargo.
+name: Checks
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  backend:
+    name: Backend — cargo test + clippy + fmt
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rust toolchain
+        run: |
+          if ! command -v cargo > /dev/null; then
+            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
+            echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
+          fi
+          rustup component add clippy rustfmt
+
+      - uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            backend/target
+          key: cargo-${{ hashFiles('backend/Cargo.lock') }}
+          restore-keys: cargo-
+
+      # SQLx runs its queries against a live database at TEST time (see backend/tests/), so the
+      # DB-backed tests need one. The pure unit tests don't care, but starting it unconditionally
+      # keeps the job simple and honest about what it covers.
+      - name: Start Postgres
+        run: |
+          docker run -d --name ci-pg -p 5432:5432 \
+            -e POSTGRES_PASSWORD=postgres -e POSTGRES_DB=eventsnap_ci \
+            postgres:16-alpine
+          for _ in $(seq 1 30); do
+            docker exec ci-pg pg_isready -U postgres > /dev/null 2>&1 && break
+            sleep 1
+          done
+
+      - name: Test
+        working-directory: ./backend
+        env:
+          DATABASE_URL: postgres://postgres:postgres@localhost:5432/eventsnap_ci
+        # `#[sqlx::test]` creates a fresh database per test and opens its own pool; run at unbounded
+        # parallelism against a default `max_connections=100` Postgres, a full suite can exhaust the
+        # server's connection slots and fail with PoolTimedOut — a pure infra flake, not a real
+        # failure. Cap the concurrency so the gate stays trustworthy on a loaded runner.
+        run: cargo test --all-features -- --test-threads=8
+
+      - name: Clippy
+        working-directory: ./backend
+        run: cargo clippy --all-targets -- -D warnings
+
+      - name: Format
+        working-directory: ./backend
+        run: cargo fmt --check
+
+  frontend:
+    name: Frontend — vitest + svelte-check
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+          cache: 'npm'
+          cache-dependency-path: 'frontend/package-lock.json'
+
+      - name: Install deps
+        working-directory: ./frontend
+        run: npm ci || npm install
+
+      - name: Unit tests
+        working-directory: ./frontend
+        run: npm run test:unit
+
+      - name: svelte-check
+        working-directory: ./frontend
+        run: npx svelte-check --threshold error
+
+      - name: ESLint
+        working-directory: ./frontend
+        run: npm run lint
+
+      - name: Prettier
+        working-directory: ./frontend
+        run: npm run format:check
+
+  e2e-typecheck:
+    name: E2E — typecheck + lint
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+      - name: Install deps
+        working-directory: ./e2e
+        run: npm install
+      # Playwright TRANSPILES specs without typechecking them, so a type error in a spec is
+      # invisible until the assertion it guards silently does the wrong thing at runtime.
+      - name: tsc --noEmit
+        working-directory: ./e2e
+        run: npx tsc --noEmit
+
+      - name: ESLint
+        working-directory: ./e2e
+        run: npm run lint
+
+      - name: Prettier
+        working-directory: ./e2e
+        run: npm run format:check

.github/workflows/e2e.yml

@@ -46,6 +46,14 @@ jobs:
         working-directory: ./e2e
         run: npm run test:e2e -- --project=chromium-desktop
 
+      # 09-mobile is `testIgnore`d on chromium-desktop (it needs hasTouch + a phone viewport), so
+      # running only that project left 22 tests — focus traps, touch targets, safe-area insets,
+      # viewport reflow, upload-cancel — never executing in CI. On a phone-first event app, where
+      # essentially every real guest is on a phone, that was the wrong half of the suite to skip.
+      - name: Run E2E tests (mobile)
+        working-directory: ./e2e
+        run: npm run test:e2e -- --project=chromium-mobile
+
       - name: Upload Playwright report
         if: failure()
         uses: actions/upload-artifact@v4

.gitignore

@@ -1,5 +1,7 @@
 # Environment secrets — never commit the real .env
 .env
+# Stale local scratch copy of .env.example; nothing in the test stack reads it.
+.env.test
 
 # Rust
 backend/target/
@@ -20,7 +22,13 @@ e2e/playwright-report/
 e2e/test-results/
 e2e/.cache/
 e2e/.env.test
+# Playwright artifacts when run from the repo root instead of e2e/
+/test-results/
+/playwright-report/
 
 # OS
 .DS_Store
 Thumbs.db
+
+# Claude Code personal (per-user) settings — shared settings.json IS committed
+.claude/settings.local.json

Caddyfile

@@ -1,5 +1,8 @@
 {$DOMAIN} {
-	encode zstd gzip
+	# Compress everything EXCEPT the SSE stream — gzip buffering delays
+	# "real-time" likes/comments until the ~30s keep-alive tick.
+	@compressible not path /api/v1/stream
+	encode @compressible zstd gzip
 
 	# Site-wide security headers (defense-in-depth). HSTS is free since Caddy
 	# already terminates TLS. nosniff also covers all of /media/*.
@@ -14,19 +17,20 @@
 	@hashed_assets path_regexp hashed /_app/immutable/.*\.[a-f0-9]{8,}\.(js|css|woff2)$
 	header @hashed_assets Cache-Control "public, max-age=31536000, immutable"
 
-	# Media previews and thumbnails
-	@previews path /media/previews/* /media/thumbnails/*
-	header @previews Cache-Control "public, max-age=3600"
+	# 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.
+	# 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"
 
-	# Original media files (private — only host can download). Force download
-	# rather than inline rendering as defense-in-depth against any future
-	# content-type confusion (previews/thumbnails are re-encoded and stay inline).
-	@originals path /media/originals/*
-	header @originals Cache-Control "private, max-age=86400"
-	header @originals Content-Disposition "attachment"
-
-	# API — never cache
-	@api path /api/*
+	# API — never cache, EXCEPT the gated image routes above.
+	@api {
+		path /api/*
+		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

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'),

README.md

@@ -94,9 +94,9 @@ eventsnap/
 ### Deploy on a fresh VPS
 
 ```bash
-# 1. Clone the repository
-git clone https://git.mc02.dev/fabi/EventSnap.git
-cd EventSnap
+# 1. Clone the repository (into a lowercase dir, matching the paths used below)
+git clone https://git.mc02.dev/fabi/EventSnap.git eventsnap
+cd eventsnap
 
 # 2. Configure environment
 cp .env.example .env
@@ -108,6 +108,8 @@ docker compose up -d
 
 Caddy automatically obtains a Let's Encrypt certificate on first start. The app is live at `https://DOMAIN` within ~30 seconds.
 
+> **If the site never comes up:** with `APP_ENV=production` the backend **refuses to boot** while `JWT_SECRET`/`ADMIN_PASSWORD_HASH` still hold the `.env.example` placeholders (this is deliberate — a publicly-known signing key is worse than downtime). Caddy then waits on the unhealthy `app` container and never serves. Check `docker compose logs app` — a "Refusing to start … placeholder …" line means you skipped step 2. Rotate the secrets (see below) and restart.
+
 > **Production note:** `docker compose up -d` does **not** expose the database — Postgres is reachable only on the internal Docker network. For local development where you need host access to Postgres, opt into the dev overlay explicitly:
 > ```bash
 > docker compose -f docker-compose.yml -f docker-compose.dev.yml up
@@ -180,6 +182,28 @@ The `/media` volume holds originals, previews, thumbnails, exports, and DB backu
 
 ---
 
+## Running the backend test suite
+
+```bash
+cd backend
+
+# The DB-backed integration tests (backend/tests/) need a live Postgres. `#[sqlx::test]` creates a
+# throwaway database per test and runs backend/migrations/ into it — it does NOT touch this one's data.
+docker run -d --name eventsnap-test-pg -p 55433:5432 \
+  -e POSTGRES_PASSWORD=postgres -e POSTGRES_DB=eventsnap postgres:16-alpine
+
+export DATABASE_URL=postgres://postgres:postgres@localhost:55433/eventsnap
+cargo test        # 44 unit + 12 DB-backed
+cargo clippy --all-targets -- -D warnings
+```
+
+**`cargo test` requires `DATABASE_URL`** — without it the integration tests panic rather than skip.
+That is deliberate. The riskiest code in this repo is SQL (the export epoch state machine, the
+atomic quota increment, the `FOR SHARE` upload lock), and for a long time *not one line of it* was
+executed by `cargo test` — every backend test was a pure-function test, so the tests clustered
+tightly around the code that could not break and stopped exactly where it started to. Tests that
+silently skip when the database is absent recreate that hole; they were meant to be a gate.
+
 ## Running the E2E test suite
 
 Playwright-based end-to-end tests live in [`e2e/`](e2e/). They spin up an isolated docker-compose stack (Postgres on `:55432`, Caddy on `:3101`) and exercise the SvelteKit frontend against the real Rust backend with rate limits disabled.
@@ -196,7 +220,14 @@ npm run stack:down            # tear it down
 
 See [`e2e/README.md`](e2e/README.md) for the full UA matrix, Samsung Internet escalation tiers, and the Phase 2/3 roadmap.
 
-CI runs this on every PR — see [`.github/workflows/e2e.yml`](.github/workflows/e2e.yml).
+CI runs this on every PR — see [`.github/workflows/e2e.yml`](.github/workflows/e2e.yml) (desktop **and**
+mobile projects), plus [`checks.yml`](.github/workflows/checks.yml) for `cargo test`/clippy, the frontend
+unit tests, svelte-check and the e2e typecheck, and [`audit.yml`](.github/workflows/audit.yml) for
+dependency advisories.
+
+**Playwright runs with `retries: 0`, including in CI.** This repo's real bugs are races, and from the
+outside a race is indistinguishable from a flake — so a retry silently resolves that ambiguity in
+favour of "flake" every time. A flake here is a bug report; treat it as one.
 
 ---
 

backend/Dockerfile

@@ -20,15 +20,17 @@ FROM alpine:3.21
 
 RUN apk add --no-cache ca-certificates ffmpeg
 
-# Run as a non-root user. Pre-create and chown the media mount path so the fresh
-# named volume inherits the non-root ownership (Docker seeds an empty named volume
-# from the image directory, preserving its uid/gid) and uploads can be written.
+# Run as a non-root user. Pre-create and chown the media + export mount paths so
+# the fresh named volumes inherit the non-root ownership (Docker seeds an empty
+# named volume from the image directory, preserving its uid/gid) and uploads +
+# export archives can be written. Exports live OUTSIDE /media on purpose so the
+# public media ServeDir can't reach them.
 RUN addgroup -S app && adduser -S app -G app
 
 WORKDIR /app
 COPY --from=builder /app/target/release/eventsnap-backend ./
 
-RUN mkdir -p /media && chown -R app:app /app /media
+RUN mkdir -p /media /exports && chown -R app:app /app /media /exports
 USER app
 
 EXPOSE 3000

backend/migrations/010_review_indexes.down.sql

@@ -0,0 +1,3 @@
+DROP INDEX IF EXISTS idx_comment_hashtag_hashtag;
+DROP INDEX IF EXISTS idx_comment_user;
+DROP INDEX IF EXISTS idx_upload_event_created_id;

backend/migrations/010_review_indexes.up.sql

@@ -0,0 +1,17 @@
+-- Composite feed index with an id tiebreaker so keyset pagination
+-- (ORDER BY created_at DESC, id DESC) stays index-covered and stable when
+-- multiple uploads share a created_at timestamp.
+CREATE INDEX idx_upload_event_created_id
+    ON upload(event_id, created_at DESC, id DESC)
+    WHERE deleted_at IS NULL;
+
+-- A user's own comments (moderation, "who commented"). The sibling
+-- idx_upload_user already exists for uploads; comment(user_id) was missing.
+CREATE INDEX idx_comment_user
+    ON comment(user_id)
+    WHERE deleted_at IS NULL;
+
+-- Hashtag filtering over comments — mirrors idx_upload_hashtag_hashtag, which
+-- only covered upload_hashtag.
+CREATE INDEX idx_comment_hashtag_hashtag
+    ON comment_hashtag(hashtag_id);

backend/migrations/011_ban_hides_and_pin_reset.down.sql

@@ -0,0 +1,25 @@
+DROP TABLE IF EXISTS pin_reset_request;
+
+-- Restore v_feed without the is_banned filter.
+CREATE OR REPLACE 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
+GROUP BY u.id, usr.display_name, usr.is_banned, usr.uploads_hidden;

backend/migrations/011_ban_hides_and_pin_reset.up.sql

@@ -0,0 +1,39 @@
+-- Ban now ALWAYS hides: exclude banned uploaders from the feed view. Previously ban and
+-- hide were decoupled (a host could ban without hiding), leaving a banned user's photos on
+-- the feed and baked into the export. `find_visible_media` and the export query get the
+-- same `is_banned = FALSE` filter in code.
+CREATE OR REPLACE 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;
+
+-- pin_reset_request: a guest who forgot their PIN (localStorage was the only copy) can ask
+-- a host to reset it in-app, instead of being permanently orphaned. One pending request per
+-- user; cleared when the host resets the PIN or dismisses it, and cascades if the user/event
+-- is removed.
+CREATE TABLE pin_reset_request (
+    id          UUID        PRIMARY KEY DEFAULT gen_random_uuid(),
+    event_id    UUID        NOT NULL REFERENCES event(id) ON DELETE CASCADE,
+    user_id     UUID        NOT NULL REFERENCES "user"(id) ON DELETE CASCADE,
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    UNIQUE (user_id)
+);

backend/migrations/012_export_release_seq.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE export_job
+    DROP COLUMN IF EXISTS release_seq;

backend/migrations/012_export_release_seq.up.sql

@@ -0,0 +1,11 @@
+-- H1: export generation guard. A reopen (which clears `export_released_at`) followed by a
+-- re-release could spawn a fresh export worker while a worker from the PRIOR release was
+-- still streaming a now-stale snapshot to `Gallery.zip`. The stale worker's finalize then
+-- re-set `export_*_ready = TRUE` on an archive that predated the reopen — a silent,
+-- permanent data loss (new uploads missing from a "ready" keepsake).
+--
+-- `release_seq` is a per-(event,type) generation counter bumped on every (re)release.
+-- A worker captures the seq it claimed and only finalizes / flips the ready flag while
+-- that seq is still current; a superseded worker discards its output instead.
+ALTER TABLE export_job
+    ADD COLUMN release_seq BIGINT NOT NULL DEFAULT 0;

backend/migrations/013_uploads_hidden_at.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE "user"
+    DROP COLUMN IF EXISTS uploads_hidden_at;

backend/migrations/013_uploads_hidden_at.up.sql

@@ -0,0 +1,12 @@
+-- Ban-replay on reconnect. A ban is not a soft-delete (it sets `uploads_hidden`/`is_banned`,
+-- never `upload.deleted_at`), and live eviction rode only on the ephemeral `user-hidden` SSE
+-- broadcast — which has no reconnect-replay. So a client (especially the unattended diashow
+-- projector) that missed that broadcast kept cycling the banned user's already-loaded slides.
+--
+-- `uploads_hidden_at` stamps WHEN a user's uploads became hidden, so the reconnect delta can
+-- return the set of users hidden since the client's cursor and the client can evict them.
+ALTER TABLE "user"
+    ADD COLUMN uploads_hidden_at TIMESTAMPTZ;
+
+-- Backfill already-hidden users so a reconnect right after this migration still evicts them.
+UPDATE "user" SET uploads_hidden_at = NOW() WHERE uploads_hidden = TRUE;

backend/migrations/014_export_epoch.down.sql

@@ -0,0 +1,28 @@
+-- Restore the stored ready flags and the per-job counter.
+DROP VIEW IF EXISTS export_current;
+
+ALTER TABLE event ADD COLUMN export_zip_ready  BOOLEAN NOT NULL DEFAULT FALSE;
+ALTER TABLE event ADD COLUMN export_html_ready BOOLEAN NOT NULL DEFAULT FALSE;
+
+-- Re-derive the flags from what the epoch model considers downloadable, so the old code sees
+-- exactly the state it would have written itself.
+UPDATE event e
+   SET export_zip_ready = EXISTS (
+         SELECT 1 FROM export_job j
+          WHERE j.event_id = e.id AND j.type = 'zip'
+            AND j.status = 'done' AND j.epoch = e.export_epoch
+       ),
+       export_html_ready = EXISTS (
+         SELECT 1 FROM export_job j
+          WHERE j.event_id = e.id AND j.type = 'html'
+            AND j.status = 'done' AND j.epoch = e.export_epoch
+       )
+ WHERE e.export_released_at IS NOT NULL;
+
+ALTER TABLE export_job RENAME COLUMN epoch TO release_seq;
+
+-- The old code treats release_seq as a non-negative per-job counter; the -1 retirement sentinel
+-- has no meaning there, so floor it back to 0.
+UPDATE export_job SET release_seq = 0 WHERE release_seq < 0;
+
+ALTER TABLE event DROP COLUMN export_epoch;

backend/migrations/014_export_epoch.up.sql

@@ -0,0 +1,86 @@
+-- Export generation, unified.
+--
+-- ⚠ ROLLBACK RUNBOOK. This is the repo's first DESTRUCTIVE migration (it DROPs two columns). The
+-- previous image will NOT boot against this schema: sqlx runs migrations before serving and errors
+-- with VersionMissing on an unknown version, so you get a crash loop, not a degraded service.
+-- To roll back to the previous release you must run 014_export_epoch.down.sql BY HAND FIRST, then
+-- deploy the old image. The down migration re-derives the old ready flags from the epoch state, so
+-- no keepsake is lost.
+--
+-- Before this migration, "which generation of the keepsake is current?" had no single answer.
+-- It was assembled at runtime from three separately-written pieces of state across two tables:
+--   * event.export_released_at   — a release marker with NO identity (you cannot ask *which* release)
+--   * export_job.release_seq     — a per-row counter, in a different table, bumped in a different statement
+--   * event.export_{zip,html}_ready — a CACHED COPY of the derivation of the other two
+-- Keeping those three in agreement took ~10 hand-written guards, and every guard was a repair of the
+-- same missing invariant. Three consecutive review rounds each found another path that slipped through.
+--
+-- This replaces all of it with ONE authority:
+--
+--   event.export_epoch — a monotonic counter bumped in the SAME UPDATE as any change to
+--                        export_released_at (release and reopen are its only writers).
+--   export_job.epoch   — a COPY of event.export_epoch taken when the job was enqueued.
+--                        NEVER independently incremented.
+--
+-- The single invariant, which replaces the entire proof:
+--
+--   An export is downloadable IFF
+--       event.export_released_at IS NOT NULL
+--   AND export_job.epoch = event.export_epoch
+--   AND export_job.status = 'done'
+--
+-- Readiness is therefore DERIVED, never stored — so it cannot drift, and no worker can set it.
+-- A worker holding a dead epoch is INERT BY CONSTRUCTION: anything it writes is invisible to every
+-- reader, with no guard involved. Losing a race can no longer corrupt state; it can only waste work.
+--
+-- Crucially, epoch equality is checked on the SAME ROW the worker updates (export_job), never via a
+-- cross-table EXISTS. That matters: under READ COMMITTED, when an UPDATE blocks on a row lock and the
+-- blocker commits, Postgres re-evaluates the WHERE against the *updated target row* but answers
+-- subqueries on OTHER tables from the statement's ORIGINAL snapshot. The old cross-row guard
+-- (`EXISTS (SELECT 1 FROM event WHERE ... export_released_at IS NOT NULL)`) was unsound for exactly
+-- that reason — it could admit a claim against an already-reopened event while RETURNING the
+-- post-bump seq. A same-row `epoch = $n` predicate is re-evaluated correctly by EPQ.
+
+ALTER TABLE event ADD COLUMN export_epoch BIGINT NOT NULL DEFAULT 0;
+
+-- A currently-released event's live generation becomes epoch 1.
+UPDATE event SET export_epoch = 1 WHERE export_released_at IS NOT NULL;
+
+-- The per-job counter becomes a plain copy of the event epoch it was enqueued for.
+ALTER TABLE export_job RENAME COLUMN release_seq TO epoch;
+
+-- Carry the OLD notion of "downloadable" across exactly: a job the old model considered ready
+-- (released + done + its ready flag) adopts the event's live epoch. Everything else is retired to
+-- -1, which can never equal a non-negative event.export_epoch, so it is inert forever.
+UPDATE export_job j
+   SET epoch = CASE
+         WHEN e.export_released_at IS NOT NULL
+          AND j.status = 'done'
+          AND ((j.type = 'zip'  AND e.export_zip_ready)
+            OR (j.type = 'html' AND e.export_html_ready))
+         THEN e.export_epoch
+         ELSE -1
+       END
+  FROM event e
+ WHERE e.id = j.event_id;
+
+-- The duplicated derivation. Gone — along with the whole class of bugs where a stale worker
+-- resurrected it, or where it disagreed with the job row it was supposed to summarise.
+ALTER TABLE event DROP COLUMN export_zip_ready;
+ALTER TABLE event DROP COLUMN export_html_ready;
+
+-- The ONE definition of "the current generation". Every reader goes through this, so readiness and
+-- the file path are resolved in a SINGLE read — closing the download-path TOCTOU where the ready
+-- flag was checked in one query and file_path fetched in another (a reopen between the two served a
+-- keepsake that should have 404'd).
+CREATE VIEW export_current AS
+SELECT j.event_id,
+       j.type,
+       j.status,
+       j.progress_pct,
+       j.file_path,
+       j.epoch
+  FROM export_job j
+  JOIN event e ON e.id = j.event_id
+ WHERE e.export_released_at IS NOT NULL   -- implied by the epoch match; kept as an assertion
+   AND j.epoch = e.export_epoch;

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/scripts/rehearse-014.sh

@@ -0,0 +1,195 @@
+#!/usr/bin/env bash
+#
+# Dress rehearsal for migration 014 (export_epoch) — the repo's first DESTRUCTIVE migration.
+#
+# 014 DROPs event.export_zip_ready / export_html_ready and rewrites export_job.release_seq into an
+# epoch. The dangerous part is not the DDL, it's the BACKFILL: it has to carry the old notion of
+# "downloadable" across exactly. Get it wrong and a released event's keepsake silently 404s for
+# every guest, on a dataset you cannot re-create.
+#
+# This script proves the backfill preserves downloadability, against a scratch copy of a REAL dump:
+#
+#   ./rehearse-014.sh /path/to/prod-dump.sql     # rehearse against production data
+#   ./rehearse-014.sh                            # synthetic: build a pre-014 DB covering every case
+#
+# It asserts:
+#   1. up:   {(event,type) downloadable BEFORE} == {(event,type) downloadable AFTER}
+#   2. down: the old ready flags come back identical  (so a rollback is actually a rollback)
+#   3. up again: still identical                      (so a roll-forward after a rollback is safe)
+#
+# It NEVER touches your real database. Everything runs in a throwaway container.
+#
+# NOTE ON ROLLBACK (see the runbook header in 014_export_epoch.up.sql): sqlx runs migrations before
+# serving and errors with VersionMissing on an unknown version, so the PREVIOUS image will not boot
+# against the 014 schema — it crash-loops. Rolling back means running 014_export_epoch.down.sql BY
+# HAND FIRST, then deploying the old image. Assertion 2 is what makes that safe. Rehearse it before
+# you need it, not while the party is happening.
+
+set -euo pipefail
+
+DUMP="${1:-}"
+MIG_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../migrations" && pwd)"
+CONTAINER="eventsnap-rehearse-014"
+PGPASSWORD="rehearse"
+DB="eventsnap_rehearsal"
+
+cleanup() { docker rm -f "$CONTAINER" > /dev/null 2>&1 || true; }
+trap cleanup EXIT
+cleanup
+
+echo "▸ Starting a throwaway postgres:16 (nothing here touches your real DB)…"
+docker run --rm -d --name "$CONTAINER" \
+  -e POSTGRES_PASSWORD="$PGPASSWORD" -e POSTGRES_DB="$DB" \
+  postgres:16-alpine > /dev/null
+
+psql() { docker exec -i -e PGPASSWORD="$PGPASSWORD" "$CONTAINER" psql -U postgres -d "$DB" -v ON_ERROR_STOP=1 "$@"; }
+
+for _ in $(seq 1 30); do
+  if docker exec "$CONTAINER" pg_isready -U postgres > /dev/null 2>&1; then break; fi
+  sleep 1
+done
+
+if [[ -n "$DUMP" ]]; then
+  echo "▸ Restoring $DUMP …"
+  psql -q < "$DUMP"
+else
+  echo "▸ No dump given — building a synthetic pre-014 DB (migrations 001→013)…"
+  for f in "$MIG_DIR"/0[0-1][0-9]_*.up.sql; do
+    [[ "$(basename "$f")" == 014_* ]] && continue
+    psql -q < "$f"
+  done
+
+  # Every state the backfill has to classify. If 014 mishandles ANY of these, assertion 1 fails.
+  # Every state the backfill has to classify. export_job is UNIQUE (event_id, type), so each event
+  # has at most one job per type — the cases are distinguished by event, not by piling up rows.
+  #   A: released, both flags, both done  → both stay downloadable
+  #   B: released, ZIP flag only          → ZIP downloadable, HTML not (a half-built keepsake)
+  #   C: released, jobs done, NO flags    → NOT downloadable (a superseded worker's finished job:
+  #                                          the exact state the old ready-flag model used to leak)
+  #   D: never released, jobs done        → NOT downloadable (reopened, or built before release)
+  #   E: released, ZIP flag set but the job is FAILED/RUNNING → NOT downloadable (flag/job disagree,
+  #                                          which the old two-source model made representable at all)
+  echo "▸ Seeding: released+both, zip-only, done-but-stale, unreleased, flag/job-disagreement…"
+  psql -q <<'SQL'
+INSERT INTO event (id, slug, name, export_released_at, export_zip_ready, export_html_ready) VALUES
+  ('aaaaaaaa-0000-0000-0000-000000000001','ev-a','A', now(), TRUE,  TRUE),
+  ('aaaaaaaa-0000-0000-0000-000000000002','ev-b','B', now(), TRUE,  FALSE),
+  ('aaaaaaaa-0000-0000-0000-000000000003','ev-c','C', now(), FALSE, FALSE),
+  ('aaaaaaaa-0000-0000-0000-000000000004','ev-d','D', NULL,  FALSE, FALSE),
+  ('aaaaaaaa-0000-0000-0000-000000000005','ev-e','E', now(), TRUE,  TRUE);
+
+INSERT INTO export_job (event_id, type, status, progress_pct, file_path, release_seq)
+SELECT e.id, t::export_type, 'done'::export_status, 100, '/x/' || e.slug || '.' || t, 0
+  FROM event e CROSS JOIN (VALUES ('zip'),('html')) AS v(t);
+
+-- E: the flags claim ready, the jobs say otherwise. Old model required BOTH, so neither is
+-- downloadable — the migration must not "trust the flag" and resurrect them.
+UPDATE export_job SET status = 'failed',  file_path = NULL, progress_pct = 40
+ WHERE event_id = 'aaaaaaaa-0000-0000-0000-000000000005' AND type = 'zip';
+UPDATE export_job SET status = 'running', file_path = NULL, progress_pct = 70
+ WHERE event_id = 'aaaaaaaa-0000-0000-0000-000000000005' AND type = 'html';
+SQL
+fi
+
+echo "▸ Snapshotting what is downloadable under the OLD model…"
+psql -q <<'SQL'
+CREATE TABLE _rehearsal_before AS
+SELECT j.event_id, j.type
+  FROM export_job j JOIN event e ON e.id = j.event_id
+ WHERE e.export_released_at IS NOT NULL
+   AND j.status = 'done'
+   AND ((j.type = 'zip' AND e.export_zip_ready) OR (j.type = 'html' AND e.export_html_ready));
+
+-- For assertion 2: the exact flags a rollback has to reproduce.
+CREATE TABLE _rehearsal_flags AS
+SELECT id, export_zip_ready, export_html_ready FROM event;
+SQL
+
+before=$(psql -tAc "SELECT count(*) FROM _rehearsal_before")
+echo "  → $before (event,type) pair(s) downloadable before."
+
+# The assertion. A symmetric difference of zero means the backfill carried the old notion of
+# "downloadable" across EXACTLY: nothing gained (a stale keepsake resurrected), nothing lost (a
+# guest's keepsake silently 404s).
+assert_up_preserves() {
+  local label="$1" diff
+  diff=$(psql -tAc "
+    SELECT count(*) FROM (
+      (SELECT event_id, type FROM _rehearsal_before
+        EXCEPT SELECT event_id, type FROM export_current WHERE status = 'done')
+      UNION ALL
+      (SELECT event_id, type FROM export_current WHERE status = 'done'
+        EXCEPT SELECT event_id, type FROM _rehearsal_before)
+    ) d")
+  if [[ "$diff" != "0" ]]; then
+    echo "✗ FAIL ($label): $diff (event,type) pair(s) changed downloadability across the migration."
+    psql -c "
+      (SELECT 'LOST — guests can no longer download this' AS problem, event_id, type FROM _rehearsal_before
+        EXCEPT ALL SELECT 'LOST — guests can no longer download this', event_id, type FROM export_current WHERE status='done')
+      UNION ALL
+      (SELECT 'GAINED — a stale keepsake became downloadable', event_id, type FROM export_current WHERE status='done'
+        EXCEPT ALL SELECT 'GAINED — a stale keepsake became downloadable', event_id, type FROM _rehearsal_before)"
+    exit 1
+  fi
+  echo "✓ $label: downloadability preserved exactly ($before pair(s))."
+}
+
+echo "▸ Applying 014 (up)…"
+psql -q < "$MIG_DIR/014_export_epoch.up.sql"
+assert_up_preserves "up"
+
+echo "▸ Applying 014 (down) — the rollback path…"
+psql -q < "$MIG_DIR/014_export_epoch.down.sql"
+
+# The down migration is an inverse UP TO DRIFT, not a bit-exact inverse — deliberately.
+#
+# The old model let a ready flag disagree with its job row (flag TRUE over a running/failed job):
+# the flag was a CACHED copy of a derivation, and keeping a cache in agreement with its source
+# across concurrent workers is precisely what it kept failing at. The down migration re-derives the
+# flags from the epoch state, so such a pair comes back FALSE. That HEALS the drift rather than
+# faithfully restoring corruption, and it costs nothing: a flag over a non-done job had no file to
+# serve (file_path is NULL until the worker finishes), so the old code 404'd on it anyway.
+#
+# What a rollback must NOT do is drop a flag for a keepsake that was genuinely downloadable
+# (flag set AND the job actually done). That is the assertion.
+lost=$(psql -tAc "
+  SELECT count(*) FROM _rehearsal_before b
+   WHERE NOT EXISTS (
+     SELECT 1 FROM event e
+      WHERE e.id = b.event_id
+        AND ((b.type = 'zip' AND e.export_zip_ready) OR (b.type = 'html' AND e.export_html_ready)))")
+if [[ "$lost" != "0" ]]; then
+  echo "✗ FAIL (down): $lost downloadable keepsake(s) lost their ready flag — the rollback is LOSSY."
+  psql -c "
+    SELECT b.event_id, b.type, 'was downloadable, flag not restored' AS problem
+      FROM _rehearsal_before b
+     WHERE NOT EXISTS (
+       SELECT 1 FROM event e
+        WHERE e.id = b.event_id
+          AND ((b.type = 'zip' AND e.export_zip_ready) OR (b.type = 'html' AND e.export_html_ready)))"
+  exit 1
+fi
+echo "✓ down: every downloadable keepsake kept its flag — the old image sees a working state."
+
+healed=$(psql -tAc "
+  SELECT count(*) FROM event e JOIN _rehearsal_flags f ON f.id = e.id
+   WHERE (e.export_zip_ready, e.export_html_ready) IS DISTINCT FROM (f.export_zip_ready, f.export_html_ready)")
+if [[ "$healed" != "0" ]]; then
+  echo "  ℹ $healed event(s) came back with a CLEARED flag that had drifted from its job row."
+  echo "    Not a loss — those had no file to serve. The rollback normalises them; the old code"
+  echo "    will rebuild on the next release. Listing them so the behaviour is not a surprise:"
+  psql -c "SELECT e.id, f.export_zip_ready AS was_zip, e.export_zip_ready AS now_zip,
+                  f.export_html_ready AS was_html, e.export_html_ready AS now_html
+             FROM event e JOIN _rehearsal_flags f ON f.id = e.id
+            WHERE (e.export_zip_ready, e.export_html_ready)
+                  IS DISTINCT FROM (f.export_zip_ready, f.export_html_ready)"
+fi
+
+echo "▸ Re-applying 014 (up) — roll forward after a rollback…"
+psql -q < "$MIG_DIR/014_export_epoch.up.sql"
+assert_up_preserves "up (after rollback)"
+
+echo
+echo "✓ Rehearsal passed. 014 is safe to deploy against this dataset."
+[[ -z "$DUMP" ]] && echo "  (synthetic data — re-run with a real pg_dump before you deploy for real)"
+exit 0

backend/src/auth/handlers.rs

@@ -1,8 +1,8 @@
 use std::time::Duration;
 
+use axum::Json;
 use axum::extract::State;
 use axum::http::{HeaderMap, StatusCode};
-use axum::Json;
 use chrono::Utc;
 use rand::Rng;
 use serde::{Deserialize, Serialize};
@@ -37,10 +37,13 @@ pub async fn join(
     Json(body): Json<JoinRequest>,
 ) -> Result<(StatusCode, Json<JoinResponse>), AppError> {
     let ip = client_ip(&headers, "unknown");
-    let rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let join_rate_on = config::get_bool(&state.pool, "join_rate_enabled", true).await;
-    if rate_limits_on && join_rate_on
-        && !state.rate_limiter.check(format!("join:{ip}"), 5, Duration::from_secs(60))
+    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(),
@@ -80,10 +83,21 @@ 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 = bcrypt::hash(&pin, 12).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
 
-    let user = User::create(&state.pool, event.id, display_name, &pin_hash).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
+    // violation to the same clean 409 the pre-check returns, not a generic 500.
+    let user = match User::create(&state.pool, event.id, display_name, &pin_hash).await {
+        Ok(u) => u,
+        Err(sqlx::Error::Database(db)) if db.is_unique_violation() => {
+            return Err(AppError::Conflict(format!(
+                "Der Name \"{}\" ist bereits vergeben.",
+                display_name
+            )));
+        }
+        Err(e) => return Err(e.into()),
+    };
 
     let token = jwt::create_token(
         user.id,
@@ -121,6 +135,18 @@ pub struct RecoverResponse {
     pub user_id: Uuid,
 }
 
+/// A real cost-12 bcrypt hash of a fixed dummy value, computed once and cached. Used
+/// to run a constant-time-ish verify on the "unknown display name" branch of
+/// [`recover`], so that branch costs the same as a real (user-exists) verify and can't
+/// be told apart by timing.
+fn dummy_pin_hash() -> &'static str {
+    static HASH: std::sync::OnceLock<String> = std::sync::OnceLock::new();
+    HASH.get_or_init(|| {
+        bcrypt::hash("eventsnap-dummy-not-a-real-pin", 12)
+            .expect("bcrypt hashing of a static dummy value cannot fail")
+    })
+}
+
 pub async fn recover(
     State(state): State<AppState>,
     headers: HeaderMap,
@@ -134,8 +160,8 @@ pub async fn recover(
     // 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 rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let recover_rate_on = config::get_bool(&state.pool, "recover_rate_enabled", true).await;
+    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 {
         let name_key = display_name.to_lowercase();
         if !state.rate_limiter.check(
@@ -154,13 +180,16 @@ pub async fn recover(
         .await?
         .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
 
-    let users =
-        User::find_by_event_and_name(&state.pool, event.id, display_name).await?;
+    let users = User::find_by_event_and_name(&state.pool, event.id, display_name).await?;
 
     if users.is_empty() {
-        return Err(AppError::NotFound(
-            "Kein Benutzer mit diesem Namen gefunden.".into(),
-        ));
+        // No user with this name. Run a throwaway bcrypt verify so this branch takes
+        // the same time as the user-exists path, and return the SAME error as a wrong
+        // 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());
+        return Err(AppError::Unauthorized("PIN ist falsch.".into()));
     }
 
     for user in &users {
@@ -180,8 +209,7 @@ pub async fn recover(
             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 = bcrypt::verify(&body.pin, &user.recovery_pin_hash).unwrap_or(false);
 
         if pin_matches {
             // Reset failed attempts on success
@@ -238,6 +266,10 @@ pub struct AdminLoginRequest {
 #[derive(Serialize)]
 pub struct AdminLoginResponse {
     pub jwt: String,
+    /// The admin's user id + display name, so the client can populate a real identity
+    /// (own-post affordances, a name on the Account page) instead of a blank session.
+    pub user_id: Uuid,
+    pub display_name: String,
 }
 
 pub async fn admin_login(
@@ -256,14 +288,14 @@ pub async fn admin_login(
     // a long-running guess campaign. 5 attempts / minute / IP is plenty for
     // honest typos.
     let ip = client_ip(&headers, "unknown");
-    let rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let admin_rate_on = config::get_bool(&state.pool, "admin_login_rate_enabled", true).await;
-    if rate_limits_on && admin_rate_on
-        && !state.rate_limiter.check(
-            format!("admin_login:{ip}"),
-            5,
-            Duration::from_secs(60),
-        )
+    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;
+    if rate_limits_on
+        && admin_rate_on
+        && !state
+            .rate_limiter
+            .check(format!("admin_login:{ip}"), 5, Duration::from_secs(60))
     {
         return Err(AppError::TooManyRequests(
             "Zu viele Anmeldeversuche. Bitte warte kurz und versuche es erneut.".into(),
@@ -271,8 +303,7 @@ pub async fn admin_login(
         ));
     }
 
-    let valid = bcrypt::verify(&body.password, &state.config.admin_password_hash)
-        .unwrap_or(false);
+    let valid = bcrypt::verify(&body.password, &state.config.admin_password_hash).unwrap_or(false);
 
     if !valid {
         tracing::warn!(ip = %ip, "admin_login: wrong password");
@@ -298,8 +329,8 @@ 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 =
+            bcrypt::hash(&dummy_pin, 4).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
         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)
@@ -325,13 +356,88 @@ pub async fn admin_login(
     let expires_at = Utc::now() + chrono::Duration::days(1);
     Session::create(&state.pool, admin_user.id, &token_hash, expires_at).await?;
 
-    Ok(Json(AdminLoginResponse { jwt: token }))
+    Ok(Json(AdminLoginResponse {
+        jwt: token,
+        user_id: admin_user.id,
+        display_name: admin_user.display_name,
+    }))
 }
 
-pub async fn logout(
-    State(state): State<AppState>,
-    auth: AuthUser,
-) -> Result<StatusCode, AppError> {
+pub async fn logout(State(state): State<AppState>, auth: AuthUser) -> Result<StatusCode, AppError> {
     Session::delete_by_token_hash(&state.pool, &auth.token_hash).await?;
     Ok(StatusCode::NO_CONTENT)
 }
+
+/// "Sign out everywhere" — revoke every session for the caller, not just the current one.
+/// A single leaked/kept-alive device (a shared phone, a laptop recovered via PIN) can then
+/// be cut from any of the user's devices.
+pub async fn logout_all(
+    State(state): State<AppState>,
+    auth: AuthUser,
+) -> Result<StatusCode, AppError> {
+    Session::delete_all_for_user(&state.pool, auth.user_id).await?;
+    Ok(StatusCode::NO_CONTENT)
+}
+
+#[derive(Deserialize)]
+pub struct PinResetRequestBody {
+    pub display_name: String,
+}
+
+/// A guest who forgot their PIN asks a host to reset it in-app. Unauthenticated (they
+/// can't log in without the PIN) and rate-limited. Always returns 204 regardless of
+/// whether the name exists, so it can't enumerate display names beyond what the public
+/// feed already exposes.
+pub async fn request_pin_reset(
+    State(state): State<AppState>,
+    headers: HeaderMap,
+    Json(body): Json<PinResetRequestBody>,
+) -> Result<StatusCode, AppError> {
+    let display_name = body.display_name.trim();
+    let ip = client_ip(&headers, "unknown");
+    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(
+            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,
+            ));
+        }
+    }
+    if display_name.is_empty() {
+        return Ok(StatusCode::NO_CONTENT);
+    }
+
+    // Single statement so the existing-name and unknown-name paths do IDENTICAL work
+    // (same event+user index scans, an INSERT that matches 0 rows for an unknown name) —
+    // no timing oracle despite the always-204 contract. Admins recover via password, so
+    // they're excluded from the join and never get a reset request queued.
+    let _ = sqlx::query(
+        "INSERT INTO pin_reset_request (event_id, user_id)
+         SELECT e.id, u.id
+         FROM event e
+         JOIN \"user\" u
+           ON u.event_id = e.id
+          AND lower(u.display_name) = lower($2)
+          AND u.role <> 'admin'
+         WHERE e.slug = $1
+         ON CONFLICT (user_id) DO NOTHING",
+    )
+    .bind(&state.config.event_slug)
+    .bind(display_name)
+    .execute(&state.pool)
+    .await;
+
+    // Broadcast unconditionally (carries no per-name info) so an online host's request
+    // badge updates without revealing whether the name existed.
+    let _ = state
+        .sse_tx
+        .send(crate::state::SseEvent::new("pin-reset-requested", "{}"));
+
+    Ok(StatusCode::NO_CONTENT)
+}

backend/src/auth/jwt.rs

@@ -46,10 +46,20 @@ pub fn create_token(
 }
 
 pub fn verify_token(token: &str, secret: &str) -> Result<Claims, jsonwebtoken::errors::Error> {
+    // We deliberately do NOT enforce the JWT's own `exp`. The authoritative session
+    // lifetime lives in the `session` row (`expires_at > NOW()`), which SLIDES forward on
+    // every authenticated request (see `Session::touch_and_renew`). Enforcing the JWT's
+    // fixed +Nd `exp` here would hard-log-out an actively-used client on day N+1 even
+    // though its session was renewed — the "30-day cliff" from the review. With server-
+    // side sliding sessions, the token is a signature-checked bearer credential and its
+    // lifetime is revocable (logout / expiry / ban all delete the row), which is strictly
+    // stronger than a stateless non-revocable exp.
+    let mut validation = Validation::default();
+    validation.validate_exp = false;
     let data = jsonwebtoken::decode::<Claims>(
         token,
         &DecodingKey::from_secret(secret.as_bytes()),
-        &Validation::default(),
+        &validation,
     )?;
     Ok(data.claims)
 }

backend/src/auth/middleware.rs

@@ -1,4 +1,4 @@
-use axum::extract::{FromRequestParts, State};
+use axum::extract::FromRequestParts;
 use axum::http::request::Parts;
 use uuid::Uuid;
 
@@ -13,6 +13,10 @@ pub struct AuthUser {
     pub user_id: Uuid,
     pub event_id: Uuid,
     pub role: UserRole,
+    /// Live ban flag. Banned users keep *read* access (per USER_JOURNEYS §10), so
+    /// the base extractor does NOT reject them — write handlers and the
+    /// Require{Host,Admin} extractors enforce the ban instead.
+    pub is_banned: bool,
     pub token_hash: String,
 }
 
@@ -33,31 +37,51 @@ impl FromRequestParts<AppState> for AuthUser {
             .strip_prefix("Bearer ")
             .ok_or_else(|| AppError::Unauthorized("Ungültiges Token-Format.".into()))?;
 
-        let claims = jwt::verify_token(token, &state.config.jwt_secret)
+        // Verify the JWT's signature. Expiry is deliberately NOT enforced here (see
+        // `jwt::verify_token`) — the authoritative, sliding session lifetime lives in the
+        // `session` row read below. We also don't trust the token's role/ban claims; the
+        // live user row is authoritative, so the decoded claims aren't needed beyond this.
+        jwt::verify_token(token, &state.config.jwt_secret)
             .map_err(|_| AppError::Unauthorized("Token ungültig oder abgelaufen.".into()))?;
 
         let token_hash = jwt::hash_token(token);
 
-        let session = Session::find_by_token_hash(&state.pool, &token_hash)
+        // Single round-trip: resolve the session token to its *live* user row. A
+        // role/ban stored in the token would survive a demote/ban for the full session
+        // lifetime (up to 30d), so we always re-read the user (a demoted host loses host
+        // powers immediately). We do NOT reject banned users here — they retain read
+        // access by design; writes and host/admin actions enforce the ban downstream.
+        let user = Session::find_user_by_token_hash(&state.pool, &token_hash)
             .await
             .map_err(|e| AppError::Internal(e.into()))?
-            .ok_or_else(|| AppError::Unauthorized("Sitzung nicht gefunden oder abgelaufen.".into()))?;
+            .ok_or_else(|| {
+                AppError::Unauthorized("Sitzung nicht gefunden oder abgelaufen.".into())
+            })?;
 
-        // Update last_seen_at in the background (fire-and-forget). Failures are
-        // non-fatal but worth surfacing — silent swallowing hides DB connection
-        // pressure that would otherwise be the first symptom of a real problem.
+        // Touch last_seen_at AND slide the session's expiry forward (fire-and-forget), so
+        // an active client's session renews instead of hitting the fixed 30-day cliff.
+        // Admin sessions keep their tighter 1-day window (they renew on activity but still
+        // lapse a day after the admin goes idle). Failures are non-fatal but worth
+        // surfacing — silent swallowing hides DB connection pressure that would otherwise
+        // be the first symptom of a real problem.
         let pool = state.pool.clone();
-        let session_id = session.id;
+        let touch_hash = token_hash.clone();
+        let expiry_days = if user.role == UserRole::Admin {
+            1
+        } else {
+            state.config.session_expiry_days
+        };
         tokio::spawn(async move {
-            if let Err(e) = Session::touch(&pool, session_id).await {
-                tracing::warn!(error = ?e, session_id = %session_id, "session touch failed");
+            if let Err(e) = Session::touch_and_renew(&pool, &touch_hash, expiry_days).await {
+                tracing::warn!(error = ?e, "session touch/renew failed");
             }
         });
 
         Ok(Self {
-            user_id: claims.sub,
-            event_id: claims.event_id,
-            role: claims.role,
+            user_id: user.id,
+            event_id: user.event_id,
+            role: user.role,
+            is_banned: user.is_banned,
             token_hash,
         })
     }
@@ -74,6 +98,9 @@ impl FromRequestParts<AppState> for RequireHost {
         state: &AppState,
     ) -> Result<Self, Self::Rejection> {
         let auth = AuthUser::from_request_parts(parts, state).await?;
+        if auth.is_banned {
+            return Err(AppError::Forbidden("Du bist gesperrt.".into()));
+        }
         match auth.role {
             UserRole::Host | UserRole::Admin => Ok(Self(auth)),
             _ => Err(AppError::Forbidden("Nur für Hosts und Admins.".into())),
@@ -92,6 +119,9 @@ impl FromRequestParts<AppState> for RequireAdmin {
         state: &AppState,
     ) -> Result<Self, Self::Rejection> {
         let auth = AuthUser::from_request_parts(parts, state).await?;
+        if auth.is_banned {
+            return Err(AppError::Forbidden("Du bist gesperrt.".into()));
+        }
         match auth.role {
             UserRole::Admin => Ok(Self(auth)),
             _ => Err(AppError::Forbidden("Nur für Admins.".into())),

backend/src/config.rs

@@ -1,11 +1,52 @@
 use std::path::PathBuf;
 
-use anyhow::{anyhow, Context, Result};
+use anyhow::{Context, Result, anyhow};
 
 /// Well-known dev JWT secret shipped in `.env.example`. If APP_ENV=production
 /// we refuse to start with this value; otherwise we warn loudly.
 const DEV_JWT_SECRET_SENTINEL: &str = "dev_secret_do_not_use_in_production_32byteslong_aaaa";
 
+/// A secret is "placeholder-ish" if it's the shipped dev sentinel or still carries
+/// the tell-tale scaffolding substrings from `.env.example`. Length alone is not
+/// enough — the shipped `change_me_...` placeholder is >32 chars.
+fn looks_placeholder(s: &str) -> bool {
+    let lower = s.to_ascii_lowercase();
+    s == DEV_JWT_SECRET_SENTINEL
+        || lower.contains("change_me")
+        || lower.contains("dev_secret")
+        || lower.contains("placeholder")
+}
+
+/// Enforce secret hygiene. In production every guard is hard-fail: a booting app
+/// with a publicly-known signing key is worse than one that refuses to start.
+/// Outside production the dev sentinel is tolerated (warned) so local dev is frictionless.
+fn validate_secrets(is_prod: bool, jwt_secret: &str, admin_password_hash: &str) -> Result<()> {
+    if is_prod {
+        if looks_placeholder(jwt_secret) {
+            return Err(anyhow!(
+                "Refusing to start in production with a placeholder JWT_SECRET — \
+                 rotate it (openssl rand -hex 64)."
+            ));
+        }
+        if jwt_secret.len() < 32 {
+            return Err(anyhow!("JWT_SECRET must be at least 32 characters."));
+        }
+        if admin_password_hash.is_empty() || looks_placeholder(admin_password_hash) {
+            return Err(anyhow!(
+                "Refusing to start in production without a real ADMIN_PASSWORD_HASH — \
+                 generate one (htpasswd -bnBC 12 '' <password> | tr -d ':\\n')."
+            ));
+        }
+    } else if jwt_secret == DEV_JWT_SECRET_SENTINEL {
+        tracing::warn!(
+            "JWT_SECRET is the dev sentinel — fine for local development, NEVER ship this."
+        );
+    } else if jwt_secret.len() < 32 {
+        return Err(anyhow!("JWT_SECRET must be at least 32 characters."));
+    }
+    Ok(())
+}
+
 #[derive(Clone, Debug)]
 pub struct AppConfig {
     pub database_url: String,
@@ -15,51 +56,148 @@ pub struct AppConfig {
     pub event_name: String,
     pub event_slug: String,
     pub media_path: PathBuf,
+    /// Where export archives are written. MUST be outside `media_path` — that
+    /// directory is served by a public `ServeDir`, so a predictable archive name
+    /// under it would leak the whole gallery to anonymous visitors.
+    pub export_path: PathBuf,
     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());
+        let app_env = std::env::var("APP_ENV").unwrap_or_else(|_| "development".to_string());
         let is_prod = app_env.eq_ignore_ascii_case("production");
 
         let jwt_secret = std::env::var("JWT_SECRET").context("JWT_SECRET must be set")?;
-        if jwt_secret == DEV_JWT_SECRET_SENTINEL {
-            if is_prod {
-                return Err(anyhow!(
-                    "Refusing to start in production with the well-known dev JWT_SECRET — \
-                     rotate it (openssl rand -hex 64)."
-                ));
-            }
-            tracing::warn!(
-                "JWT_SECRET is the dev sentinel — fine for local development, NEVER ship this."
-            );
-        } else if jwt_secret.len() < 32 {
-            return Err(anyhow!("JWT_SECRET must be at least 32 characters."));
-        }
+        let admin_password_hash = std::env::var("ADMIN_PASSWORD_HASH").unwrap_or_default();
+
+        validate_secrets(is_prod, &jwt_secret, &admin_password_hash)?;
 
         Ok(Self {
-            database_url: std::env::var("DATABASE_URL")
-                .context("DATABASE_URL must be set")?,
+            database_url: std::env::var("DATABASE_URL").context("DATABASE_URL must be set")?,
             jwt_secret,
             session_expiry_days: std::env::var("SESSION_EXPIRY_DAYS")
                 .unwrap_or_else(|_| "30".to_string())
                 .parse()
                 .context("SESSION_EXPIRY_DAYS must be a number")?,
-            admin_password_hash: std::env::var("ADMIN_PASSWORD_HASH")
-                .unwrap_or_default(),
-            event_name: std::env::var("EVENT_NAME")
-                .unwrap_or_else(|_| "EventSnap".to_string()),
-            event_slug: std::env::var("EVENT_SLUG")
-                .context("EVENT_SLUG must be set")?,
+            admin_password_hash,
+            event_name: std::env::var("EVENT_NAME").unwrap_or_else(|_| "EventSnap".to_string()),
+            event_slug: std::env::var("EVENT_SLUG").context("EVENT_SLUG must be set")?,
             media_path: PathBuf::from(
                 std::env::var("MEDIA_PATH").unwrap_or_else(|_| "/media".to_string()),
             ),
+            export_path: PathBuf::from(
+                std::env::var("EXPORT_PATH").unwrap_or_else(|_| "/exports".to_string()),
+            ),
             app_port: std::env::var("APP_PORT")
                 .unwrap_or_else(|_| "3000".to_string())
                 .parse()
                 .context("APP_PORT must be a number")?,
+            compression_concurrency: std::env::var("COMPRESSION_WORKER_CONCURRENCY")
+                .ok()
+                .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()),
         })
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    const REAL_SECRET: &str = "a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6a7b8c9d0e1f2a3b4c5d6e7f8a9b0c1d2";
+    const REAL_HASH: &str = "$2y$12$abcdefghijklmnopqrstuv.wxyzABCDEFGHIJKLMNOPQRSTUVWXYZ012";
+
+    #[test]
+    fn prod_rejects_shipped_placeholder_secret() {
+        // The exact string shipped in `.env` — >32 chars, so it must be caught by
+        // the substring guard, not the length check.
+        let err = validate_secrets(true, "change_me_to_a_random_64_byte_hex_string", REAL_HASH);
+        assert!(
+            err.is_err(),
+            "placeholder JWT_SECRET must be rejected in prod"
+        );
+    }
+
+    #[test]
+    fn prod_rejects_dev_sentinel_and_short_secret() {
+        assert!(validate_secrets(true, DEV_JWT_SECRET_SENTINEL, REAL_HASH).is_err());
+        assert!(validate_secrets(true, "tooshort", REAL_HASH).is_err());
+    }
+
+    #[test]
+    fn prod_rejects_missing_or_placeholder_admin_hash() {
+        assert!(validate_secrets(true, REAL_SECRET, "").is_err());
+        assert!(validate_secrets(true, REAL_SECRET, "$2y$12$placeholder_replace_me").is_err());
+    }
+
+    #[test]
+    fn prod_accepts_real_secrets() {
+        assert!(validate_secrets(true, REAL_SECRET, REAL_HASH).is_ok());
+    }
+
+    #[test]
+    fn non_prod_tolerates_dev_sentinel() {
+        assert!(validate_secrets(false, DEV_JWT_SECRET_SENTINEL, "").is_ok());
+    }
+
+    #[test]
+    fn non_prod_still_rejects_short_non_sentinel_secret() {
+        assert!(validate_secrets(false, "tooshort", "").is_err());
+    }
+
+    #[test]
+    fn placeholder_detection_is_case_insensitive() {
+        // looks_placeholder lowercases before matching — an upper/mixed-case
+        // placeholder must still be rejected in prod.
+        assert!(
+            validate_secrets(true, "CHANGE_ME_TO_A_RANDOM_64_BYTE_HEX_STRING", REAL_HASH).is_err()
+        );
+        assert!(validate_secrets(true, REAL_SECRET, "$2Y$12$PLACEHOLDER_replace_me").is_err());
+    }
+
+    #[test]
+    fn prod_len_boundary_at_32() {
+        // Exactly 32 non-placeholder chars is the minimum accepted; 31 is rejected.
+        const LEN_32: &str = "abcdefghijklmnopqrstuvwxyz012345";
+        const LEN_31: &str = "abcdefghijklmnopqrstuvwxyz01234";
+        assert_eq!(LEN_32.len(), 32);
+        assert_eq!(LEN_31.len(), 31);
+        assert!(validate_secrets(true, LEN_32, REAL_HASH).is_ok());
+        assert!(validate_secrets(true, LEN_31, REAL_HASH).is_err());
+    }
+}

backend/src/db.rs

@@ -1,6 +1,6 @@
 use anyhow::{Context, Result};
-use sqlx::postgres::PgPoolOptions;
 use sqlx::PgPool;
+use sqlx::postgres::PgPoolOptions;
 
 const DEFAULT_MAX_CONNECTIONS: u32 = 10;
 

backend/src/error.rs

@@ -6,10 +6,19 @@ pub enum AppError {
     BadRequest(String),
     Unauthorized(String),
     Forbidden(String),
+    /// Uploads are temporarily locked (event closed / gallery released). Distinct from
+    /// `Forbidden` so the client can tell this REVERSIBLE 403 apart from a permanent one
+    /// (banned user, quota): the queued blob is kept and retried if the host reopens,
+    /// instead of being purged like a genuinely-terminal rejection.
+    UploadsLocked(String),
     NotFound(String),
     Conflict(String),
     /// Second field: optional retry-after seconds to include in the response.
     TooManyRequests(String, Option<u64>),
+    /// Per-user storage quota exhausted. Distinct from `TooManyRequests` (rate limit) so
+    /// the client can treat it as *terminal* (413, no retry) instead of backing off and
+    /// retrying a permanently-failing upload forever.
+    QuotaExceeded(String),
     Internal(anyhow::Error),
 }
 
@@ -19,9 +28,11 @@ impl AppError {
             Self::BadRequest(_) => (StatusCode::BAD_REQUEST, "bad_request"),
             Self::Unauthorized(_) => (StatusCode::UNAUTHORIZED, "unauthorized"),
             Self::Forbidden(_) => (StatusCode::FORBIDDEN, "forbidden"),
+            Self::UploadsLocked(_) => (StatusCode::FORBIDDEN, "uploads_locked"),
             Self::NotFound(_) => (StatusCode::NOT_FOUND, "not_found"),
             Self::Conflict(_) => (StatusCode::CONFLICT, "conflict"),
             Self::TooManyRequests(..) => (StatusCode::TOO_MANY_REQUESTS, "too_many_requests"),
+            Self::QuotaExceeded(_) => (StatusCode::PAYLOAD_TOO_LARGE, "quota_exceeded"),
             Self::Internal(_) => (StatusCode::INTERNAL_SERVER_ERROR, "internal_error"),
         }
     }
@@ -31,9 +42,11 @@ impl AppError {
             Self::BadRequest(msg)
             | Self::Unauthorized(msg)
             | Self::Forbidden(msg)
+            | Self::UploadsLocked(msg)
             | Self::NotFound(msg)
             | Self::Conflict(msg) => msg.clone(),
             Self::TooManyRequests(msg, _) => msg.clone(),
+            Self::QuotaExceeded(msg) => msg.clone(),
             Self::Internal(err) => {
                 tracing::error!("internal error: {err:#}");
                 "Ein interner Fehler ist aufgetreten.".to_string()
@@ -62,10 +75,11 @@ impl IntoResponse for AppError {
         }
 
         let mut resp = (status, axum::Json(body)).into_response();
-        if let Some(secs) = retry_after_secs {
-            if let Ok(val) = axum::http::HeaderValue::from_str(&secs.to_string()) {
-                resp.headers_mut().insert(axum::http::header::RETRY_AFTER, val);
-            }
+        if let Some(secs) = retry_after_secs
+            && let Ok(val) = axum::http::HeaderValue::from_str(&secs.to_string())
+        {
+            resp.headers_mut()
+                .insert(axum::http::header::RETRY_AFTER, val);
         }
         resp
     }

backend/src/handlers/admin.rs

@@ -1,11 +1,10 @@
 use std::collections::HashMap;
 use std::time::Duration;
 
+use axum::Json;
 use axum::extract::{Query, State};
 use axum::http::{HeaderMap, StatusCode};
-use axum::Json;
 use serde::{Deserialize, Serialize};
-use sysinfo::System;
 
 use crate::auth::middleware::RequireAdmin;
 use crate::error::AppError;
@@ -46,19 +45,17 @@ pub async fn get_stats(
         .await?
         .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
 
-    let (user_count,): (i64,) =
-        sqlx::query_as("SELECT COUNT(*) FROM \"user\" WHERE event_id = $1")
+    let (user_count,): (i64,) = sqlx::query_as("SELECT COUNT(*) FROM \"user\" WHERE event_id = $1")
+        .bind(event.id)
+        .fetch_one(&state.pool)
+        .await?;
+
+    let (upload_count,): (i64,) =
+        sqlx::query_as("SELECT COUNT(*) FROM upload WHERE event_id = $1 AND deleted_at IS NULL")
             .bind(event.id)
             .fetch_one(&state.pool)
             .await?;
 
-    let (upload_count,): (i64,) = sqlx::query_as(
-        "SELECT COUNT(*) FROM upload WHERE event_id = $1 AND deleted_at IS NULL",
-    )
-    .bind(event.id)
-    .fetch_one(&state.pool)
-    .await?;
-
     let (comment_count,): (i64,) = sqlx::query_as(
         "SELECT COUNT(*) FROM comment c
          JOIN upload u ON u.id = c.upload_id
@@ -68,23 +65,12 @@ pub async fn get_stats(
     .fetch_one(&state.pool)
     .await?;
 
-    // Disk usage via sysinfo
-    let mut sys = System::new();
-    sys.refresh_all();
-
-    let media_path = state.config.media_path.to_string_lossy().to_string();
-    let (disk_total, disk_free) = sysinfo::Disks::new_with_refreshed_list()
-        .iter()
-        .find(|d| media_path.starts_with(d.mount_point().to_string_lossy().as_ref()))
-        .map(|d| (d.total_space(), d.available_space()))
-        .unwrap_or_else(|| {
-            // Fall back to the root disk
-            sysinfo::Disks::new_with_refreshed_list()
-                .iter()
-                .find(|d| d.mount_point().to_string_lossy() == "/")
-                .map(|d| (d.total_space(), d.available_space()))
-                .unwrap_or((0, 0))
-        });
+    // Disk usage from the shared cache (unknown mount → zeros, same as before).
+    let (disk_total, disk_free) = state
+        .disk_cache
+        .snapshot(&state.config.media_path)
+        .map(|d| (d.total, d.free))
+        .unwrap_or((0, 0));
 
     let disk_used = disk_total.saturating_sub(disk_free);
 
@@ -102,14 +88,17 @@ pub async fn get_config(
     State(state): State<AppState>,
     RequireAdmin(_auth): RequireAdmin,
 ) -> Result<Json<HashMap<String, String>>, AppError> {
-    let rows: Vec<(String, String)> =
-        sqlx::query_as("SELECT key, value FROM config ORDER BY key")
-            .fetch_all(&state.pool)
-            .await?;
+    let rows: Vec<(String, String)> = sqlx::query_as("SELECT key, value FROM config ORDER BY key")
+        .fetch_all(&state.pool)
+        .await?;
 
     Ok(Json(rows.into_iter().collect()))
 }
 
+/// Documents the wire shape of `PATCH /admin/config` (a flat `{key: value}` object).
+/// `patch_config` extracts the `HashMap` directly rather than going through this newtype, so it is
+/// never constructed in Rust — it stays as the serde-derived description of the request body.
+#[allow(dead_code)]
 #[derive(Deserialize)]
 pub struct PatchConfigRequest(pub HashMap<String, String>);
 
@@ -121,15 +110,18 @@ pub async fn patch_config(
     // Numeric keys validated as f64; boolean keys validated as truthy strings; the
     // privacy note is free text. Splitting these explicitly is verbose but makes the
     // failure mode for typos obvious (`Unbekannter Schlüssel: ...`).
-    const NUMERIC_KEYS: &[&str] = &[
-        "max_image_size_mb",
-        "max_video_size_mb",
-        "upload_rate_per_hour",
-        "feed_rate_per_min",
-        "export_rate_per_day",
-        "quota_tolerance",
-        "estimated_guest_count",
-        "compression_concurrency",
+    // (key, integer_only, min, max). Ranges reject values that `parse::<f64>` would
+    // accept but that silently revert to the hardcoded default at read time
+    // (get_usize/get_i64 can't parse negatives/NaN/fractionals). `compression_concurrency`
+    // is intentionally absent — it's read once at boot, so a live edit was a no-op.
+    const NUMERIC_SPECS: &[(&str, bool, f64, f64)] = &[
+        ("max_image_size_mb", true, 1.0, 1024.0),
+        ("max_video_size_mb", true, 1.0, 10240.0),
+        ("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),
+        ("quota_tolerance", false, 0.0, 1.0),
+        ("estimated_guest_count", true, 1.0, 1_000_000.0),
     ];
     const BOOL_KEYS: &[&str] = &[
         "rate_limits_enabled",
@@ -137,21 +129,61 @@ pub async fn patch_config(
         "feed_rate_enabled",
         "export_rate_enabled",
         "join_rate_enabled",
+        // These two per-area rate toggles are HONOURED by their handlers (auth/handlers.rs reads
+        // `admin_login_rate_enabled` and `recover_rate_enabled`, both defaulting true) but were
+        // missing from this allowlist — so the switch existed in code and could never be flipped.
+        "admin_login_rate_enabled",
+        "recover_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.
     for (key, value) in &body {
         let key_str = key.as_str();
-        if NUMERIC_KEYS.contains(&key_str) {
-            if value.parse::<f64>().is_err() {
+        if let Some(&(_, integer_only, min, max)) =
+            NUMERIC_SPECS.iter().find(|(k, ..)| *k == key_str)
+        {
+            let n = value.trim().parse::<f64>().ok().filter(|n| n.is_finite());
+            let n = match n {
+                Some(n) => n,
+                None => {
+                    return Err(AppError::BadRequest(format!(
+                        "Ungültiger Wert für {key}: muss eine Zahl sein."
+                    )));
+                }
+            };
+            if integer_only && n.fract() != 0.0 {
                 return Err(AppError::BadRequest(format!(
-                    "Ungültiger Wert für {key}: muss eine Zahl sein."
+                    "Ungültiger Wert für {key}: muss eine ganze Zahl sein."
+                )));
+            }
+            if n < min || n > max {
+                return Err(AppError::BadRequest(format!(
+                    "Wert für {key} liegt außerhalb des zulässigen Bereichs ({min}–{max})."
                 )));
             }
         } else if BOOL_KEYS.contains(&key_str) {
@@ -164,42 +196,83 @@ pub async fn patch_config(
                 }
             }
         } else if TEXT_KEYS.contains(&key_str) {
-            if value.len() > PRIVACY_NOTE_MAX_LEN {
+            // Count characters, not bytes — the message says "Zeichen" and a
+            // multi-byte grapheme shouldn't count against the limit multiple times.
+            if value.chars().count() > PRIVACY_NOTE_MAX_LEN {
                 return Err(AppError::BadRequest(format!(
                     "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!(
                 "Unbekannter Konfigurationsschlüssel: {key}"
             )));
         }
+    }
 
+    // Apply all writes in one transaction — the batch is all-or-nothing.
+    let mut tx = state.pool.begin().await?;
+    for (key, value) in &body {
         sqlx::query(
             "INSERT INTO config (key, value, updated_at) VALUES ($1, $2, NOW())
              ON CONFLICT (key) DO UPDATE SET value = EXCLUDED.value, updated_at = NOW()",
         )
         .bind(key)
         .bind(value)
-        .execute(&state.pool)
+        .execute(&mut *tx)
         .await?;
     }
+    tx.commit().await?;
+
+    // The config cache must reflect this write on the very next read (tests PATCH then
+    // immediately assert the new value takes effect). Invalidate synchronously here —
+    // the TTL is only a backstop and must not be relied on for correctness.
+    state.config_cache.invalidate();
 
     // 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,
@@ -238,6 +311,10 @@ pub async fn export_ticket(
     State(state): State<AppState>,
     auth: crate::auth::middleware::AuthUser,
 ) -> Json<serde_json::Value> {
+    // NOTE: intentionally NOT gated on `is_banned`. A banned user keeps *read* access
+    // by design (USER_JOURNEYS §10.3, FEATURES: "Can still download the export once
+    // released — Spec design choice"). The export is read-only, so it stays available
+    // to them, consistent with the read-only-ban model.
     let ticket = state.sse_tickets.issue(auth.token_hash);
     Json(serde_json::json!({ "ticket": ticket }))
 }
@@ -263,22 +340,50 @@ pub async fn download_zip(
     authenticate_download_ticket(&state, &q.ticket).await?;
     enforce_export_rate(&state, &headers).await?;
 
-    let event = crate::models::event::Event::find_by_slug(&state.pool, &state.config.event_slug)
-        .await?
-        .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
+    let path =
+        resolve_export_file(&state, "zip", "Der ZIP-Export ist noch nicht verfügbar.").await?;
+    serve_file(path, "Gallery.zip", "application/zip").await
+}
 
-    if !event.export_zip_ready {
-        return Err(AppError::NotFound(
-            "Der ZIP-Export ist noch nicht verfügbar.".into(),
-        ));
-    }
+/// Resolve the on-disk path of the CURRENT export generation — readiness check and path lookup in
+/// ONE read, through the `export_current` view (migration 014).
+///
+/// This used to be two statements: the caller checked `event.export_zip_ready`, then this fetched
+/// `export_job.file_path`. A reopen landing between them served a keepsake that should have 404'd —
+/// the same stale-keepsake class, leaking through the read path, and it existed only because
+/// readiness was a stored copy rather than a derivation. `export_current` gives both facts from one
+/// consistent snapshot: it yields a row only when the event is released AND the job is `done` at the
+/// event's current epoch, so "is it ready" and "which file" can no longer disagree.
+async fn resolve_export_file(
+    state: &AppState,
+    export_type: &str,
+    not_ready_msg: &str,
+) -> Result<std::path::PathBuf, AppError> {
+    let file_path: Option<(Option<String>,)> = sqlx::query_as(
+        "SELECT c.file_path FROM export_current c
+         JOIN event e ON e.id = c.event_id
+         WHERE e.slug = $1 AND c.type = $2::export_type AND c.status = 'done'",
+    )
+    .bind(&state.config.event_slug)
+    .bind(export_type)
+    .fetch_optional(&state.pool)
+    .await
+    .map_err(|e| AppError::Internal(e.into()))?;
 
-    let path = state.config.media_path.join("exports").join("Gallery.zip");
+    let Some((Some(rel),)) = file_path else {
+        return Err(AppError::NotFound(not_ready_msg.into()));
+    };
+
+    // `file_path` is stored as `exports/<name>`; the base dir is already `export_path`, so
+    // join only the file name (defends against any absolute/`..` content too).
+    let name = std::path::Path::new(&rel)
+        .file_name()
+        .ok_or_else(|| AppError::NotFound("Exportdatei nicht gefunden.".into()))?;
+    let path = state.config.export_path.join(name);
     if !path.exists() {
         return Err(AppError::NotFound("Exportdatei nicht gefunden.".into()));
     }
-
-    serve_file(path, "Gallery.zip", "application/zip").await
+    Ok(path)
 }
 
 pub async fn download_html(
@@ -289,21 +394,8 @@ pub async fn download_html(
     authenticate_download_ticket(&state, &q.ticket).await?;
     enforce_export_rate(&state, &headers).await?;
 
-    let event = crate::models::event::Event::find_by_slug(&state.pool, &state.config.event_slug)
-        .await?
-        .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
-
-    if !event.export_html_ready {
-        return Err(AppError::NotFound(
-            "Der HTML-Export ist noch nicht verfügbar.".into(),
-        ));
-    }
-
-    let path = state.config.media_path.join("exports").join("Memories.zip");
-    if !path.exists() {
-        return Err(AppError::NotFound("Exportdatei nicht gefunden.".into()));
-    }
-
+    let path =
+        resolve_export_file(&state, "html", "Der HTML-Export ist noch nicht verfügbar.").await?;
     serve_file(path, "Memories.zip", "application/zip").await
 }
 
@@ -313,7 +405,7 @@ async fn serve_file(
     content_type: &str,
 ) -> Result<axum::response::Response, AppError> {
     use axum::body::Body;
-    use axum::http::{header, Response, StatusCode};
+    use axum::http::{Response, StatusCode, header};
     use tokio_util::io::ReaderStream;
 
     let file = tokio::fs::File::open(&path)
@@ -349,8 +441,19 @@ pub async fn export_status(
 
     let released = event.export_released_at.is_some();
 
+    // ONE statement: the epoch comparison happens inside the query, against a single snapshot.
+    // Binding the epoch read by a previous statement would let a release/regeneration commit in
+    // between and yield `{released: true, zip: locked, html: locked}` — a state that never existed.
+    //
+    // Only jobs at the CURRENT epoch are reported. A row left behind by a retired generation (a
+    // 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 type::text, status::text, progress_pct FROM export_job WHERE event_id = $1",
+        "SELECT j.type::text, j.status::text, j.progress_pct
+           FROM export_job j
+           JOIN event e ON e.id = j.event_id
+          WHERE e.id = $1 AND j.epoch = e.export_epoch",
     )
     .bind(event.id)
     .fetch_all(&state.pool)
@@ -359,9 +462,7 @@ 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 })
-            })
+            .map(|(_, status, pct)| serde_json::json!({ "status": status, "progress_pct": pct }))
             .unwrap_or_else(|| serde_json::json!({ "status": "locked", "progress_pct": 0 }))
     };
 
@@ -376,13 +477,13 @@ pub async fn export_status(
 /// 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> {
-    let rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let export_rate_on = config::get_bool(&state.pool, "export_rate_enabled", true).await;
+    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.pool, "export_rate_per_day", 3).await;
+    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))

backend/src/handlers/feed.rs

@@ -1,8 +1,8 @@
 use std::time::Duration;
 
+use axum::Json;
 use axum::extract::{Query, State};
 use axum::http::HeaderMap;
-use axum::Json;
 use chrono::{DateTime, Utc};
 use serde::{Deserialize, Serialize};
 use uuid::Uuid;
@@ -27,6 +27,8 @@ 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 +50,7 @@ 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,
@@ -62,10 +65,10 @@ pub async fn feed(
     Query(q): Query<FeedQuery>,
 ) -> Result<Json<FeedResponse>, AppError> {
     let ip = client_ip(&headers, "unknown");
-    let rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let feed_rate_on = config::get_bool(&state.pool, "feed_rate_enabled", true).await;
+    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.pool, "feed_rate_per_min", 60).await;
+        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))
@@ -79,49 +82,51 @@ pub async fn feed(
 
     let limit = q.limit.unwrap_or(20).min(100);
 
+    // Resolve the cursor to a (created_at, id) position. The pair is compared as a
+    // tuple so ties on created_at break on id — keyset pagination on created_at
+    // alone would silently drop rows sharing a timestamp across a page boundary.
+    let (cursor_time, cursor_id) = match q.cursor {
+        Some(c) => match get_cursor_pos(&state.pool, c).await {
+            Some((t, id)) => (Some(t), Some(id)),
+            None => (None, None),
+        },
+        None => (None, None),
+    };
+
     let rows = if let Some(hashtag) = &q.hashtag {
         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
              WHERE v.event_id = $2
-               AND ($3::timestamptz IS NULL OR v.created_at < $3)
-             ORDER BY v.created_at DESC
-             LIMIT $4",
+               AND ($3::timestamptz IS NULL OR (v.created_at, v.id) < ($3, $4))
+             ORDER BY v.created_at DESC, v.id DESC
+             LIMIT $5",
         )
         .bind(&tag)
         .bind(auth.event_id)
-        .bind(
-            if let Some(cursor) = q.cursor {
-                get_cursor_time(&state.pool, cursor).await
-            } else {
-                None
-            },
-        )
+        .bind(cursor_time)
+        .bind(cursor_id)
         .bind(limit + 1)
         .fetch_all(&state.pool)
         .await?
     } 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 < $2)
-             ORDER BY created_at DESC
-             LIMIT $3",
+               AND ($2::timestamptz IS NULL OR (created_at, id) < ($2, $3))
+             ORDER BY created_at DESC, id DESC
+             LIMIT $4",
         )
         .bind(auth.event_id)
-        .bind(
-            if let Some(cursor) = q.cursor {
-                get_cursor_time(&state.pool, cursor).await
-            } else {
-                None
-            },
-        )
+        .bind(cursor_time)
+        .bind(cursor_id)
         .bind(limit + 1)
         .fetch_all(&state.pool)
         .await?
@@ -129,7 +134,11 @@ pub async fn feed(
 
     let has_more = rows.len() as i64 > limit;
     let rows: Vec<FeedRow> = rows.into_iter().take(limit as usize).collect();
-    let next_cursor = if has_more { rows.last().map(|r| r.id) } else { None };
+    let next_cursor = if has_more {
+        rows.last().map(|r| r.id)
+    } else {
+        None
+    };
 
     // Batch check which uploads the current user has liked
     let upload_ids: Vec<Uuid> = rows.iter().map(|r| r.id).collect();
@@ -138,8 +147,21 @@ pub async fn feed(
     let uploads = rows
         .into_iter()
         .map(|r| {
-            let preview_url = r.preview_path.map(|p| format!("/media/{p}"));
-            let thumbnail_url = r.thumbnail_path.map(|p| format!("/media/{p}"));
+            // Gated media aliases (visibility-checked, direct /media blocked). Emit the
+            // URL only when the variant actually exists — the URL is what signals the
+            // client which variant to load.
+            let preview_url = r
+                .preview_path
+                .as_ref()
+                .map(|_| format!("/api/v1/upload/{}/preview", r.id));
+            let thumbnail_url = r
+                .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,
@@ -147,6 +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,
@@ -171,6 +194,22 @@ pub struct DeltaQuery {
 pub struct DeltaResponse {
     pub uploads: Vec<FeedUpload>,
     pub deleted_ids: Vec<Uuid>,
+    /// Users whose uploads became hidden (banned / uploads_hidden) since `since`. A ban is
+    /// not a soft-delete, so it never appears in `deleted_ids`; without this, a client that
+    /// missed the ephemeral `user-hidden` SSE (a reconnecting projector, most acutely) would
+    /// keep displaying the banned user's already-loaded slides. The client evicts every
+    /// upload from these users on receipt.
+    pub hidden_user_ids: Vec<Uuid>,
+    /// True when the upload query hit `DELTA_LIMIT`: the response carries only the
+    /// newest slice of the gap, so the client must fall back to a full feed refresh
+    /// rather than merging (the older missed uploads are absent and unrecoverable
+    /// via a later delta, which advances `since` past them).
+    pub truncated: bool,
+    /// The server's clock at the moment this delta was computed. The client advances its
+    /// reconnect cursor from THIS, never `new Date()` — a browser clock even seconds fast
+    /// would otherwise silently skip uploads whose server `created_at` falls in the skew
+    /// window (they'd never reappear without a hard refresh).
+    pub server_time: DateTime<Utc>,
 }
 
 pub async fn feed_delta(
@@ -178,21 +217,78 @@ pub async fn feed_delta(
     auth: AuthUser,
     Query(q): Query<DeltaQuery>,
 ) -> Result<Json<DeltaResponse>, AppError> {
+    // Rate-limit the delta the same way as the paginated feed. Without this, ~100 clients
+    // reconnecting at once (post-outage, or a flapping network) each fire an unbounded
+    // delta fetch — a reconnect stampede. Keyed per-user so one client can't starve others
+    // behind a shared NAT.
+    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_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,
+            ));
+        }
+    }
+
+    // Anchor the next cursor to the DB clock, captured *before* the queries so an upload
+    // committed during this handler is re-fetched next time rather than skipped (a
+    // duplicate id merges idempotently on the client; a miss is unrecoverable).
+    let server_time: DateTime<Utc> = sqlx::query_scalar("SELECT NOW()")
+        .fetch_one(&state.pool)
+        .await?;
+
+    // Bounded like the paginated feed: a stale `since` could otherwise pull the
+    // entire event's uploads in one response. If a client hits the cap it should
+    // fall back to a full feed refresh rather than another delta.
+    const DELTA_LIMIT: i64 = 200;
+    // `>= since` (not `>`): `created_at` is not unique, so a strict `>` anchored to the exact
+    // timestamp of the last-seen upload silently drops a SECOND upload committed in the same
+    // microsecond — an unrecoverable live-update miss. `>=` re-includes the boundary rows;
+    // the client merges by id (see the feed-delta handler's `seen` set), so the duplicate is
+    // harmless while the tied upload is no longer lost. The cursor still advances to the
+    // 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",
+         WHERE event_id = $1 AND created_at >= $2
+         ORDER BY created_at DESC, id DESC
+         LIMIT $3",
+    )
+    .bind(auth.event_id)
+    .bind(q.since)
+    .bind(DELTA_LIMIT)
+    .fetch_all(&state.pool)
+    .await?;
+
+    // Hit the cap => this is only the newest slice of a larger gap. Signal the
+    // client to full-refresh instead of merging a partial delta.
+    let truncated = rows.len() as i64 >= DELTA_LIMIT;
+
+    // `>=` for the same tie-break reason as the uploads query above; re-signalling an
+    // already-removed id is idempotent on the client (it filters its list by these ids).
+    let deleted_ids: Vec<(Uuid,)> = sqlx::query_as(
+        "SELECT id FROM upload
+         WHERE event_id = $1 AND deleted_at IS NOT NULL AND deleted_at >= $2",
     )
     .bind(auth.event_id)
     .bind(q.since)
     .fetch_all(&state.pool)
     .await?;
 
-    let deleted_ids: Vec<(Uuid,)> = sqlx::query_as(
-        "SELECT id FROM upload
-         WHERE event_id = $1 AND deleted_at IS NOT NULL AND deleted_at > $2",
+    // Users hidden since the cursor (ban / uploads_hidden). Uncapped like `deleted_ids` and
+    // for the same reason — an eviction the client misses is unrecoverable via a later delta.
+    let hidden_user_ids: Vec<(Uuid,)> = sqlx::query_as(
+        "SELECT id FROM \"user\"
+         WHERE event_id = $1 AND uploads_hidden = TRUE
+           AND uploads_hidden_at IS NOT NULL AND uploads_hidden_at >= $2",
     )
     .bind(auth.event_id)
     .bind(q.since)
@@ -209,8 +305,18 @@ pub async fn feed_delta(
             id: r.id,
             user_id: r.user_id,
             uploader_name: r.uploader_name,
-            preview_url: r.preview_path.map(|p| format!("/media/{p}")),
-            thumbnail_url: r.thumbnail_path.map(|p| format!("/media/{p}")),
+            preview_url: r
+                .preview_path
+                .as_ref()
+                .map(|_| format!("/api/v1/upload/{}/preview", r.id)),
+            thumbnail_url: r
+                .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,
@@ -222,6 +328,9 @@ pub async fn feed_delta(
     Ok(Json(DeltaResponse {
         uploads,
         deleted_ids: deleted_ids.into_iter().map(|r| r.0).collect(),
+        hidden_user_ids: hidden_user_ids.into_iter().map(|r| r.0).collect(),
+        truncated,
+        server_time,
     }))
 }
 
@@ -235,12 +344,11 @@ pub async fn hashtags(
     State(state): State<AppState>,
     auth: AuthUser,
 ) -> Result<Json<Vec<HashtagCount>>, AppError> {
-    let rows: Vec<(String, i64)> = sqlx::query_as(
-        "SELECT tag, upload_count FROM v_hashtag_counts WHERE event_id = $1",
-    )
-    .bind(auth.event_id)
-    .fetch_all(&state.pool)
-    .await?;
+    let rows: Vec<(String, i64)> =
+        sqlx::query_as("SELECT tag, upload_count FROM v_hashtag_counts WHERE event_id = $1")
+            .bind(auth.event_id)
+            .fetch_all(&state.pool)
+            .await?;
 
     Ok(Json(
         rows.into_iter()
@@ -249,14 +357,17 @@ pub async fn hashtags(
     ))
 }
 
-async fn get_cursor_time(pool: &sqlx::PgPool, cursor_id: Uuid) -> Option<DateTime<Utc>> {
-    let row: Option<(DateTime<Utc>,)> =
-        sqlx::query_as("SELECT created_at FROM upload WHERE id = $1")
+/// Resolve a cursor id to its `(created_at, id)` position. Both are needed:
+/// `created_at` alone isn't unique, so pagination must break ties on `id` to
+/// avoid silently dropping rows that share a timestamp across a page boundary.
+async fn get_cursor_pos(pool: &sqlx::PgPool, cursor_id: Uuid) -> Option<(DateTime<Utc>, Uuid)> {
+    let row: Option<(DateTime<Utc>, Uuid)> =
+        sqlx::query_as("SELECT created_at, id FROM upload WHERE id = $1")
             .bind(cursor_id)
             .fetch_optional(pool)
             .await
             .ok()?;
-    row.map(|r| r.0)
+    row
 }
 
 async fn get_liked_set(
@@ -267,14 +378,13 @@ async fn get_liked_set(
     if upload_ids.is_empty() {
         return std::collections::HashSet::new();
     }
-    let rows: Vec<(Uuid,)> = sqlx::query_as(
-        "SELECT upload_id FROM \"like\" WHERE user_id = $1 AND upload_id = ANY($2)",
-    )
-    .bind(user_id)
-    .bind(upload_ids)
-    .fetch_all(pool)
-    .await
-    .unwrap_or_default();
+    let rows: Vec<(Uuid,)> =
+        sqlx::query_as("SELECT upload_id FROM \"like\" WHERE user_id = $1 AND upload_id = ANY($2)")
+            .bind(user_id)
+            .bind(upload_ids)
+            .fetch_all(pool)
+            .await
+            .unwrap_or_default();
 
     rows.into_iter().map(|r| r.0).collect()
 }

backend/src/handlers/host.rs

@@ -1,6 +1,6 @@
+use axum::Json;
 use axum::extract::{Path, State};
 use axum::http::StatusCode;
-use axum::Json;
 use chrono::{DateTime, Utc};
 use serde::{Deserialize, Serialize};
 use uuid::Uuid;
@@ -9,8 +9,10 @@ use crate::auth::middleware::RequireHost;
 use crate::error::AppError;
 use crate::models::comment::Comment;
 use crate::models::event::Event;
+use crate::models::session::Session;
 use crate::models::upload::Upload;
 use crate::models::user::UserRole;
+use crate::services::export::Affects;
 use crate::state::{AppState, SseEvent};
 
 // ── DTOs ─────────────────────────────────────────────────────────────────────
@@ -35,9 +37,24 @@ pub struct EventStatus {
     pub export_released: bool,
 }
 
-#[derive(Deserialize)]
-pub struct BanRequest {
-    pub hide_uploads: bool,
+/// Count non-banned hosts/admins in the event OTHER than `excluding` — the operators
+/// who would remain if `excluding` were demoted or banned. Used to enforce the "an event
+/// always keeps at least one operator" floor.
+async fn remaining_operators(
+    state: &AppState,
+    event_id: Uuid,
+    excluding: Uuid,
+) -> Result<i64, AppError> {
+    let count = sqlx::query_scalar::<_, i64>(
+        "SELECT COUNT(*) FROM \"user\"
+         WHERE event_id = $1 AND id != $2
+           AND role IN ('host', 'admin') AND is_banned = FALSE",
+    )
+    .bind(event_id)
+    .bind(excluding)
+    .fetch_one(&state.pool)
+    .await?;
+    Ok(count)
 }
 
 #[derive(Deserialize)]
@@ -93,11 +110,13 @@ pub async fn ban_user(
     State(state): State<AppState>,
     RequireHost(auth): RequireHost,
     Path(user_id): Path<Uuid>,
-    Json(body): Json<BanRequest>,
 ) -> Result<StatusCode, AppError> {
+    // The ban request carries no body — ban always hides (no per-request options).
     // Cannot ban yourself or another host/admin
     if user_id == auth.user_id {
-        return Err(AppError::BadRequest("Du kannst dich nicht selbst sperren.".into()));
+        return Err(AppError::BadRequest(
+            "Du kannst dich nicht selbst sperren.".into(),
+        ));
     }
     let target = sqlx::query_as::<_, (String,)>(
         "SELECT role::text FROM \"user\" WHERE id = $1 AND event_id = $2",
@@ -108,23 +127,74 @@ pub async fn ban_user(
     .await?
     .ok_or_else(|| AppError::NotFound("Benutzer nicht gefunden.".into()))?;
 
-    if target.0 == "admin" || (target.0 == "host" && auth.role != crate::models::user::UserRole::Admin) {
-        return Err(AppError::Forbidden("Du kannst diesen Benutzer nicht sperren.".into()));
+    if target.0 == "admin"
+        || (target.0 == "host" && auth.role != crate::models::user::UserRole::Admin)
+    {
+        return Err(AppError::Forbidden(
+            "Du kannst diesen Benutzer nicht sperren.".into(),
+        ));
     }
 
+    // Floor: never leave the event with zero operators. Banning removes the target from
+    // the active-operator pool, so refuse if they're the last non-banned host/admin.
+    if target.0 == "host" && remaining_operators(&state, auth.event_id, user_id).await? == 0 {
+        return Err(AppError::BadRequest(
+            "Der letzte Host kann nicht gesperrt werden.".into(),
+        ));
+    }
+
+    // Ban ALWAYS hides: a banned user's content is "gone" everywhere. The visibility
+    // views/queries now also filter on `is_banned` (defense in depth), and we set
+    // `uploads_hidden` so the existing `user-hidden` live-eviction path fires too. The old
+    // opt-out checkbox is gone — `hide_uploads` in the request is ignored.
+    //
+    // We deliberately do NOT revoke the banned user's sessions. This is a *read-only ban*
+    // by design (USER_JOURNEYS §10.3): the user keeps read access to the feed and can still
+    // download the released export — writes and host/admin actions are what the ban blocks
+    // (enforced live on the write handlers + Require{Host,Admin}). Revoking sessions would
+    // contradict that model, break the documented "banned guest can still download the
+    // keepsake" flow, and be ineffective anyway (the user could just /recover a new session).
+    //
+    // The ban and the keepsake invalidation are ONE transaction — see `host_delete_upload`.
+    let mut tx = state.pool.begin().await?;
     sqlx::query(
-        "UPDATE \"user\" SET is_banned = TRUE, uploads_hidden = $2 WHERE id = $1",
+        "UPDATE \"user\"
+         SET is_banned = TRUE, uploads_hidden = TRUE, uploads_hidden_at = NOW()
+         WHERE id = $1 AND event_id = $2",
     )
     .bind(user_id)
-    .bind(body.hide_uploads)
-    .execute(&state.pool)
+    .bind(auth.event_id)
+    .execute(&mut *tx)
     .await?;
 
+    // A ban hides the user's uploads EVERYWHERE — and the keepsake is the place that matters most,
+    // because it is the copy people keep. The export already filters `is_banned = FALSE`, so a
+    // FUTURE export excludes them; without this, an ALREADY-RELEASED archive would keep serving a
+    // banned user's photos forever. Same class as a takedown, so same treatment.
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        Affects::Both,
+    )
+    .await?;
+    tx.commit().await?;
+    if let Some(r) = regen {
+        start_regen(&state, r);
+    }
+
+    // Evict their content live from every feed + the diashow so it disappears without
+    // each viewer having to reload. (Their own SSE stream is separately dropped by the
+    // is_banned revalidation in `sse::stream`, so they stop receiving live pushes while
+    // retaining plain read access.)
+    let _ = state.sse_tx.send(SseEvent::new(
+        "user-hidden",
+        serde_json::json!({ "user_id": user_id }).to_string(),
+    ));
+
     tracing::info!(
         actor_user_id = %auth.user_id,
         target_user_id = %user_id,
         event_id = %auth.event_id,
-        hide_uploads = body.hide_uploads,
         "host: ban_user"
     );
 
@@ -136,16 +206,56 @@ pub async fn unban_user(
     RequireHost(auth): RequireHost,
     Path(user_id): Path<Uuid>,
 ) -> Result<StatusCode, AppError> {
-    let result = sqlx::query(
-        "UPDATE \"user\" SET is_banned = FALSE WHERE id = $1 AND event_id = $2",
+    // Mirror the ban guard: a host may only lift bans on guests, never on hosts or
+    // admins. Without this a host could override an admin's ban of another host,
+    // which is asymmetric with `ban_user` and lets a host escalate a peer back in.
+    let target = sqlx::query_as::<_, (String,)>(
+        "SELECT role::text FROM \"user\" WHERE id = $1 AND event_id = $2",
     )
     .bind(user_id)
     .bind(auth.event_id)
-    .execute(&state.pool)
+    .fetch_optional(&state.pool)
+    .await?
+    .ok_or_else(|| AppError::NotFound("Benutzer nicht gefunden.".into()))?;
+
+    if target.0 == "admin"
+        || (target.0 == "host" && auth.role != crate::models::user::UserRole::Admin)
+    {
+        return Err(AppError::Forbidden(
+            "Du kannst diesen Benutzer nicht entsperren.".into(),
+        ));
+    }
+
+    // Unban restores visibility too: ban set `uploads_hidden = TRUE`, so clearing only
+    // `is_banned` would leave their content invisible. Clear all three (the timestamp too,
+    // so a future ban stamps a fresh `uploads_hidden_at` the reconnect delta will replay).
+    let mut tx = state.pool.begin().await?;
+    let result = sqlx::query(
+        "UPDATE \"user\"
+         SET is_banned = FALSE, uploads_hidden = FALSE, uploads_hidden_at = NULL
+         WHERE id = $1 AND event_id = $2",
+    )
+    .bind(user_id)
+    .bind(auth.event_id)
+    .execute(&mut *tx)
     .await?;
     if result.rows_affected() == 0 {
         return Err(AppError::NotFound("Benutzer nicht gefunden.".into()));
     }
+
+    // The mirror of the ban case: an unban RESTORES their uploads to the export query, so an
+    // already-released keepsake is now missing content it should contain. Rebuild it.
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        Affects::Both,
+    )
+    .await?;
+    tx.commit().await?;
+    if let Some(r) = regen {
+        start_regen(&state, r);
+    }
+
     tracing::info!(
         actor_user_id = %auth.user_id,
         target_user_id = %user_id,
@@ -155,6 +265,55 @@ pub async fn unban_user(
     Ok(StatusCode::NO_CONTENT)
 }
 
+/// Force a keepsake rebuild. The ESCAPE HATCH.
+///
+/// Without this, a failed or stranded export is terminal at runtime: `release_gallery` refuses an
+/// already-released event ("bereits freigegeben"), `recover_exports` only runs at boot, and there is
+/// no other retry path — so the host's only options were restarting the container or reopening the
+/// event (which unlocks uploads to every guest and discards the release). This is also the recovery
+/// path for a keepsake that went stale for any reason we haven't thought of.
+pub async fn rebuild_export(
+    State(state): State<AppState>,
+    RequireHost(auth): RequireHost,
+) -> Result<StatusCode, AppError> {
+    let mut tx = state.pool.begin().await?;
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        Affects::Both,
+    )
+    .await?;
+    tx.commit().await?;
+
+    let Some(r) = regen else {
+        return Err(AppError::BadRequest(
+            "Die Galerie ist nicht freigegeben — es gibt nichts neu zu erzeugen.".into(),
+        ));
+    };
+
+    // No debounce: this is an explicit, deliberate host action, not a burst.
+    for export_type in ["zip", "html"] {
+        let _ = state.sse_tx.send(SseEvent::new(
+            "export-progress",
+            serde_json::json!({ "type": export_type, "progress_pct": 0 }).to_string(),
+        ));
+    }
+    crate::services::export::spawn_export_jobs(
+        r.event_id,
+        r.event_name,
+        r.epoch,
+        state.config.comments_enabled,
+        std::time::Duration::ZERO,
+        state.pool.clone(),
+        state.config.media_path.clone(),
+        state.config.export_path.clone(),
+        state.sse_tx.clone(),
+    );
+
+    tracing::info!(actor_user_id = %auth.user_id, "host: rebuild_export");
+    Ok(StatusCode::NO_CONTENT)
+}
+
 pub async fn set_role(
     State(state): State<AppState>,
     RequireHost(auth): RequireHost,
@@ -172,14 +331,15 @@ pub async fn set_role(
         _ => {
             return Err(AppError::BadRequest(
                 "Ungültige Rolle. Erlaubt: guest, host.".into(),
-            ))
+            ));
         }
     };
 
-    // Look up the current role so we can apply the host-vs-admin guard. Hosts may
-    // promote guests and demote *other* hosts (the user explicitly requested this
-    // expansion). Hosts may not touch admins. Admins may do anything (except change
-    // themselves, blocked above).
+    // Look up the current role so we can apply the host-vs-admin guard. A plain host may
+    // promote/demote GUESTS only; it may not change any host's or admin's role (see the
+    // guard below — this closes the demote-a-peer-host→ban/PIN-reset takeover chain, F1).
+    // Only an admin may change a host's role. Admins may do anything except change
+    // themselves (blocked above).
     let target = sqlx::query_as::<_, (String,)>(
         "SELECT role::text FROM \"user\" WHERE id = $1 AND event_id = $2",
     )
@@ -189,9 +349,25 @@ pub async fn set_role(
     .await?
     .ok_or_else(|| AppError::NotFound("Benutzer nicht gefunden.".into()))?;
 
-    if target.0 == "admin" {
+    // Admins are untouchable by hosts. A plain host also may not demote another
+    // *host*: without this guard a host could demote a peer host to guest and then
+    // ban / PIN-reset (→ account-takeover via /recover) them — the ban/pin-reset peer
+    // guards key off the target's *current* role, so a prior demotion would launder
+    // past them. Only an admin may change a host's role.
+    if target.0 == "admin" || (target.0 == "host" && auth.role != UserRole::Admin) {
         return Err(AppError::Forbidden(
-            "Admins können nicht geändert werden.".into(),
+            "Du darfst die Rolle dieses Benutzers nicht ändern.".into(),
+        ));
+    }
+
+    // Floor: demoting the last non-banned host/admin to guest would leave the event with
+    // no operator. Refuse.
+    if new_role == "guest"
+        && target.0 == "host"
+        && remaining_operators(&state, auth.event_id, user_id).await? == 0
+    {
+        return Err(AppError::BadRequest(
+            "Der letzte Host kann nicht zum Gast gemacht werden.".into(),
         ));
     }
 
@@ -252,26 +428,41 @@ pub async fn reset_user_pin(
         _ => {
             return Err(AppError::Forbidden(
                 "Du darfst die PIN dieses Benutzers nicht zurücksetzen.".into(),
-            ))
+            ));
         }
     }
 
     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 = bcrypt::hash(&pin, 12).map_err(|e| AppError::Internal(anyhow::anyhow!(e)))?;
 
     sqlx::query(
         "UPDATE \"user\"
          SET recovery_pin_hash = $1,
-             pin_failed_attempts = 0,
+             failed_pin_attempts = 0,
              pin_locked_until = NULL
-         WHERE id = $2",
+         WHERE id = $2 AND event_id = $3",
     )
     .bind(&pin_hash)
     .bind(user_id)
+    .bind(auth.event_id)
     .execute(&state.pool)
     .await?;
 
+    // A PIN reset means the old credential is compromised/forgotten — revoke every
+    // existing session so old devices must re-authenticate with the new PIN. This is a
+    // security-relevant revoke: if it fails, the old sessions stay valid (sessions are
+    // token- not PIN-bound), so surface the error in logs rather than swallowing it
+    // silently while reporting success to the host.
+    if let Err(e) = Session::delete_all_for_user(&state.pool, user_id).await {
+        tracing::error!(error = ?e, user_id = %user_id, "PIN reset: failed to revoke sessions");
+    }
+
+    // Resolve any pending in-app "I forgot my PIN" request for this user.
+    let _ = sqlx::query("DELETE FROM pin_reset_request WHERE user_id = $1")
+        .bind(user_id)
+        .execute(&state.pool)
+        .await;
+
     // Notify the *recipient* device(s) if they happen to be online so they can clear
     // their cached local PIN. They'll save the new one on the next /recover.
     let _ = state.sse_tx.send(SseEvent::new(
@@ -289,6 +480,88 @@ pub async fn reset_user_pin(
     Ok(Json(PinResetResponse { pin }))
 }
 
+#[derive(Serialize, sqlx::FromRow)]
+pub struct PinResetRequestSummary {
+    pub id: Uuid,
+    pub user_id: Uuid,
+    pub display_name: String,
+    pub created_at: DateTime<Utc>,
+}
+
+/// List pending in-app PIN-reset requests so a host can action them (via the existing
+/// `reset_user_pin`, which also clears the request).
+pub async fn list_pin_reset_requests(
+    State(state): State<AppState>,
+    RequireHost(auth): RequireHost,
+) -> Result<Json<Vec<PinResetRequestSummary>>, AppError> {
+    let rows = sqlx::query_as::<_, PinResetRequestSummary>(
+        "SELECT r.id, r.user_id, u.display_name, r.created_at
+         FROM pin_reset_request r
+         JOIN \"user\" u ON u.id = r.user_id
+         WHERE r.event_id = $1
+         ORDER BY r.created_at ASC",
+    )
+    .bind(auth.event_id)
+    .fetch_all(&state.pool)
+    .await?;
+    Ok(Json(rows))
+}
+
+/// Dismiss a PIN-reset request without resetting (e.g. the host couldn't verify the
+/// requester's identity).
+pub async fn dismiss_pin_reset_request(
+    State(state): State<AppState>,
+    RequireHost(auth): RequireHost,
+    Path(id): Path<Uuid>,
+) -> Result<StatusCode, AppError> {
+    sqlx::query("DELETE FROM pin_reset_request WHERE id = $1 AND event_id = $2")
+        .bind(id)
+        .bind(auth.event_id)
+        .execute(&state.pool)
+        .await?;
+    Ok(StatusCode::NO_CONTENT)
+}
+
+/// Content changed AFTER the gallery was released — regenerate the keepsake.
+///
+/// Deleting a photo used to remove it from the live feed but leave it in the already-generated
+/// archive FOREVER: the old `if ready { continue }` skip guaranteed the export was never rebuilt.
+/// For a takedown ("please remove my photo") that is the one place it most needs to disappear.
+///
+/// Bumping the epoch (while staying released) retires the current generation, so the stale archive
+/// stops being downloadable the instant the delete commits, and a fresh worker rebuilds it without
+/// the removed content. The download 404s in the meantime, which is the correct answer — serving
+/// the old archive would serve the deleted photo.
+/// Start the workers for a regeneration that was armed inside a (now-committed) transaction, and
+/// tell every client the current keepsake just became undownloadable.
+///
+/// The SSE matters: bumping the epoch retires the archive INSTANTLY, so `/export/zip` starts 404ing
+/// the moment the change commits. Without a nudge, a guest sitting on `/export` keeps rendering an
+/// enabled "download" button for the whole rebuild. Both the nav badge and the export page already
+/// refetch `/export/status` on `export-progress`, so a 0% tick is the cheapest correct signal.
+pub fn start_regen(state: &AppState, regen: crate::services::export::PendingRegen) {
+    for export_type in ["zip", "html"] {
+        let _ = state.sse_tx.send(SseEvent::new(
+            "export-progress",
+            serde_json::json!({ "type": export_type, "progress_pct": 0 }).to_string(),
+        ));
+    }
+    crate::services::export::spawn_export_jobs(
+        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.
+        crate::services::export::REGEN_DEBOUNCE,
+        state.pool.clone(),
+        state.config.media_path.clone(),
+        state.config.export_path.clone(),
+        state.sse_tx.clone(),
+    );
+}
+
 pub async fn host_delete_upload(
     State(state): State<AppState>,
     RequireHost(auth): RequireHost,
@@ -298,15 +571,29 @@ pub async fn host_delete_upload(
         .await?
         .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
 
-    let deleted = Upload::soft_delete_in_event(&state.pool, upload_id, auth.event_id).await?;
+    // The delete and the keepsake invalidation are ONE transaction: if the delete committed and the
+    // invalidation didn't, the taken-down photo would stay downloadable forever and nothing would
+    // notice (the keepsake still looks complete, and the host can no longer find the upload to retry).
+    let mut tx = state.pool.begin().await?;
+    let deleted = Upload::soft_delete_in_event(&mut tx, upload_id, auth.event_id).await?;
     if !deleted {
         return Err(AppError::NotFound("Upload nicht gefunden.".into()));
     }
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        Affects::Both,
+    )
+    .await?;
+    tx.commit().await?;
 
     let _ = state.sse_tx.send(SseEvent::new(
         "upload-deleted",
         serde_json::json!({ "upload_id": upload.id }).to_string(),
     ));
+    if let Some(r) = regen {
+        start_regen(&state, r);
+    }
 
     tracing::info!(
         actor_user_id = %auth.user_id,
@@ -323,11 +610,29 @@ pub async fn host_delete_comment(
     RequireHost(auth): RequireHost,
     Path(comment_id): Path<Uuid>,
 ) -> Result<StatusCode, AppError> {
-    let deleted =
-        Comment::soft_delete_in_event(&state.pool, comment_id, auth.event_id).await?;
+    let mut tx = state.pool.begin().await?;
+    let deleted = Comment::soft_delete_in_event(&mut tx, comment_id, auth.event_id).await?;
     if !deleted {
         return Err(AppError::NotFound("Kommentar nicht gefunden.".into()));
     }
+    // Only the HTML viewer embeds comments — the ZIP is media-only, so it is carried forward rather
+    // than rebuilt. Otherwise moderating one comment would 404 the photo download for minutes to
+    // change nothing in it.
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        Affects::ViewerOnly,
+    )
+    .await?;
+    tx.commit().await?;
+
+    let _ = state.sse_tx.send(SseEvent::new(
+        "comment-deleted",
+        serde_json::json!({ "comment_id": comment_id }).to_string(),
+    ));
+    if let Some(r) = regen {
+        start_regen(&state, r);
+    }
     tracing::info!(
         actor_user_id = %auth.user_id,
         event_id = %auth.event_id,
@@ -341,14 +646,18 @@ pub async fn close_event(
     State(state): State<AppState>,
     RequireHost(_auth): RequireHost,
 ) -> Result<StatusCode, AppError> {
-    sqlx::query(
+    let result = sqlx::query(
         "UPDATE event SET uploads_locked_at = NOW() WHERE slug = $1 AND uploads_locked_at IS NULL",
     )
     .bind(&state.config.event_slug)
     .execute(&state.pool)
     .await?;
 
-    let _ = state.sse_tx.send(SseEvent::new("event-closed", "{}"));
+    // Only broadcast when this call actually flipped the lock — closing an
+    // already-closed event is a no-op and shouldn't spam listeners.
+    if result.rows_affected() > 0 {
+        let _ = state.sse_tx.send(SseEvent::new("event-closed", "{}"));
+    }
 
     Ok(StatusCode::NO_CONTENT)
 }
@@ -357,14 +666,29 @@ pub async fn open_event(
     State(state): State<AppState>,
     RequireHost(_auth): RequireHost,
 ) -> Result<StatusCode, AppError> {
-    sqlx::query(
-        "UPDATE event SET uploads_locked_at = NULL WHERE slug = $1",
+    // Reopening invalidates any prior release: the keepsake was snapshotted at release time, so
+    // allowing new uploads afterwards would silently diverge the live feed from the frozen export.
+    //
+    // ONE statement retires the entire export generation. Bumping `export_epoch` in the same write
+    // that clears `export_released_at` instantly invalidates every in-flight worker, every `done`
+    // row and all readiness — because readiness is DERIVED from this epoch (migration 014), not
+    // stored. There is no export_job row to touch and nothing to keep in sync, so this needs no
+    // transaction. Any worker still streaming holds the old epoch and is now inert: its
+    // epoch-guarded finalize matches nothing, and it discards its own output.
+    let result = sqlx::query(
+        "UPDATE event
+         SET uploads_locked_at  = NULL,
+             export_released_at = NULL,
+             export_epoch       = export_epoch + 1
+         WHERE slug = $1 AND (uploads_locked_at IS NOT NULL OR export_released_at IS NOT NULL)",
     )
     .bind(&state.config.event_slug)
     .execute(&state.pool)
     .await?;
 
-    let _ = state.sse_tx.send(SseEvent::new("event-opened", "{}"));
+    if result.rows_affected() > 0 {
+        let _ = state.sse_tx.send(SseEvent::new("event-opened", "{}"));
+    }
 
     Ok(StatusCode::NO_CONTENT)
 }
@@ -373,37 +697,69 @@ pub async fn release_gallery(
     State(state): State<AppState>,
     RequireHost(_auth): RequireHost,
 ) -> Result<StatusCode, AppError> {
-    let event = Event::find_by_slug(&state.pool, &state.config.event_slug)
-        .await?
-        .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
+    // The release claim, the epoch bump, the upload lock and BOTH job rows are written in ONE
+    // transaction. Two reasons, both of which were live bugs:
+    //
+    //  1. Cancellation. This handler used to commit `export_released_at` and only THEN await the
+    //     enqueue. Axum drops the handler future when the client disconnects (closed tab, proxy
+    //     timeout), which left the event released and uploads locked with ZERO export_job rows and
+    //     no workers: downloads 404 forever and the host cannot retry, because release_gallery
+    //     rejects an already-released event ("bereits freigegeben"). Only a restart escaped it.
+    //     Now nothing is committed until every row is written, and the workers are spawned AFTER
+    //     the commit (a detached `tokio::spawn` survives cancellation).
+    //  2. Atomicity vs. a concurrent reopen. Bumping the epoch in the same statement that sets
+    //     `export_released_at` means no worker and no reader can ever observe "released again but
+    //     the generation hasn't moved on yet" — the window every previous fix kept leaving open.
+    //
+    // Release also locks uploads in the same statement (release ⇒ lock), so the export snapshot is
+    // taken against a frozen upload set. `COALESCE` preserves an earlier explicit lock time.
+    let mut tx = state.pool.begin().await?;
 
-    if event.export_released_at.is_some() {
-        return Err(AppError::BadRequest("Galerie wurde bereits freigegeben.".into()));
-    }
+    let claimed: Option<(Uuid, String, i64)> = sqlx::query_as(
+        "UPDATE event
+         SET export_released_at = NOW(),
+             uploads_locked_at  = COALESCE(uploads_locked_at, NOW()),
+             export_epoch       = export_epoch + 1
+         WHERE slug = $1 AND export_released_at IS NULL
+         RETURNING id, name, export_epoch",
+    )
+    .bind(&state.config.event_slug)
+    .fetch_optional(&mut *tx)
+    .await?;
 
-    sqlx::query("UPDATE event SET export_released_at = NOW() WHERE slug = $1")
-        .bind(&state.config.event_slug)
-        .execute(&state.pool)
-        .await?;
+    let Some((event_id, event_name, epoch)) = claimed else {
+        // Distinguish "no such event" from "already released" for a clean error.
+        let exists = Event::find_by_slug(&state.pool, &state.config.event_slug)
+            .await?
+            .is_some();
+        return Err(if exists {
+            AppError::BadRequest("Galerie wurde bereits freigegeben.".into())
+        } else {
+            AppError::NotFound("Event nicht gefunden.".into())
+        });
+    };
 
-    // Enqueue export jobs
-    for export_type in ["zip", "html"] {
-        sqlx::query(
-            "INSERT INTO export_job (event_id, type) VALUES ($1, $2::export_type)
-             ON CONFLICT (event_id, type) DO NOTHING",
-        )
-        .bind(event.id)
-        .bind(export_type)
-        .execute(&state.pool)
-        .await?;
-    }
+    // Arm both types at THIS epoch. No "skip the type that's already ready" check any more: the
+    // epoch bump above retired every prior generation, so there is nothing to preserve and nothing
+    // to be fooled by. (That skip was how a stale ready flag used to suppress regeneration.)
+    crate::services::export::enqueue_jobs_at_epoch(&mut tx, event_id, epoch).await?;
 
-    // Spawn export workers
+    tx.commit().await?;
+
+    // Release locks uploads too — tell any open composer to flip to the locked UI live rather than
+    // discovering it via a rejected upload.
+    let _ = state.sse_tx.send(SseEvent::new("event-closed", "{}"));
+
+    // Detached — survives this handler being cancelled.
     crate::services::export::spawn_export_jobs(
-        event.id,
-        event.name,
+        event_id,
+        event_name,
+        epoch,
+        state.config.comments_enabled,
+        std::time::Duration::ZERO,
         state.pool.clone(),
         state.config.media_path.clone(),
+        state.config.export_path.clone(),
         state.sse_tx.clone(),
     );
 

backend/src/handlers/me.rs

@@ -7,14 +7,14 @@
 //!   account page loads this once on mount instead of issuing several round trips.
 //! - `GET /api/v1/me/quota`  — live per-user storage quota estimate.
 
-use axum::extract::State;
 use axum::Json;
+use axum::extract::State;
 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
+        },
     }))
 }
 
@@ -55,6 +69,12 @@ pub struct MeContextDto {
     pub privacy_note: String,
     pub quota_enabled: bool,
     pub storage_quota_enabled: bool,
+    /// Uploads are locked (event closed) — the composer should show a locked state live
+    /// instead of letting a guest compose an upload only to eat a 403.
+    pub uploads_locked: bool,
+    /// The gallery has been released and the export snapshotted — uploads are permanently
+    /// closed for this run (release ⇒ lock, and reopening regenerates).
+    pub gallery_released: bool,
 }
 
 pub async fn get_context(
@@ -65,9 +85,21 @@ pub async fn get_context(
         .await?
         .ok_or_else(|| AppError::NotFound("Benutzer nicht gefunden.".into()))?;
 
-    let privacy_note = config::get_str(&state.pool, "privacy_note", "").await;
-    let quota_enabled = config::get_bool(&state.pool, "quota_enabled", true).await;
-    let storage_quota_enabled = config::get_bool(&state.pool, "storage_quota_enabled", true).await;
+    let privacy_note = config::get_str(&state.config_cache, "privacy_note", "").await;
+    let quota_enabled = config::get_bool(&state.config_cache, "quota_enabled", true).await;
+    let storage_quota_enabled =
+        config::get_bool(&state.config_cache, "storage_quota_enabled", true).await;
+
+    let event =
+        crate::models::event::Event::find_by_slug(&state.pool, &state.config.event_slug).await?;
+    let uploads_locked = event
+        .as_ref()
+        .map(|e| e.uploads_locked_at.is_some())
+        .unwrap_or(false);
+    let gallery_released = event
+        .as_ref()
+        .map(|e| e.export_released_at.is_some())
+        .unwrap_or(false);
 
     Ok(Json(MeContextDto {
         user_id: user.id,
@@ -76,5 +108,7 @@ pub async fn get_context(
         privacy_note,
         quota_enabled,
         storage_quota_enabled,
+        uploads_locked,
+        gallery_released,
     }))
 }

backend/src/handlers/mod.rs

@@ -2,6 +2,7 @@ pub mod admin;
 pub mod feed;
 pub mod host;
 pub mod me;
+pub mod public;
 pub mod social;
 pub mod sse;
 pub mod test_admin;

backend/src/handlers/public.rs

@@ -0,0 +1,44 @@
+//! Unauthenticated, read-only endpoints safe to expose before a user has joined.
+
+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 + 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

@@ -1,8 +1,8 @@
+use axum::Json;
 use axum::extract::{Path, Query, State};
 use axum::http::StatusCode;
-use axum::Json;
 use chrono::{DateTime, Utc};
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 use uuid::Uuid;
 
 use crate::auth::middleware::AuthUser;
@@ -12,11 +12,22 @@ use crate::models::hashtag::{self, Hashtag};
 use crate::models::upload::Upload;
 use crate::state::AppState;
 
+#[derive(Serialize)]
+pub struct LikeResponse {
+    /// The caller's like state *after* this toggle. The client sets `liked_by_me` from
+    /// this rather than blind-inverting local state — otherwise a second device (same
+    /// recovered user) drifts, since the `like-update` broadcast only carries `like_count`.
+    pub liked: bool,
+    /// Fresh like count, or `null` if the (best-effort) count query hiccuped. The client
+    /// keeps its current count when this is null rather than adopting a wrong number.
+    pub like_count: Option<i64>,
+}
+
 pub async fn toggle_like(
     State(state): State<AppState>,
     auth: AuthUser,
     Path(upload_id): Path<Uuid>,
-) -> Result<StatusCode, AppError> {
+) -> Result<Json<LikeResponse>, AppError> {
     // Check if user is banned
     let user = crate::models::user::User::find_by_id(&state.pool, auth.user_id)
         .await?
@@ -31,7 +42,11 @@ pub async fn toggle_like(
         .await?
         .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
 
-    // Try to insert; if conflict, delete (toggle)
+    // NOTE: liking is intentionally allowed while the event is locked. Locking
+    // ("Event schließen") freezes *new uploads* only — likes, comments and
+    // browsing stay open (USER_JOURNEYS §9.3, FEATURES capability matrix).
+
+    // Try to insert; if conflict, delete (toggle). `liked` = the caller's state afterwards.
     let result = sqlx::query(
         "INSERT INTO \"like\" (upload_id, user_id) VALUES ($1, $2)
          ON CONFLICT (upload_id, user_id) DO NOTHING",
@@ -41,7 +56,8 @@ pub async fn toggle_like(
     .execute(&state.pool)
     .await?;
 
-    if result.rows_affected() == 0 {
+    let liked = result.rows_affected() > 0;
+    if !liked {
         // Already liked — remove
         sqlx::query("DELETE FROM \"like\" WHERE upload_id = $1 AND user_id = $2")
             .bind(upload_id)
@@ -51,24 +67,29 @@ pub async fn toggle_like(
     }
 
     // Fresh count so feed clients can patch the single card in place instead of
-    // refetching page 1 (mirrors v_feed.like_count = COUNT(DISTINCT user_id)). The
-    // count + broadcast are a UI optimisation — the like itself is already committed,
-    // so a failure here must not fail the request. Swallow the error and skip the
-    // broadcast; the next event or a pull-to-refresh reconciles the count.
-    if let Ok(like_count) = sqlx::query_scalar::<_, i64>(
+    // refetching page 1 (mirrors v_feed.like_count = COUNT(DISTINCT user_id)). The like
+    // itself is already committed, so a failed count must not fail the request — but we
+    // also must NOT broadcast/return a bogus 0 (that would push like_count: 0 to every
+    // client until the next event). On error we skip the broadcast and return null.
+    let like_count = sqlx::query_scalar::<_, i64>(
         "SELECT COUNT(DISTINCT user_id) FROM \"like\" WHERE upload_id = $1",
     )
     .bind(upload_id)
     .fetch_one(&state.pool)
     .await
-    {
+    .ok();
+
+    if let Some(count) = like_count {
+        // Broadcast the new count so other clients patch their card. Only `like_count` is
+        // shared — each client's own `liked_by_me` only changes via its own toggle (which
+        // now reads it straight from this response).
         let _ = state.sse_tx.send(crate::state::SseEvent {
             event_type: "like-update".to_string(),
-            data: serde_json::json!({ "upload_id": upload_id, "like_count": like_count }).to_string(),
+            data: serde_json::json!({ "upload_id": upload_id, "like_count": count }).to_string(),
         });
     }
 
-    Ok(StatusCode::NO_CONTENT)
+    Ok(Json(LikeResponse { liked, like_count }))
 }
 
 #[derive(Deserialize, Default)]
@@ -108,6 +129,12 @@ 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()))?;
@@ -120,6 +147,10 @@ pub async fn add_comment(
         .await?
         .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
 
+    // NOTE: commenting is intentionally allowed while the event is locked. Locking
+    // freezes *new uploads* only — likes, comments and browsing stay open
+    // (USER_JOURNEYS §9.3, FEATURES capability matrix).
+
     let text = body.body.trim();
     let text_chars = text.chars().count();
     if text_chars == 0 || text_chars > 500 {
@@ -128,20 +159,22 @@ pub async fn add_comment(
         ));
     }
 
-    let comment = Comment::create(&state.pool, upload_id, auth.user_id, text).await?;
-
-    // Process hashtags in comment body
+    // Insert the comment and link its hashtags atomically, so a crash mid-loop
+    // can't leave a committed comment with only some of its tags indexed.
     let tags = hashtag::extract_hashtags(text);
+    let mut tx = state.pool.begin().await?;
+    let comment = Comment::create(&mut *tx, upload_id, auth.user_id, text).await?;
     for tag in &tags {
-        let h = Hashtag::upsert(&state.pool, auth.event_id, tag).await?;
+        let h = Hashtag::upsert(&mut *tx, auth.event_id, tag).await?;
         sqlx::query(
             "INSERT INTO comment_hashtag (comment_id, hashtag_id) VALUES ($1, $2) ON CONFLICT DO NOTHING",
         )
         .bind(comment.id)
         .bind(h.id)
-        .execute(&state.pool)
+        .execute(&mut *tx)
         .await?;
     }
+    tx.commit().await?;
 
     // Fresh count so feed clients can patch the single card in place instead of
     // refetching page 1 (mirrors v_feed.comment_count = COUNT(DISTINCT c.id); COUNT(*)
@@ -179,6 +212,10 @@ pub async fn delete_comment(
     auth: AuthUser,
     Path(comment_id): Path<Uuid>,
 ) -> Result<StatusCode, AppError> {
+    // Banned users keep read access but cannot mutate (USER_JOURNEYS §10).
+    if auth.is_banned {
+        return Err(AppError::Forbidden("Du bist gesperrt.".into()));
+    }
     let comment = Comment::find_by_id(&state.pool, comment_id)
         .await?
         .ok_or_else(|| AppError::NotFound("Kommentar nicht gefunden.".into()))?;
@@ -189,9 +226,25 @@ pub async fn delete_comment(
 
     // Event-scope: soft_delete_in_event only matches comments whose upload is in
     // the caller's event, so a cross-event comment_id resolves to a 404 here.
-    let deleted = Comment::soft_delete_in_event(&state.pool, comment_id, auth.event_id).await?;
+    let mut tx = state.pool.begin().await?;
+    let deleted = Comment::soft_delete_in_event(&mut tx, comment_id, auth.event_id).await?;
     if !deleted {
         return Err(AppError::NotFound("Kommentar nicht gefunden.".into()));
     }
+    // Comments live only in the HTML viewer, so the ZIP is carried forward, not rebuilt.
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        crate::services::export::Affects::ViewerOnly,
+    )
+    .await?;
+    tx.commit().await?;
+    if let Some(r) = regen {
+        crate::handlers::host::start_regen(&state, r);
+    }
+    let _ = state.sse_tx.send(crate::state::SseEvent::new(
+        "comment-deleted",
+        serde_json::json!({ "comment_id": comment_id, "upload_id": comment.upload_id }).to_string(),
+    ));
     Ok(StatusCode::NO_CONTENT)
 }

backend/src/handlers/sse.rs

@@ -1,13 +1,14 @@
 use std::convert::Infallible;
 use std::time::Duration;
 
+use axum::Json;
 use axum::extract::{Query, State};
 use axum::response::sse::{Event, KeepAlive, Sse};
-use axum::Json;
 use futures::stream::Stream;
 use serde::{Deserialize, Serialize};
-use tokio_stream::wrappers::BroadcastStream;
 use tokio_stream::StreamExt;
+use tokio_stream::wrappers::BroadcastStream;
+use tokio_stream::wrappers::errors::BroadcastStreamRecvError;
 
 use crate::auth::middleware::AuthUser;
 use crate::error::AppError;
@@ -22,6 +23,10 @@ pub struct SseQuery {
 #[derive(Serialize)]
 pub struct StreamTicketResponse {
     pub ticket: String,
+    /// Server clock at mint time — the client seeds its SSE reconnect cursor from this
+    /// instead of `new Date()`, so a skewed browser clock can't drop uploads. See
+    /// `DeltaResponse::server_time`.
+    pub server_time: chrono::DateTime<chrono::Utc>,
 }
 
 /// Mint a short-lived single-use SSE ticket. The browser's `EventSource` cannot
@@ -32,9 +37,15 @@ pub struct StreamTicketResponse {
 pub async fn issue_ticket(
     State(state): State<AppState>,
     auth: AuthUser,
-) -> Json<StreamTicketResponse> {
+) -> Result<Json<StreamTicketResponse>, AppError> {
     let ticket = state.sse_tickets.issue(auth.token_hash);
-    Json(StreamTicketResponse { ticket })
+    let server_time = sqlx::query_scalar("SELECT NOW()")
+        .fetch_one(&state.pool)
+        .await?;
+    Ok(Json(StreamTicketResponse {
+        ticket,
+        server_time,
+    }))
 }
 
 /// SSE stream endpoint. Authenticates via a single-use ticket (see
@@ -48,19 +59,57 @@ pub async fn stream(
         .consume(&q.ticket)
         .ok_or_else(|| AppError::Unauthorized("Ticket ungültig oder abgelaufen.".into()))?;
 
+    // NOTE: this authenticates via ticket→session, not the `AuthUser` extractor. The
+    // SSE stream is read-only, and under the read-only-ban model (USER_JOURNEYS §10)
+    // banned users retain read access — so both minting a ticket and holding a stream
+    // open are intentionally allowed for banned users; only writes are blocked.
     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()))?;
 
     let rx = state.sse_tx.subscribe();
-    let stream = BroadcastStream::new(rx).filter_map(|msg| match msg {
+    let events = BroadcastStream::new(rx).filter_map(|msg| match msg {
         Ok(sse_event) => Some(Ok(Event::default()
             .event(sse_event.event_type)
             .data(sse_event.data))),
-        Err(_) => None,
+        // A consumer that falls behind the broadcast buffer would otherwise silently
+        // lose events, leaving its feed permanently stale. Instead of dropping the
+        // gap, tell the client to resync — the frontend responds by running a full
+        // feed-delta fetch (which reconciles both new uploads and deletions).
+        Err(BroadcastStreamRecvError::Lagged(n)) => {
+            tracing::warn!("SSE consumer lagged, dropped {n} event(s); emitting resync");
+            Some(Ok(Event::default().event("resync").data(n.to_string())))
+        }
     });
 
+    // The session is only checked once at open. Re-validate it periodically so a
+    // logged-out, expired, OR banned session's stream is closed rather than kept alive
+    // until the client happens to disconnect. Bounds a stale stream to ~60s. NOTE: a ban is
+    // deliberately read-only and does NOT revoke sessions (see `ban_user`), so the
+    // `is_banned` re-read below is LOAD-BEARING — it is the only thing that stops a banned
+    // user's live push stream. Do not remove it. Only a *definitive* gone/expired/banned
+    // state ends the stream; a transient DB error just retries next tick.
+    let pool = state.pool.clone();
+    let session_hash = token_hash.clone();
+    let session_gone = async move {
+        let mut ticker = tokio::time::interval(Duration::from_secs(60));
+        ticker.tick().await; // consume the immediate first tick
+        loop {
+            ticker.tick().await;
+            match Session::find_user_by_token_hash(&pool, &session_hash).await {
+                Ok(Some(user)) if !user.is_banned => {} // still valid — keep streaming
+                Ok(Some(_)) => break,                   // banned — cut the stream
+                Ok(None) => break,                      // logged out or expired — stop
+                Err(e) => {
+                    tracing::warn!(error = ?e, "SSE session revalidation query failed; retrying");
+                }
+            }
+        }
+    };
+
+    let stream = futures::StreamExt::take_until(events, Box::pin(session_gone));
+
     Ok(Sse::new(stream).keep_alive(
         KeepAlive::new()
             .interval(Duration::from_secs(30))

backend/src/handlers/test_admin.rs

@@ -40,13 +40,13 @@ pub async fn truncate_all(
     .execute(&state.pool)
     .await?;
 
-    // Reseed config — mirrors migrations 005 and 009. Kept in sync by hand
+    // Reseed config — mirrors migrations 005, 009 and 015. Kept in sync by hand
     // because pulling SQL out of the migration files at runtime is fragile.
     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'),
             ('quota_tolerance',            '0.75'),
@@ -70,10 +70,41 @@ pub async fn truncate_all(
     let _ = tokio::fs::remove_dir_all(&state.config.media_path).await;
     let _ = tokio::fs::create_dir_all(&state.config.media_path).await;
 
+    // Wipe the export directory too. Exports moved OUT of media_path (CR2 fix), so
+    // the media wipe above no longer covers them — without this a real export in
+    // one test would leave Gallery.zip on disk and contaminate the next.
+    let _ = tokio::fs::remove_dir_all(&state.config.export_path).await;
+    let _ = tokio::fs::create_dir_all(&state.config.export_path).await;
+
     // The rate limiter holds an in-memory HashMap; clear it so a previous test's
     // counters don't leak into the next one.
     state.rate_limiter.clear();
 
+    // The reseed above wrote the `config` table directly (bypassing patch_config), so
+    // the cache must be invalidated too — otherwise the first request after a truncate
+    // could serve the previous test's toggles.
+    state.config_cache.invalidate();
+
+    // The other two in-memory singletons that TRUNCATE used to leave standing.
+    //
+    // `disk_cache` holds a free-space reading for up to its TTL. TRUNCATE has just deleted every
+    // uploaded file, which materially changes free space — so without this the next test can
+    // compute a storage quota from the PREVIOUS test's disk. That was harmless only while quotas
+    // were globally disabled in e2e (they no longer are: see specs/02-upload/quota.spec.ts, which
+    // steers the per-user limit off `free_disk_bytes`), i.e. two holes were masking each other.
+    state.disk_cache.invalidate();
+
+    // `sse_tickets` maps a ticket to a session token hash. TRUNCATE deletes the sessions, so every
+    // surviving ticket is a dangling reference to a user that no longer exists.
+    state.sse_tickets.clear();
+
+    // Invalidate any in-flight/queued compression task spawned by the previous test. Without this a
+    // task still waiting on the concurrency semaphore wakes AFTER this wipe, fails to find its
+    // (now-deleted) file, and broadcasts upload-error/upload-deleted into the NEXT test's SSE
+    // stream. (Export workers are already inert across a truncate: they are epoch-guarded on the
+    // event row, and truncate gives the event a fresh random UUID, so their writes match nothing.)
+    state.compression.bump_generation();
+
     Ok(StatusCode::NO_CONTENT)
 }
 

backend/src/handlers/upload.rs

@@ -1,8 +1,9 @@
 use std::time::Duration;
 
+use axum::Json;
 use axum::extract::{Multipart, Path, State};
 use axum::http::StatusCode;
-use axum::Json;
+use chrono::{DateTime, Utc};
 use serde::Deserialize;
 use uuid::Uuid;
 
@@ -43,10 +44,11 @@ pub async fn upload(
     mut multipart: Multipart,
 ) -> Result<(StatusCode, Json<UploadDto>), AppError> {
     // Rate limit: N uploads per hour per user. Gated by master + per-endpoint toggles.
-    let rate_limits_on = config::get_bool(&state.pool, "rate_limits_enabled", true).await;
-    let upload_rate_on = config::get_bool(&state.pool, "upload_rate_enabled", true).await;
+    let rate_limits_on = config::get_bool(&state.config_cache, "rate_limits_enabled", true).await;
+    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.pool, "upload_rate_per_hour", 10).await as usize;
+        let upload_rate =
+            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,
@@ -75,59 +77,117 @@ pub async fn upload(
         .ok_or_else(|| AppError::NotFound("Event nicht gefunden.".into()))?;
     if event.uploads_locked_at.is_some() {
         drain_multipart(multipart).await;
-        return Err(AppError::Forbidden("Uploads sind gesperrt.".into()));
+        // Reversible: a host can reopen the event, so the client keeps the queued blob and
+        // retries on `event-opened` rather than purging it (UploadsLocked, not Forbidden).
+        return Err(AppError::UploadsLocked("Uploads sind gesperrt.".into()));
+    }
+    // Belt-and-suspenders on top of the lock (release ⇒ lock): once the gallery is
+    // released the export has been snapshotted, so a late upload could never make it into
+    // the keepsake. Reject it explicitly rather than silently diverging the live feed.
+    // Also reversible (reopen clears `export_released_at`), so likewise UploadsLocked.
+    if event.export_released_at.is_some() {
+        drain_multipart(multipart).await;
+        return Err(AppError::UploadsLocked(
+            "Galerie wurde bereits freigegeben.".into(),
+        ));
     }
 
     // Read config limits from DB
-    let max_image_mb: i64 = config::get_i64(&state.pool, "max_image_size_mb", 20).await;
-    let max_video_mb: i64 = config::get_i64(&state.pool, "max_video_size_mb", 500).await;
+    let max_image_mb: i64 = config::get_i64(&state.config_cache, "max_image_size_mb", 20).await;
+    let max_video_mb: i64 = config::get_i64(&state.config_cache, "max_video_size_mb", 500).await;
 
-    let mut file_data: Option<Vec<u8>> = None;
+    // The uploaded file is streamed straight to a temp file on disk (never buffered
+    // whole in memory — a 500 MB video used to cost 500 MB of RAM per concurrent
+    // upload). We only keep the first ≤512 bytes in memory for magic-byte sniffing.
+    // On success the temp file is renamed into place under its detected extension.
+    let upload_id = Uuid::new_v4();
+    let event_slug = &state.config.event_slug;
+    let originals_dir = state
+        .config
+        .media_path
+        .join(format!("originals/{event_slug}"));
+    let temp_abs = originals_dir.join(format!("{upload_id}.tmp"));
+
+    let mut streamed: Option<(i64, Vec<u8>)> = None; // (size, head bytes for sniffing)
     let mut caption: Option<String> = None;
     let mut hashtags_csv: Option<String> = None;
 
-    while let Some(field) = multipart.next_field().await.map_err(|e| AppError::BadRequest(e.to_string()))? {
-        let name = field.name().unwrap_or_default().to_string();
-        match name.as_str() {
-            "file" => {
-                // Note: the client-declared filename and Content-Type are intentionally
-                // ignored — the stored MIME and extension are derived from the file's
-                // magic bytes below, so a mislabelled payload can't influence them.
-                file_data = Some(
-                    field.bytes().await
-                        .map_err(|e| AppError::BadRequest(format!("Datei konnte nicht gelesen werden: {e}")))?
-                        .to_vec(),
-                );
+    // Wrap the multipart read so any error after the temp file is created still cleans
+    // it up (a mid-stream parse failure must not leave a stray `.tmp` on disk).
+    let parse_result: Result<(), AppError> = async {
+        while let Some(field) = multipart
+            .next_field()
+            .await
+            .map_err(|e| AppError::BadRequest(e.to_string()))?
+        {
+            let name = field.name().unwrap_or_default().to_string();
+            match name.as_str() {
+                "file" => {
+                    // The client-declared Content-Type does NOT determine the stored
+                    // MIME/extension — those come from the file's magic bytes below. The
+                    // declared type only picks the streaming cap so an oversized body is
+                    // aborted early; a mislabelled type only makes the cap *stricter*
+                    // (safe), and the authoritative per-class check still runs on the
+                    // detected type.
+                    let declared = field.content_type().unwrap_or("").to_string();
+                    let cap_bytes = if declared.starts_with("video/") {
+                        (max_video_mb * 1024 * 1024) as usize
+                    } else if declared.starts_with("image/") {
+                        (max_image_mb * 1024 * 1024) as usize
+                    } else {
+                        (max_image_mb.max(max_video_mb) * 1024 * 1024) as usize
+                    };
+                    tokio::fs::create_dir_all(&originals_dir)
+                        .await
+                        .map_err(|e| AppError::Internal(e.into()))?;
+                    streamed = Some(stream_field_to_file(field, &temp_abs, cap_bytes).await?);
+                }
+                "caption" => {
+                    caption = Some(
+                        field
+                            .text()
+                            .await
+                            .map_err(|e| AppError::BadRequest(e.to_string()))?,
+                    );
+                }
+                "hashtags" => {
+                    hashtags_csv = Some(
+                        field
+                            .text()
+                            .await
+                            .map_err(|e| AppError::BadRequest(e.to_string()))?,
+                    );
+                }
+                _ => {}
             }
-            "caption" => {
-                caption = Some(
-                    field.text().await
-                        .map_err(|e| AppError::BadRequest(e.to_string()))?,
-                );
-            }
-            "hashtags" => {
-                hashtags_csv = Some(
-                    field.text().await
-                        .map_err(|e| AppError::BadRequest(e.to_string()))?,
-                );
-            }
-            _ => {}
         }
+        Ok(())
+    }
+    .await;
+
+    if let Err(e) = parse_result {
+        let _ = tokio::fs::remove_file(&temp_abs).await;
+        return Err(e);
     }
 
-    let data = file_data.ok_or_else(|| AppError::BadRequest("Keine Datei hochgeladen.".into()))?;
-    let size = data.len() as i64;
+    // From here on the temp file may exist; every validation failure removes it before
+    // returning so a rejected upload never leaves bytes behind.
+    let (size, head) = match streamed {
+        Some(s) => s,
+        None => return Err(AppError::BadRequest("Keine Datei hochgeladen.".into())),
+    };
 
     // Validate caption length. Counted in chars (code points) to match the
     // "Zeichen" wording in the error message — `.len()` would be bytes and
     // reject perfectly valid German/emoji captions early.
-    if let Some(ref cap) = caption {
-        if cap.chars().count() > MAX_CAPTION_LENGTH {
-            return Err(AppError::BadRequest(format!(
-                "Beschreibung ist zu lang. Maximum: {} Zeichen.",
-                MAX_CAPTION_LENGTH
-            )));
-        }
+    if let Some(ref cap) = caption
+        && cap.chars().count() > MAX_CAPTION_LENGTH
+    {
+        let _ = tokio::fs::remove_file(&temp_abs).await;
+        return Err(AppError::BadRequest(format!(
+            "Beschreibung ist zu lang. Maximum: {} Zeichen.",
+            MAX_CAPTION_LENGTH
+        )));
     }
 
     // Determine the file type from its magic bytes and require it to be on the
@@ -135,26 +195,38 @@ pub async fn upload(
     // those are rejected outright — closing the stored-XSS vector. Both the MIME
     // we persist and the on-disk extension come from the detected type, never from
     // client-supplied values.
-    let kind = infer::get(&data)
-        .ok_or_else(|| AppError::BadRequest("Dateityp nicht erkannt oder nicht unterstützt.".into()))?;
-    let (mime, ext) = ALLOWED_MEDIA
+    let kind = match infer::get(&head) {
+        Some(k) => k,
+        None => {
+            let _ = tokio::fs::remove_file(&temp_abs).await;
+            return Err(AppError::BadRequest(
+                "Dateityp nicht erkannt oder nicht unterstützt.".into(),
+            ));
+        }
+    };
+    let (mime, ext) = match ALLOWED_MEDIA
         .iter()
         .find(|(allowed, _)| *allowed == kind.mime_type())
         .map(|(m, e)| ((*m).to_string(), *e))
-        .ok_or_else(|| {
-            AppError::BadRequest(format!(
+    {
+        Some(v) => v,
+        None => {
+            let _ = tokio::fs::remove_file(&temp_abs).await;
+            return Err(AppError::BadRequest(format!(
                 "Dateityp wird nicht unterstützt: {}.",
                 kind.mime_type()
-            ))
-        })?;
+            )));
+        }
+    };
 
-    // Validate file size
+    // Validate file size against the authoritative per-detected-class limit.
     let max_bytes = if mime.starts_with("video/") {
         max_video_mb * 1024 * 1024
     } else {
         max_image_mb * 1024 * 1024
     };
     if size > max_bytes {
+        let _ = tokio::fs::remove_file(&temp_abs).await;
         return Err(AppError::BadRequest(format!(
             "Datei ist zu groß. Maximum: {} MB.",
             max_bytes / (1024 * 1024)
@@ -164,50 +236,36 @@ pub async fn upload(
     // 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.
-    let quota_on = config::get_bool(&state.pool, "quota_enabled", true).await;
-    let storage_quota_on = config::get_bool(&state.pool, "storage_quota_enabled", true).await;
+    let quota_on = config::get_bool(&state.config_cache, "quota_enabled", true).await;
+    let storage_quota_on =
+        config::get_bool(&state.config_cache, "storage_quota_enabled", true).await;
+    // When quota is enforced, this holds the byte ceiling so the increment UPDATE below can
+    // enforce it atomically (`WHERE total + size <= limit`). Without that guard, two
+    // concurrent uploads from the same user (e.g. phone + laptop) both pass this stale
+    // pre-check and both increment, blowing past the quota. The pre-check stays as a
+    // fast path that avoids the disk write when the user is already clearly over.
+    let mut quota_limit: Option<i64> = None;
     if quota_on && storage_quota_on {
         let estimate = compute_storage_quota(&state).await;
         if let Some(limit) = estimate.limit_bytes {
+            quota_limit = Some(limit);
             let prospective_total = user.total_upload_bytes.saturating_add(size);
             if prospective_total > limit {
-                return Err(AppError::TooManyRequests(
+                let _ = tokio::fs::remove_file(&temp_abs).await;
+                return Err(AppError::QuotaExceeded(
                     "Du hast dein Upload-Limit für dieses Event erreicht.".into(),
-                    None,
                 ));
             }
         }
     }
 
-    let upload_id = Uuid::new_v4();
-    let event_slug = &state.config.event_slug;
+    // All checks passed — atomically move the temp file to its final, extension-correct
+    // path (same directory, so the rename is cheap and atomic).
     let relative_path = format!("originals/{event_slug}/{upload_id}.{ext}");
     let absolute_path = state.config.media_path.join(&relative_path);
-
-    // Ensure directory exists and write file
-    if let Some(parent) = absolute_path.parent() {
-        tokio::fs::create_dir_all(parent).await.map_err(|e| AppError::Internal(e.into()))?;
-    }
-    tokio::fs::write(&absolute_path, &data).await.map_err(|e| AppError::Internal(e.into()))?;
-
-    // Update user's total upload bytes
-    sqlx::query("UPDATE \"user\" SET total_upload_bytes = total_upload_bytes + $2 WHERE id = $1")
-        .bind(auth.user_id)
-        .bind(size)
-        .execute(&state.pool)
-        .await?;
-
-    // Insert upload record
-    let upload = Upload::create(
-        &state.pool,
-        auth.event_id,
-        auth.user_id,
-        &relative_path,
-        &mime,
-        size,
-        caption.as_deref(),
-    )
-    .await?;
+    tokio::fs::rename(&temp_abs, &absolute_path)
+        .await
+        .map_err(|e| AppError::Internal(e.into()))?;
 
     // Process hashtags from caption and explicit CSV
     let mut tags: Vec<String> = Vec::new();
@@ -225,10 +283,98 @@ pub async fn upload(
     tags.sort();
     tags.dedup();
 
-    for tag in &tags {
-        let h = Hashtag::upsert(&state.pool, auth.event_id, tag).await?;
-        Hashtag::link_to_upload(&state.pool, upload.id, h.id).await?;
+    // Quota accounting, the upload row, and its hashtag links must be atomic: a
+    // crash between the bytes increment and the insert would permanently charge
+    // bytes with no row to reclaim them (silent quota erosion / spurious lockout).
+    let tx_result: Result<Upload, AppError> = async {
+        let mut tx = state.pool.begin().await?;
+
+        // RE-CHECK THE LOCK, UNDER A ROW LOCK, INSIDE THE COMMIT TX.
+        //
+        // The pre-flight check at the top of this handler ran BEFORE we streamed the body — which
+        // for a 500 MB video is minutes. Trusting it here is a TOCTOU that silently loses photos
+        // from the keepsake, and it is the real cause of the "stale keepsake" bug that survived
+        // three rounds of fixes inside the export state machine:
+        //
+        //   1. guest starts a big upload; the lock check passes (event open)
+        //   2. host releases the gallery → uploads lock, export workers snapshot the uploads table
+        //   3. this upload commits AFTER that snapshot → it shows up in the live feed but is
+        //      MISSING from the downloaded keepsake, permanently (nothing ever regenerates it)
+        //
+        // `FOR SHARE` conflicts with the `UPDATE event` in `release_gallery`, which serializes us
+        // against it. Either we take the lock first — and release (hence the export snapshot) is
+        // strictly ordered after our commit, so the snapshot CONTAINS this upload — or release
+        // commits first and we observe the lock here and reject. Either way the keepsake is
+        // complete. `UploadsLocked` (not Forbidden) is reversible: the client keeps the blob and
+        // resumes it when the host reopens.
+        let (locked_at, released_at): (Option<DateTime<Utc>>, Option<DateTime<Utc>>) =
+            sqlx::query_as(
+                "SELECT uploads_locked_at, export_released_at FROM event WHERE id = $1 FOR SHARE",
+            )
+            .bind(auth.event_id)
+            .fetch_one(&mut *tx)
+            .await?;
+        if locked_at.is_some() || released_at.is_some() {
+            return Err(AppError::UploadsLocked("Uploads sind gesperrt.".into()));
+        }
+
+        // Increment the user's byte total. When a quota is in force, guard it atomically
+        // (`total + size <= limit`) so two concurrent uploads can't both slip past the
+        // stale pre-check — the loser's UPDATE matches 0 rows and we abort with the same
+        // terminal quota error (the tx rolls back on drop; the on-disk file is cleaned by
+        // the error path below).
+        let inc = if let Some(limit) = quota_limit {
+            sqlx::query(
+                "UPDATE \"user\" SET total_upload_bytes = total_upload_bytes + $2
+                 WHERE id = $1 AND total_upload_bytes + $2 <= $3",
+            )
+            .bind(auth.user_id)
+            .bind(size)
+            .bind(limit)
+            .execute(&mut *tx)
+            .await?
+        } else {
+            sqlx::query(
+                "UPDATE \"user\" SET total_upload_bytes = total_upload_bytes + $2 WHERE id = $1",
+            )
+            .bind(auth.user_id)
+            .bind(size)
+            .execute(&mut *tx)
+            .await?
+        };
+        if inc.rows_affected() == 0 {
+            return Err(AppError::QuotaExceeded(
+                "Du hast dein Upload-Limit für dieses Event erreicht.".into(),
+            ));
+        }
+        let upload = Upload::create(
+            &mut *tx,
+            auth.event_id,
+            auth.user_id,
+            &relative_path,
+            &mime,
+            size,
+            caption.as_deref(),
+        )
+        .await?;
+        for tag in &tags {
+            let h = Hashtag::upsert(&mut *tx, auth.event_id, tag).await?;
+            Hashtag::link_to_upload(&mut *tx, upload.id, h.id).await?;
+        }
+        tx.commit().await?;
+        Ok(upload)
     }
+    .await;
+
+    // The file is already on disk at `absolute_path`. If the transaction failed, no DB
+    // row will ever reference it, so remove it now rather than orphan bytes on disk.
+    let upload = match tx_result {
+        Ok(u) => u,
+        Err(e) => {
+            let _ = tokio::fs::remove_file(&absolute_path).await;
+            return Err(e);
+        }
+    };
 
     // Spawn compression task
     state
@@ -271,6 +417,10 @@ pub async fn edit_upload(
     Path(upload_id): Path<Uuid>,
     Json(body): Json<EditUploadRequest>,
 ) -> Result<StatusCode, AppError> {
+    // Banned users keep read access but cannot mutate (USER_JOURNEYS §10).
+    if auth.is_banned {
+        return Err(AppError::Forbidden("Du bist gesperrt.".into()));
+    }
     let upload = Upload::find_by_id_and_event(&state.pool, upload_id, auth.event_id)
         .await?
         .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
@@ -279,17 +429,38 @@ pub async fn edit_upload(
         return Err(AppError::Forbidden("Nur eigene Uploads bearbeiten.".into()));
     }
 
+    // Caption update + hashtag wipe-then-relink in one transaction, so a crash
+    // mid-relink can't leave the upload with its hashtags stripped.
+    //
+    // Editing is intentionally allowed while uploads are locked or the gallery is released — like
+    // comments and likes, the lock freezes *new uploads* only (USER_JOURNEYS §9.3). But a caption
+    // is embedded in the HTML viewer keepsake (the ZIP holds media only — see export.rs), so an
+    // edit AFTER release must regenerate the viewer, or the downloadable keepsake keeps showing the
+    // old caption forever while the live feed shows the new one. Same atomicity as delete_upload:
+    // the edit and its invalidation share one tx so a dropped handler can't leave them disagreeing.
+    // `Affects::ViewerOnly` carries the finished ZIP forward (the media didn't change); when the
+    // gallery isn't released, `invalidate_and_arm` returns None and this is a no-op.
+    let mut tx = state.pool.begin().await?;
     if let Some(ref caption) = body.caption {
-        Upload::update_caption(&state.pool, upload_id, Some(caption)).await?;
+        Upload::update_caption(&mut *tx, upload_id, Some(caption)).await?;
     }
-
     if let Some(ref hashtags) = body.hashtags {
-        Hashtag::unlink_all_from_upload(&state.pool, upload_id).await?;
+        Hashtag::unlink_all_from_upload(&mut *tx, upload_id).await?;
         for tag in hashtags {
-            let h = Hashtag::upsert(&state.pool, auth.event_id, tag).await?;
-            Hashtag::link_to_upload(&state.pool, upload_id, h.id).await?;
+            let h = Hashtag::upsert(&mut *tx, auth.event_id, tag).await?;
+            Hashtag::link_to_upload(&mut *tx, upload_id, h.id).await?;
         }
     }
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        crate::services::export::Affects::ViewerOnly,
+    )
+    .await?;
+    tx.commit().await?;
+    if let Some(r) = regen {
+        crate::handlers::host::start_regen(&state, r);
+    }
 
     Ok(StatusCode::OK)
 }
@@ -299,6 +470,10 @@ pub async fn delete_upload(
     auth: AuthUser,
     Path(upload_id): Path<Uuid>,
 ) -> Result<StatusCode, AppError> {
+    // Banned users keep read access but cannot mutate (USER_JOURNEYS §10).
+    if auth.is_banned {
+        return Err(AppError::Forbidden("Du bist gesperrt.".into()));
+    }
     let upload = Upload::find_by_id_and_event(&state.pool, upload_id, auth.event_id)
         .await?
         .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
@@ -307,11 +482,96 @@ pub async fn delete_upload(
         return Err(AppError::Forbidden("Nur eigene Uploads löschen.".into()));
     }
 
-    Upload::soft_delete_in_event(&state.pool, upload_id, auth.event_id).await?;
+    // Atomic with the keepsake invalidation: a guest removing their own photo must have it removed
+    // from the downloadable archive too, and a half-applied delete would leave it there forever.
+    let mut tx = state.pool.begin().await?;
+    Upload::soft_delete_in_event(&mut tx, upload_id, auth.event_id).await?;
+    let regen = crate::services::export::invalidate_and_arm(
+        &mut tx,
+        &state.config.event_slug,
+        crate::services::export::Affects::Both,
+    )
+    .await?;
+    tx.commit().await?;
+    if let Some(r) = regen {
+        crate::handlers::host::start_regen(&state, r);
+    }
+
+    // Evict the card live on every other feed + the projector diashow — otherwise
+    // a self-deleted post lingers until each viewer manually reloads. Same event
+    // the host-delete path already emits and the frontend already handles.
+    let _ = state.sse_tx.send(crate::state::SseEvent::new(
+        "upload-deleted",
+        serde_json::json!({ "upload_id": upload_id }).to_string(),
+    ));
 
     Ok(StatusCode::NO_CONTENT)
 }
 
+/// Number of leading bytes retained in memory for magic-byte (`infer`) sniffing. Every
+/// allowed type's signature sits well within this; 512 is comfortably generous.
+const HEAD_SNIFF_BYTES: usize = 512;
+
+/// Stream a multipart field straight to `dest`, aborting with a 400 the moment it
+/// exceeds `max_bytes`. Only the first [`HEAD_SNIFF_BYTES`] bytes are kept in memory
+/// (for type detection); the rest goes chunk-by-chunk to disk, so peak memory is a
+/// single chunk rather than the whole file. Returns `(total_size, head_bytes)`. On any
+/// error the partial temp file is removed so no stray `.tmp` is left behind.
+async fn stream_field_to_file(
+    mut field: axum::extract::multipart::Field<'_>,
+    dest: &std::path::Path,
+    max_bytes: usize,
+) -> Result<(i64, Vec<u8>), AppError> {
+    use tokio::io::AsyncWriteExt;
+
+    let mut file = tokio::fs::File::create(dest)
+        .await
+        .map_err(|e| AppError::Internal(e.into()))?;
+    let mut total: usize = 0;
+    let mut head: Vec<u8> = Vec::with_capacity(HEAD_SNIFF_BYTES);
+
+    loop {
+        let chunk = match field.chunk().await {
+            Ok(Some(c)) => c,
+            Ok(None) => break,
+            Err(e) => {
+                let _ = file.shutdown().await;
+                let _ = tokio::fs::remove_file(dest).await;
+                return Err(AppError::BadRequest(format!(
+                    "Datei konnte nicht gelesen werden: {e}"
+                )));
+            }
+        };
+
+        total = total.saturating_add(chunk.len());
+        if total > max_bytes {
+            let _ = file.shutdown().await;
+            let _ = tokio::fs::remove_file(dest).await;
+            return Err(AppError::BadRequest(format!(
+                "Datei ist zu groß. Maximum: {} MB.",
+                max_bytes / (1024 * 1024)
+            )));
+        }
+
+        if head.len() < HEAD_SNIFF_BYTES {
+            let need = HEAD_SNIFF_BYTES - head.len();
+            head.extend_from_slice(&chunk[..need.min(chunk.len())]);
+        }
+
+        if let Err(e) = file.write_all(&chunk).await {
+            let _ = tokio::fs::remove_file(dest).await;
+            return Err(AppError::Internal(e.into()));
+        }
+    }
+
+    if let Err(e) = file.flush().await {
+        let _ = tokio::fs::remove_file(dest).await;
+        return Err(AppError::Internal(e.into()));
+    }
+
+    Ok((total as i64, head))
+}
+
 /// Drain a multipart body so the HTTP connection stays clean when returning an early error.
 /// Without draining, the client may still be sending the body after we've sent our response,
 /// which can corrupt the keep-alive connection for subsequent requests.
@@ -328,6 +588,9 @@ pub struct QuotaEstimate {
     pub limit_bytes: Option<i64>,
     pub active_uploaders: i64,
     pub free_disk_bytes: i64,
+    /// The tolerance factor the limit above was computed with. Carried on the snapshot so the
+    /// number is self-describing; no caller reads it back today.
+    #[allow(dead_code)]
     pub tolerance: f64,
 }
 
@@ -343,33 +606,35 @@ fn quota_limit_bytes(free_disk: i64, tolerance: f64, active_uploaders: i64) -> i
 /// None` whenever the storage quota is currently disabled — callers should skip the
 /// check (upload handler) or hide the UI (quota endpoint).
 pub async fn compute_storage_quota(state: &AppState) -> QuotaEstimate {
-    let quota_on = config::get_bool(&state.pool, "quota_enabled", true).await;
-    let storage_quota_on = config::get_bool(&state.pool, "storage_quota_enabled", true).await;
-    let tolerance = config::get_f64(&state.pool, "quota_tolerance", 0.75).await;
+    let quota_on = config::get_bool(&state.config_cache, "quota_enabled", true).await;
+    let storage_quota_on =
+        config::get_bool(&state.config_cache, "storage_quota_enabled", true).await;
+    let tolerance = config::get_f64(&state.config_cache, "quota_tolerance", 0.75).await;
 
-    let (active_count,): (i64,) = sqlx::query_as(
-        "SELECT COUNT(DISTINCT user_id) FROM upload WHERE deleted_at IS NULL",
-    )
-    .fetch_one(&state.pool)
-    .await
-    .unwrap_or((0,));
+    let (active_count,): (i64,) =
+        sqlx::query_as("SELECT COUNT(DISTINCT user_id) FROM upload WHERE deleted_at IS NULL")
+            .fetch_one(&state.pool)
+            .await
+            .unwrap_or((0,));
     let active = active_count.max(1);
 
-    let media_path = state.config.media_path.to_string_lossy().to_string();
-    let free_disk = sysinfo::Disks::new_with_refreshed_list()
-        .iter()
-        .find(|d| media_path.starts_with(d.mount_point().to_string_lossy().as_ref()))
-        .map(|d| d.available_space())
-        .unwrap_or_else(|| {
-            sysinfo::Disks::new_with_refreshed_list()
-                .iter()
-                .find(|d| d.mount_point().to_string_lossy() == "/")
-                .map(|d| d.available_space())
-                .unwrap_or(0)
-        }) as i64;
+    // Cached disk reading. `None` means we couldn't resolve the media filesystem.
+    let disk = state.disk_cache.snapshot(&state.config.media_path);
+    let free_disk = disk.map(|d| d.free as i64).unwrap_or(0);
 
     let limit_bytes = if quota_on && storage_quota_on {
-        Some(quota_limit_bytes(free_disk, tolerance, active))
+        match disk {
+            Some(d) => Some(quota_limit_bytes(d.free as i64, tolerance, active)),
+            // Fail OPEN, not closed: if the disk can't be read we don't know the real
+            // free space, and enforcing a 0-byte limit would reject every upload with a
+            // spurious "quota reached". Skip enforcement this round and warn instead.
+            None => {
+                tracing::warn!(
+                    "disk snapshot unavailable; skipping storage-quota enforcement this round"
+                );
+                None
+            }
+        }
     } else {
         None
     };
@@ -382,34 +647,26 @@ pub async fn compute_storage_quota(state: &AppState) -> QuotaEstimate {
     }
 }
 
-/// Streaming download of the original file behind an upload. Used by:
-///   - the per-post "Original anzeigen" context action (`window.open`)
-///   - `<img src>` / `<video src>` in the feed, lightbox, and diashow when the user is in
-///     Data Mode = Original
-///
-/// **Auth model:** the route is intentionally unauthenticated, matching how the rest of
-/// `/media/*` is served (preview + thumbnail variants). The URL contains the upload's
-/// UUID, which is unguessable — same security posture as `/media/originals/{slug}/{id}`.
-/// Adding `Authorization: Bearer` here would make the endpoint unusable from `<img src>`
-/// and `window.open`, defeating the purpose of having the alias.
-pub async fn get_original(
-    State(state): State<AppState>,
-    Path(upload_id): Path<Uuid>,
+/// 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
+/// content-type confusion, even if the edge proxy is bypassed) plus an explicit
+/// `Content-Disposition` and `Cache-Control`.
+async fn stream_media_file(
+    absolute: &std::path::Path,
+    content_type: String,
+    disposition: &str,
+    cache_control: &str,
 ) -> Result<axum::response::Response, AppError> {
-    let upload = Upload::find_by_id(&state.pool, upload_id)
-        .await?
-        .ok_or_else(|| AppError::NotFound("Upload nicht gefunden.".into()))?;
+    use axum::body::Body;
+    use axum::http::{Response, StatusCode, header};
+    use tokio_util::io::ReaderStream;
 
-    let absolute = state.config.media_path.join(&upload.original_path);
     if !absolute.exists() {
         return Err(AppError::NotFound("Datei nicht gefunden.".into()));
     }
 
-    use axum::body::Body;
-    use axum::http::{header, Response, StatusCode};
-    use tokio_util::io::ReaderStream;
-
-    let file = tokio::fs::File::open(&absolute)
+    let file = tokio::fs::File::open(absolute)
         .await
         .map_err(|e| AppError::Internal(e.into()))?;
     let metadata = file
@@ -418,19 +675,122 @@ pub async fn get_original(
         .map_err(|e| AppError::Internal(e.into()))?;
     let stream = ReaderStream::new(file);
 
+    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()))
+}
+
+/// Streaming download of the original file behind an upload. Used by:
+///   - the per-post "Original anzeigen" context action (`window.open`)
+///   - `<img src>` / `<video src>` in the feed, lightbox, and diashow when the user is in
+///     Data Mode = Original
+///
+/// **Auth model:** the route is intentionally unauthenticated so it works from
+/// `<img src>` / `window.open`. The URL contains the upload's unguessable UUID. Unlike
+/// raw `/media` files, this alias is the *only* way to fetch an original: direct
+/// `/media/originals/**` access is blocked in the router, and this handler filters out
+/// soft-deleted and ban-hidden uploads (via `find_visible_media`) so moderation actually
+/// removes access to content. Preview and thumbnail variants are gated the same way (see
+/// [`get_preview`] / [`get_thumbnail`]).
+pub async fn get_original(
+    State(state): State<AppState>,
+    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 absolute = state.config.media_path.join(&media.original_path);
     let filename = absolute
         .file_name()
         .and_then(|n| n.to_str())
         .unwrap_or("original");
     let disposition = format!("attachment; filename=\"{filename}\"");
 
-    Response::builder()
-        .status(StatusCode::OK)
-        .header(header::CONTENT_TYPE, upload.mime_type)
-        .header(header::CONTENT_DISPOSITION, disposition)
-        .header(header::CONTENT_LENGTH, metadata.len())
-        .body(Body::from_stream(stream))
-        .map_err(|e| AppError::Internal(e.into()))
+    // Full-res original: force download, never cache at the edge.
+    stream_media_file(&absolute, media.mime_type, &disposition, "no-store").await
+}
+
+/// Streaming access to an upload's compressed **preview** image. Gated exactly like
+/// [`get_original`]: `find_visible_media` drops soft-deleted / ban-hidden uploads, so a
+/// deleted or moderated post's preview 404s here even though the file may still be on
+/// disk. Direct `/media/previews/**` is blocked in the router, making this the only path
+/// to a preview.
+///
+/// Served inline (it's an `<img src>`) and privately cacheable for a short window. The
+/// window is intentionally short (5 min) so a moderated image stops being served to a
+/// direct-URL holder promptly; the live feed already evicts the card instantly via the
+/// `upload-deleted` / `user-hidden` SSE events, so this only bounds the raw-URL edge case.
+pub async fn get_preview(
+    State(state): State<AppState>,
+    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
+        .preview_path
+        .ok_or_else(|| AppError::NotFound("Vorschau nicht verfügbar.".into()))?;
+    let absolute = state.config.media_path.join(&rel);
+    stream_media_file(
+        &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>,
+    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(
+        &absolute,
+        "image/jpeg".to_string(),
+        "inline",
+        "private, max-age=300",
+    )
+    .await
+}
+
+/// Streaming access to an upload's **thumbnail** (video poster). Gated identically to
+/// [`get_preview`].
+pub async fn get_thumbnail(
+    State(state): State<AppState>,
+    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
+        .thumbnail_path
+        .ok_or_else(|| AppError::NotFound("Thumbnail nicht verfügbar.".into()))?;
+    let absolute = state.config.media_path.join(&rel);
+    stream_media_file(
+        &absolute,
+        "image/jpeg".to_string(),
+        "inline",
+        "private, max-age=300",
+    )
+    .await
 }
 
 #[cfg(test)]

backend/src/main.rs

@@ -1,7 +1,7 @@
 use anyhow::Result;
+use axum::Router;
 use axum::extract::DefaultBodyLimit;
 use axum::routing::{delete, get, patch, post};
-use axum::Router;
 use tower_http::services::ServeDir;
 use tower_http::trace::TraceLayer;
 use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};
@@ -27,9 +27,10 @@ async fn main() -> Result<()> {
     dotenvy::dotenv().ok();
 
     tracing_subscriber::registry()
-        .with(tracing_subscriber::EnvFilter::try_from_default_env().unwrap_or_else(|_| {
-            "eventsnap_backend=debug,tower_http=debug".into()
-        }))
+        .with(
+            tracing_subscriber::EnvFilter::try_from_default_env()
+                .unwrap_or_else(|_| "eventsnap_backend=debug,tower_http=debug".into()),
+        )
         .with(tracing_subscriber::fmt::layer())
         .init();
 
@@ -44,6 +45,24 @@ async fn main() -> Result<()> {
 
     let state = AppState::new(pool.clone(), config.clone());
 
+    // Backfill the big-screen display derivative for image uploads processed before it
+    // existed (v0.17.x). Fire-and-forget behind the compression semaphore; each upload
+    // falls back to its original in the diashow until its display is generated.
+    state.compression.backfill_missing_display().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
+    // background; the HTTP server can start accepting requests meanwhile.
+    services::export::recover_exports(
+        pool.clone(),
+        config.media_path.clone(),
+        config.export_path.clone(),
+        config.comments_enabled,
+        state.sse_tx.clone(),
+    )
+    .await;
+
     // Hourly background hygiene: prune expired sessions, evict cold rate-limiter
     // keys. Keeps the DB and process from growing unboundedly over multi-day events.
     services::maintenance::spawn_periodic_tasks(
@@ -57,17 +76,27 @@ async fn main() -> Result<()> {
 
     let api = Router::new()
         // Auth
+        .route("/api/v1/event", get(handlers::public::get_public_event))
         .route("/api/v1/join", post(auth::handlers::join))
         .route("/api/v1/recover", post(auth::handlers::recover))
+        // Forgotten-PIN escape hatch: ask a host to reset it (unauthenticated, throttled).
+        .route(
+            "/api/v1/recover/request",
+            post(auth::handlers::request_pin_reset),
+        )
         .route("/api/v1/admin/login", post(auth::handlers::admin_login))
         .route("/api/v1/session", delete(auth::handlers::logout))
+        // "Sign out everywhere" — revoke all of the caller's sessions.
+        .route("/api/v1/sessions", delete(auth::handlers::logout_all))
         // Upload — HTTP-level body cap as an OOM backstop. The handler still enforces
         // the precise per-class limits from DB config (max_image/video_size_mb); this
         // layer just stops a multi-GB body from being buffered into memory before that
         // check runs. Sized generously above the default 500 MB video limit + multipart
         // overhead — if an admin raises max_video_size_mb above this, bump MAX_UPLOAD_BYTES.
-        .route("/api/v1/upload", post(handlers::upload::upload)
-            .route_layer(DefaultBodyLimit::max(MAX_UPLOAD_BYTES)))
+        .route(
+            "/api/v1/upload",
+            post(handlers::upload::upload).route_layer(DefaultBodyLimit::max(MAX_UPLOAD_BYTES)),
+        )
         .route(
             "/api/v1/upload/{id}",
             patch(handlers::upload::edit_upload).delete(handlers::upload::delete_upload),
@@ -76,6 +105,21 @@ async fn main() -> Result<()> {
             "/api/v1/upload/{id}/original",
             get(handlers::upload::get_original),
         )
+        // Preview/thumbnail variants are gated the same way as originals (visibility
+        // check + direct /media block below) so moderation actually revokes access to
+        // the displayed images, not just the full-res download.
+        .route(
+            "/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),
+        )
         // Current-user endpoints (live quota estimate, profile + privacy note bundle)
         .route("/api/v1/me/context", get(handlers::me::get_context))
         .route("/api/v1/me/quota", get(handlers::me::get_quota))
@@ -84,33 +128,77 @@ async fn main() -> Result<()> {
         .route("/api/v1/feed/delta", get(handlers::feed::feed_delta))
         .route("/api/v1/hashtags", get(handlers::feed::hashtags))
         // Social
-        .route("/api/v1/upload/{id}/like", post(handlers::social::toggle_like))
+        .route(
+            "/api/v1/upload/{id}/like",
+            post(handlers::social::toggle_like),
+        )
         .route(
             "/api/v1/upload/{id}/comments",
             get(handlers::social::list_comments).post(handlers::social::add_comment),
         )
-        .route("/api/v1/comment/{id}", delete(handlers::social::delete_comment))
+        .route(
+            "/api/v1/comment/{id}",
+            delete(handlers::social::delete_comment),
+        )
         // SSE
         .route("/api/v1/stream", get(handlers::sse::stream))
         .route("/api/v1/stream/ticket", post(handlers::sse::issue_ticket))
         // Host Dashboard
         .route("/api/v1/host/event", get(handlers::host::get_event_status))
-        .route("/api/v1/host/event/close", post(handlers::host::close_event))
+        .route(
+            "/api/v1/host/event/close",
+            post(handlers::host::close_event),
+        )
         .route("/api/v1/host/event/open", post(handlers::host::open_event))
-        .route("/api/v1/host/gallery/release", post(handlers::host::release_gallery))
+        .route(
+            "/api/v1/host/gallery/release",
+            post(handlers::host::release_gallery),
+        )
+        // Escape hatch: force a keepsake rebuild. Without it a failed export is terminal at runtime
+        // (release_gallery refuses an already-released event; recovery only runs at boot).
+        .route(
+            "/api/v1/host/export/rebuild",
+            post(handlers::host::rebuild_export),
+        )
         .route("/api/v1/host/users", get(handlers::host::list_users))
-        .route("/api/v1/host/users/{id}/ban", post(handlers::host::ban_user))
-        .route("/api/v1/host/users/{id}/unban", post(handlers::host::unban_user))
-        .route("/api/v1/host/users/{id}/role", patch(handlers::host::set_role))
+        .route(
+            "/api/v1/host/users/{id}/ban",
+            post(handlers::host::ban_user),
+        )
+        .route(
+            "/api/v1/host/users/{id}/unban",
+            post(handlers::host::unban_user),
+        )
+        .route(
+            "/api/v1/host/users/{id}/role",
+            patch(handlers::host::set_role),
+        )
         .route(
             "/api/v1/host/users/{id}/pin-reset",
             post(handlers::host::reset_user_pin),
         )
-        .route("/api/v1/host/upload/{id}", delete(handlers::host::host_delete_upload))
-        .route("/api/v1/host/comment/{id}", delete(handlers::host::host_delete_comment))
+        .route(
+            "/api/v1/host/pin-reset-requests",
+            get(handlers::host::list_pin_reset_requests),
+        )
+        .route(
+            "/api/v1/host/pin-reset-requests/{id}",
+            delete(handlers::host::dismiss_pin_reset_request),
+        )
+        .route(
+            "/api/v1/host/upload/{id}",
+            delete(handlers::host::host_delete_upload),
+        )
+        .route(
+            "/api/v1/host/comment/{id}",
+            delete(handlers::host::host_delete_comment),
+        )
         // Export (all authenticated users)
         .route("/api/v1/export/status", get(handlers::admin::export_status))
-        .route("/api/v1/export/ticket", post(handlers::admin::export_ticket))
+        .route(
+            "/api/v1/export/ticket",
+            post(handlers::admin::export_ticket),
+        )
         .route("/api/v1/export/zip", get(handlers::admin::download_zip))
         .route("/api/v1/export/html", get(handlers::admin::download_html))
         // Admin Dashboard
@@ -119,7 +207,10 @@ async fn main() -> Result<()> {
             "/api/v1/admin/config",
             get(handlers::admin::get_config).patch(handlers::admin::patch_config),
         )
-        .route("/api/v1/admin/export/jobs", get(handlers::admin::get_export_jobs));
+        .route(
+            "/api/v1/admin/export/jobs",
+            get(handlers::admin::get_export_jobs),
+        );
 
     // Test-only route: a hard reset for the Playwright E2E harness. The handler
     // is compiled in always, but the route is only attached when
@@ -144,13 +235,99 @@ async fn main() -> Result<()> {
     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/displays",
+            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).await?;
+    axum::serve(listener, router)
+        .with_graceful_shutdown(shutdown_signal())
+        .await?;
 
     Ok(())
 }
+
+/// Hard cap on how long we wait for in-flight connections to drain after a shutdown
+/// signal. Uploads (streamed to disk) finish in well under this; the cap exists because
+/// long-lived SSE streams never end on their own and would otherwise keep the graceful
+/// drain — and thus the process — pending until the orchestrator force-kills it.
+const SHUTDOWN_GRACE: std::time::Duration = std::time::Duration::from_secs(10);
+
+/// Resolves on SIGINT (Ctrl-C) or SIGTERM (container stop / deploy). Letting
+/// `axum::serve` drain in-flight requests on this signal means a redeploy no longer
+/// truncates uploads mid-flight; any background compression/export half-states that a
+/// hard kill would leave are already reconciled by `startup_recovery` on the next boot.
+///
+/// Once the signal fires we also arm a detached backstop that force-exits after
+/// [`SHUTDOWN_GRACE`]. Without it, open SSE streams (which have no natural end) would
+/// hold the graceful drain open indefinitely; the backstop bounds shutdown regardless
+/// of the orchestrator's own kill timeout. If the drain completes first, `main` returns
+/// and the process exits before the timer ever fires.
+async fn shutdown_signal() {
+    let ctrl_c = async {
+        let _ = tokio::signal::ctrl_c().await;
+    };
+
+    #[cfg(unix)]
+    let terminate = async {
+        match tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate()) {
+            Ok(mut sig) => {
+                sig.recv().await;
+            }
+            Err(e) => {
+                tracing::warn!(error = ?e, "failed to install SIGTERM handler");
+                // Never resolve — fall back to ctrl_c only.
+                std::future::pending::<()>().await;
+            }
+        }
+    };
+
+    #[cfg(not(unix))]
+    let terminate = std::future::pending::<()>();
+
+    tokio::select! {
+        _ = ctrl_c => {}
+        _ = terminate => {}
+    }
+
+    tracing::info!(
+        "shutdown signal received, draining in-flight requests (max {}s)",
+        SHUTDOWN_GRACE.as_secs()
+    );
+
+    // Backstop: if the graceful drain is still blocked after the grace window (almost
+    // always because SSE streams are still open), exit anyway so deploys aren't stalled.
+    tokio::spawn(async {
+        tokio::time::sleep(SHUTDOWN_GRACE).await;
+        tracing::warn!(
+            "graceful drain exceeded {}s (likely open SSE streams); forcing exit",
+            SHUTDOWN_GRACE.as_secs()
+        );
+        std::process::exit(0);
+    });
+}

backend/src/models/comment.rs

@@ -3,6 +3,10 @@ use serde::Serialize;
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `comment`: every field is populated by sqlx from `SELECT *` / `RETURNING *`.
+// `deleted_at` is not read in Rust today (the soft-delete filter lives in SQL), but it is part of
+// the row and stays here so the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Comment {
     pub id: Uuid,
@@ -24,19 +28,24 @@ pub struct CommentDto {
 }
 
 impl Comment {
-    pub async fn create(
-        pool: &PgPool,
+    /// Takes any executor so the caller can insert the comment and link its
+    /// hashtags inside a single transaction.
+    pub async fn create<'e, E>(
+        executor: E,
         upload_id: Uuid,
         user_id: Uuid,
         body: &str,
-    ) -> Result<Self, sqlx::Error> {
+    ) -> Result<Self, sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query_as::<_, Self>(
             "INSERT INTO comment (upload_id, user_id, body) VALUES ($1, $2, $3) RETURNING *",
         )
         .bind(upload_id)
         .bind(user_id)
         .bind(body)
-        .fetch_one(pool)
+        .fetch_one(executor)
         .await
     }
 
@@ -74,26 +83,18 @@ impl Comment {
     }
 
     pub async fn find_by_id(pool: &PgPool, id: Uuid) -> Result<Option<Self>, sqlx::Error> {
-        sqlx::query_as::<_, Self>(
-            "SELECT * FROM comment WHERE id = $1 AND deleted_at IS NULL",
-        )
-        .bind(id)
-        .fetch_optional(pool)
-        .await
-    }
-
-    pub async fn soft_delete(pool: &PgPool, id: Uuid) -> Result<(), sqlx::Error> {
-        sqlx::query("UPDATE comment SET deleted_at = NOW() WHERE id = $1")
+        sqlx::query_as::<_, Self>("SELECT * FROM comment WHERE id = $1 AND deleted_at IS NULL")
             .bind(id)
-            .execute(pool)
-            .await?;
-        Ok(())
+            .fetch_optional(pool)
+            .await
     }
 
-    /// Event-scoped variant of [`Self::soft_delete`]. Returns `false` if the
-    /// comment doesn't exist or belongs to a different event.
+    /// Event-scoped soft delete. Returns `false` if the comment doesn't exist or belongs to a
+    /// different event.
+    /// Executor-generic so the delete and the keepsake regeneration can share one transaction
+    /// (see `Upload::soft_delete_in_event` for why that must be atomic).
     pub async fn soft_delete_in_event(
-        pool: &PgPool,
+        conn: &mut sqlx::PgConnection,
         id: Uuid,
         event_id: Uuid,
     ) -> Result<bool, sqlx::Error> {
@@ -106,7 +107,7 @@ impl Comment {
         )
         .bind(id)
         .bind(event_id)
-        .execute(pool)
+        .execute(conn)
         .await?;
         Ok(result.rows_affected() > 0)
     }

backend/src/models/event.rs

@@ -2,6 +2,11 @@ use chrono::{DateTime, Utc};
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `event`: every field is populated by sqlx from `SELECT *` / `RETURNING *`. Several
+// (`slug`, `cover_image_path`, `export_epoch`, `created_at`) are not read through this struct today
+// — callers that need them query the column directly — but they are part of the row and stay here so
+// the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Event {
     pub id: Uuid,
@@ -11,8 +16,11 @@ pub struct Event {
     pub is_active: bool,
     pub uploads_locked_at: Option<DateTime<Utc>>,
     pub export_released_at: Option<DateTime<Utc>>,
-    pub export_zip_ready: bool,
-    pub export_html_ready: bool,
+    /// Monotonic generation counter for the keepsake. Bumped in the SAME UPDATE as any change to
+    /// `export_released_at` (release and reopen are its only writers). An export is downloadable
+    /// iff a `done` `export_job` row carries this exact epoch — readiness is derived from that,
+    /// never stored, so it cannot drift and no worker can resurrect it. See migration 014.
+    pub export_epoch: i64,
     pub created_at: DateTime<Utc>,
 }
 
@@ -25,13 +33,11 @@ impl Event {
     }
 
     pub async fn create(pool: &PgPool, slug: &str, name: &str) -> Result<Self, sqlx::Error> {
-        sqlx::query_as::<_, Self>(
-            "INSERT INTO event (slug, name) VALUES ($1, $2) RETURNING *",
-        )
-        .bind(slug)
-        .bind(name)
-        .fetch_one(pool)
-        .await
+        sqlx::query_as::<_, Self>("INSERT INTO event (slug, name) VALUES ($1, $2) RETURNING *")
+            .bind(slug)
+            .bind(name)
+            .fetch_one(pool)
+            .await
     }
 
     pub async fn find_or_create(

backend/src/models/hashtag.rs

@@ -1,6 +1,8 @@
-use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `hashtag`, populated by sqlx from `RETURNING *` in `upsert`. Callers only use
+// `id` today; `event_id`/`tag` are the rest of the row and stay part of the struct.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Hashtag {
     pub id: Uuid,
@@ -10,7 +12,13 @@ pub struct Hashtag {
 
 impl Hashtag {
     /// Upsert a hashtag (insert if not exists, return existing if it does).
-    pub async fn upsert(pool: &PgPool, event_id: Uuid, tag: &str) -> Result<Self, sqlx::Error> {
+    ///
+    /// Takes any executor so callers can run it inside a transaction (atomic
+    /// upload/comment writes) or standalone against the pool.
+    pub async fn upsert<'e, E>(executor: E, event_id: Uuid, tag: &str) -> Result<Self, sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         let normalized = tag.trim().trim_start_matches('#').to_lowercase();
         sqlx::query_as::<_, Self>(
             "INSERT INTO hashtag (event_id, tag) VALUES ($1, $2)
@@ -19,52 +27,42 @@ impl Hashtag {
         )
         .bind(event_id)
         .bind(&normalized)
-        .fetch_one(pool)
+        .fetch_one(executor)
         .await
     }
 
-    pub async fn link_to_upload(
-        pool: &PgPool,
+    pub async fn link_to_upload<'e, E>(
+        executor: E,
         upload_id: Uuid,
         hashtag_id: Uuid,
-    ) -> Result<(), sqlx::Error> {
+    ) -> Result<(), sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query(
             "INSERT INTO upload_hashtag (upload_id, hashtag_id) VALUES ($1, $2)
              ON CONFLICT DO NOTHING",
         )
         .bind(upload_id)
         .bind(hashtag_id)
-        .execute(pool)
+        .execute(executor)
         .await?;
         Ok(())
     }
 
-    pub async fn unlink_all_from_upload(
-        pool: &PgPool,
+    pub async fn unlink_all_from_upload<'e, E>(
+        executor: E,
         upload_id: Uuid,
-    ) -> Result<(), sqlx::Error> {
+    ) -> Result<(), sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query("DELETE FROM upload_hashtag WHERE upload_id = $1")
             .bind(upload_id)
-            .execute(pool)
+            .execute(executor)
             .await?;
         Ok(())
     }
-
-    pub async fn tags_for_upload(
-        pool: &PgPool,
-        upload_id: Uuid,
-    ) -> Result<Vec<String>, sqlx::Error> {
-        let rows: Vec<(String,)> = sqlx::query_as(
-            "SELECT h.tag FROM hashtag h
-             JOIN upload_hashtag uh ON uh.hashtag_id = h.id
-             WHERE uh.upload_id = $1
-             ORDER BY h.tag",
-        )
-        .bind(upload_id)
-        .fetch_all(pool)
-        .await?;
-        Ok(rows.into_iter().map(|r| r.0).collect())
-    }
 }
 
 /// Extract `#hashtags` from text (caption or body). Tags are restricted to
@@ -124,14 +122,20 @@ mod tests {
         assert_eq!(extract_hashtags(&format!("#{ok}")), vec![ok.clone()]);
         // 41+ chars → dropped entirely (not truncated).
         let too_long = "a".repeat(41);
-        assert_eq!(extract_hashtags(&format!("#{too_long}")), Vec::<String>::new());
+        assert_eq!(
+            extract_hashtags(&format!("#{too_long}")),
+            Vec::<String>::new()
+        );
     }
 
     #[test]
     fn duplicate_tags_are_returned_verbatim_not_deduplicated() {
         // Dedup is the DB's job (Hashtag::upsert ON CONFLICT); extraction returns each
         // occurrence so callers can count/link them independently. Case folds to lower.
-        assert_eq!(extract_hashtags("#fun #Fun #fun!"), vec!["fun", "fun", "fun"]);
+        assert_eq!(
+            extract_hashtags("#fun #Fun #fun!"),
+            vec!["fun", "fun", "fun"]
+        );
     }
 
     #[test]

backend/src/models/session.rs

@@ -2,6 +2,9 @@ use chrono::{DateTime, Utc};
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `session`, populated by sqlx from `RETURNING *`. Session validation is done in SQL
+// (expiry/last-seen predicates), so no field is read in Rust — the struct is the row's shape.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Session {
     pub id: Uuid,
@@ -43,22 +46,65 @@ impl Session {
         .await
     }
 
-    pub async fn touch(pool: &PgPool, id: Uuid) -> Result<(), sqlx::Error> {
-        sqlx::query("UPDATE session SET last_seen_at = NOW() WHERE id = $1")
-            .bind(id)
-            .execute(pool)
-            .await?;
+    /// Resolve a session token straight to its live user row in one round-trip.
+    ///
+    /// The auth extractor runs on every authenticated request and used to do two
+    /// sequential queries (session lookup, then user lookup); this collapses them into
+    /// a single `session JOIN "user"`. The `expires_at` guard mirrors
+    /// [`Self::find_by_token_hash`], and the user row is read live (role/ban are never
+    /// trusted from the JWT). Returns `None` when the session is missing/expired.
+    pub async fn find_user_by_token_hash(
+        pool: &PgPool,
+        token_hash: &str,
+    ) -> Result<Option<crate::models::user::User>, sqlx::Error> {
+        sqlx::query_as::<_, crate::models::user::User>(
+            "SELECT u.*
+             FROM session s
+             JOIN \"user\" u ON u.id = s.user_id
+             WHERE s.token_hash = $1 AND s.expires_at > NOW()",
+        )
+        .bind(token_hash)
+        .fetch_optional(pool)
+        .await
+    }
+
+    /// Touch `last_seen_at` AND slide `expires_at` forward by `expiry_days` from now, so
+    /// an actively-used session never hits the fixed 30-day cliff (it renews on every
+    /// authenticated request). An idle session still expires `expiry_days` after its last
+    /// activity. Keyed by token hash so the auth extractor needs no prior id lookup.
+    pub async fn touch_and_renew(
+        pool: &PgPool,
+        token_hash: &str,
+        expiry_days: i64,
+    ) -> Result<(), sqlx::Error> {
+        sqlx::query(
+            "UPDATE session
+             SET last_seen_at = NOW(),
+                 expires_at = NOW() + ($2 || ' days')::interval
+             WHERE token_hash = $1",
+        )
+        .bind(token_hash)
+        .bind(expiry_days.to_string())
+        .execute(pool)
+        .await?;
         Ok(())
     }
 
-    pub async fn delete_by_token_hash(
-        pool: &PgPool,
-        token_hash: &str,
-    ) -> Result<(), sqlx::Error> {
+    pub async fn delete_by_token_hash(pool: &PgPool, token_hash: &str) -> Result<(), sqlx::Error> {
         sqlx::query("DELETE FROM session WHERE token_hash = $1")
             .bind(token_hash)
             .execute(pool)
             .await?;
         Ok(())
     }
+
+    /// Revoke every session for a user. Backs "sign out everywhere" and the forced
+    /// re-auth after a host PIN-reset or a ban. Returns the number of sessions cleared.
+    pub async fn delete_all_for_user(pool: &PgPool, user_id: Uuid) -> Result<u64, sqlx::Error> {
+        let r = sqlx::query("DELETE FROM session WHERE user_id = $1")
+            .bind(user_id)
+            .execute(pool)
+            .await?;
+        Ok(r.rows_affected())
+    }
 }

backend/src/models/upload.rs

@@ -3,6 +3,10 @@ use serde::Serialize;
 use sqlx::PgPool;
 use uuid::Uuid;
 
+// Row shape for `upload`: every field is populated by sqlx from `RETURNING *` in `create`. Callers
+// mostly use `id` and hand the rest to the compression/feed queries, so most fields are never read
+// through this struct — they stay here so it keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct Upload {
     pub id: Uuid,
@@ -35,16 +39,32 @@ pub struct UploadDto {
     pub created_at: DateTime<Utc>,
 }
 
+/// Minimal projection of an upload's on-disk file paths, used by the visibility-gated
+/// media aliases so they don't hydrate the entire `Upload` row per request.
+#[derive(Debug, sqlx::FromRow)]
+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,
+}
+
 impl Upload {
-    pub async fn create(
-        pool: &PgPool,
+    /// Takes any executor so the caller can run it inside a transaction (atomic
+    /// quota + insert) or standalone against the pool.
+    pub async fn create<'e, E>(
+        executor: E,
         event_id: Uuid,
         user_id: Uuid,
         original_path: &str,
         mime_type: &str,
         original_size_bytes: i64,
         caption: Option<&str>,
-    ) -> Result<Self, sqlx::Error> {
+    ) -> Result<Self, sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query_as::<_, Self>(
             "INSERT INTO upload (event_id, user_id, original_path, mime_type, original_size_bytes, caption)
              VALUES ($1, $2, $3, $4, $5, $6)
@@ -56,13 +76,29 @@ impl Upload {
         .bind(mime_type)
         .bind(original_size_bytes)
         .bind(caption)
-        .fetch_one(pool)
+        .fetch_one(executor)
         .await
     }
 
-    pub async fn find_by_id(pool: &PgPool, id: Uuid) -> Result<Option<Self>, sqlx::Error> {
-        sqlx::query_as::<_, Self>(
-            "SELECT * FROM upload WHERE id = $1 AND deleted_at IS NULL",
+    /// Lean lookup for the public media aliases (`get_original`/`get_preview`/
+    /// `get_thumbnail`): returns ONLY the file paths + mime for a visible upload —
+    /// excluding soft-deleted rows, hidden owners (`uploads_hidden`), and banned owners
+    /// (`is_banned`) — the same filter `v_feed` applies. So moderation that removes a post
+    /// from the feed also stops its original/preview/thumbnail from being pulled by UUID.
+    ///
+    /// Selects four columns instead of the whole `Upload` row: this runs once per image
+    /// per cache-miss on the media hot path, so we avoid hydrating fields the response
+    /// never uses.
+    pub async fn find_visible_media(
+        pool: &PgPool,
+        id: Uuid,
+    ) -> Result<Option<VisibleMedia>, sqlx::Error> {
+        sqlx::query_as::<_, VisibleMedia>(
+            "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
+               AND u.uploads_hidden = false AND u.is_banned = false",
         )
         .bind(id)
         .fetch_optional(pool)
@@ -99,6 +135,19 @@ 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(())
+    }
+
     pub async fn set_thumbnail_path(
         pool: &PgPool,
         id: Uuid,
@@ -148,12 +197,17 @@ impl Upload {
     /// Event-scoped variant of [`Self::soft_delete`]. Returns `false` if no row
     /// matched (already deleted, wrong event, or unknown id) so host handlers
     /// can return a clean 404 instead of silently no-op'ing.
+    /// Executor-generic so a caller can run the delete and the keepsake regeneration in ONE
+    /// transaction. They must be atomic: if the delete commits and the regeneration doesn't (a
+    /// dropped handler future, a failed second tx), the taken-down photo stays in the downloadable
+    /// archive forever, and recovery can't tell — the keepsake still looks complete at the current
+    /// epoch, and the host can no longer even find the upload to retry.
     pub async fn soft_delete_in_event(
-        pool: &PgPool,
+        conn: &mut sqlx::PgConnection,
         id: Uuid,
         event_id: Uuid,
     ) -> Result<bool, sqlx::Error> {
-        let mut tx = pool.begin().await?;
+        let tx = conn;
         let row: Option<(Uuid, i64)> = sqlx::query_as(
             "UPDATE upload
              SET deleted_at = NOW()
@@ -178,19 +232,21 @@ impl Upload {
         } else {
             false
         };
-        tx.commit().await?;
         Ok(deleted)
     }
 
-    pub async fn update_caption(
-        pool: &PgPool,
+    pub async fn update_caption<'e, E>(
+        executor: E,
         id: Uuid,
         caption: Option<&str>,
-    ) -> Result<(), sqlx::Error> {
+    ) -> Result<(), sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query("UPDATE upload SET caption = $2 WHERE id = $1")
             .bind(id)
             .bind(caption)
-            .execute(pool)
+            .execute(executor)
             .await?;
         Ok(())
     }

backend/src/models/user.rs

@@ -22,6 +22,10 @@ impl UserRole {
     }
 }
 
+// Row shape for `user`: every field is populated by sqlx from `SELECT *` / `RETURNING *`.
+// `uploads_hidden`, `failed_pin_attempts` and `created_at` are enforced/updated in SQL rather than
+// read in Rust, but they are part of the row and stay here so the struct keeps mirroring the table.
+#[allow(dead_code)]
 #[derive(Debug, sqlx::FromRow)]
 pub struct User {
     pub id: Uuid,
@@ -105,14 +109,16 @@ impl User {
         Ok(row.0)
     }
 
-    pub async fn lock_pin(pool: &PgPool, id: Uuid, until: DateTime<Utc>) -> Result<(), sqlx::Error> {
-        sqlx::query(
-            "UPDATE \"user\" SET pin_locked_until = $2 WHERE id = $1",
-        )
-        .bind(id)
-        .bind(until)
-        .execute(pool)
-        .await?;
+    pub async fn lock_pin(
+        pool: &PgPool,
+        id: Uuid,
+        until: DateTime<Utc>,
+    ) -> Result<(), sqlx::Error> {
+        sqlx::query("UPDATE \"user\" SET pin_locked_until = $2 WHERE id = $1")
+            .bind(id)
+            .bind(until)
+            .execute(pool)
+            .await?;
         Ok(())
     }
 

backend/src/services/compression.rs

@@ -1,9 +1,10 @@
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
+use std::sync::atomic::{AtomicU64, Ordering};
 
 use anyhow::{Context, Result};
 use sqlx::PgPool;
-use tokio::sync::{broadcast, Semaphore};
+use tokio::sync::{Semaphore, broadcast};
 use uuid::Uuid;
 
 use crate::models::upload::Upload;
@@ -15,24 +16,54 @@ pub struct CompressionWorker {
     pool: PgPool,
     media_path: PathBuf,
     sse_tx: broadcast::Sender<SseEvent>,
+    /// Bumped whenever the underlying data is reset out from under in-flight work (only the e2e
+    /// TRUNCATE does this today). A task captures the value at spawn and abandons itself if it has
+    /// changed by the time it runs — see `process`.
+    generation: Arc<AtomicU64>,
 }
 
 impl CompressionWorker {
-    pub fn new(pool: PgPool, media_path: PathBuf, concurrency: usize, sse_tx: broadcast::Sender<SseEvent>) -> Self {
+    pub fn new(
+        pool: PgPool,
+        media_path: PathBuf,
+        concurrency: usize,
+        sse_tx: broadcast::Sender<SseEvent>,
+    ) -> Self {
         Self {
             semaphore: Arc::new(Semaphore::new(concurrency)),
             pool,
             media_path,
             sse_tx,
+            generation: Arc::new(AtomicU64::new(0)),
         }
     }
 
+    /// Invalidate all in-flight and queued compression work. Called by the e2e TRUNCATE endpoint:
+    /// truncating deletes the upload rows and wipes `media/`, so a worker that was queued on the
+    /// semaphore when the wipe happened would otherwise wake in the NEXT test, fail to find its
+    /// file, and broadcast `upload-error` / `upload-deleted` into that test's live SSE stream —
+    /// corrupting any test that asserts on toasts or feed contents. Bumping the generation makes
+    /// those stale tasks return silently instead. A no-op in production (never called there).
+    pub fn bump_generation(&self) {
+        self.generation.fetch_add(1, Ordering::SeqCst);
+    }
+
     /// 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();
+        let born_at = worker.generation.load(Ordering::SeqCst);
         tokio::spawn(async move {
             let _permit = worker.semaphore.acquire().await;
-            match worker.do_process(upload_id, &original_path, &mime_type).await {
+            // The data this task was queued against may have been reset while it waited for a permit
+            // (e2e TRUNCATE). If so, its file and row are gone; doing anything — including
+            // broadcasting a failure — would leak into an unrelated test. Abandon quietly.
+            if worker.generation.load(Ordering::SeqCst) != born_at {
+                return;
+            }
+            match worker
+                .do_process(upload_id, &original_path, &mime_type)
+                .await
+            {
                 Ok(_) => {
                     tracing::info!("compression completed for upload {upload_id}");
                     let _ = worker.sse_tx.send(SseEvent {
@@ -42,11 +73,29 @@ 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).
+                    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");
+                    }
                     let _ = worker.sse_tx.send(SseEvent {
                         event_type: "upload-error".to_string(),
-                        data: serde_json::json!({ "upload_id": upload_id, "error": e.to_string() }).to_string(),
+                        data: serde_json::json!({ "upload_id": upload_id, "error": e.to_string() })
+                            .to_string(),
+                    });
+                    let _ = worker.sse_tx.send(SseEvent {
+                        event_type: "upload-deleted".to_string(),
+                        data: serde_json::json!({ "upload_id": upload_id }).to_string(),
                     });
-                    let _ = Upload::set_compression_status(&worker.pool, upload_id, "failed").await;
                 }
             }
         });
@@ -63,9 +112,12 @@ 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).await?;
+            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?;
+            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?;
@@ -76,20 +128,33 @@ 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<()> {
@@ -109,10 +174,29 @@ impl CompressionWorker {
             reader.limits(limits);
             let img = reader.decode().context("failed to decode image")?;
 
-            // 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" {
@@ -131,14 +215,64 @@ impl CompressionWorker {
         })
         .await??;
 
-        Ok(format!("previews/{preview_filename}"))
+        Ok((
+            format!("previews/{filename}"),
+            format!("displays/{filename}"),
+        ))
     }
 
-    async fn generate_video_thumbnail(
-        &self,
-        upload_id: Uuid,
-        original: &Path,
-    ) -> Result<String> {
+    /// One-time backfill: existing image uploads processed before the display derivative
+    /// existed have a preview but no `display_path`. Regenerate both derivatives for them
+    /// (decode is cheap and idempotent) and set the path. Unlike the failure path in
+    /// `process`, a backfill error is logged and skipped — it must NEVER soft-delete an
+    /// upload that already has a working preview. Fire-and-forget from startup.
+    pub async fn backfill_missing_display(&self) {
+        let rows = sqlx::query_as::<_, (Uuid, String, String)>(
+            "SELECT id, original_path, mime_type FROM upload
+             WHERE display_path IS NULL AND preview_path IS NOT NULL
+               AND deleted_at IS NULL AND mime_type LIKE 'image/%'",
+        )
+        .fetch_all(&self.pool)
+        .await;
+        let rows = match rows {
+            Ok(r) => r,
+            Err(e) => {
+                tracing::warn!(error = ?e, "display backfill query failed");
+                return;
+            }
+        };
+        if rows.is_empty() {
+            return;
+        }
+        tracing::info!(
+            "backfilling display derivative 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;
+                        tracing::info!("display backfilled for upload {id}");
+                    }
+                    Err(e) => {
+                        // Leave the existing preview intact; the diashow falls back to the
+                        // original for this upload until a later successful pass.
+                        tracing::warn!(error = ?e, %id, "display backfill failed; leaving as-is");
+                    }
+                }
+            });
+        }
+    }
+
+    async fn generate_video_thumbnail(&self, upload_id: Uuid, original: &Path) -> Result<String> {
         let thumbs_dir = self.media_path.join("thumbnails");
         tokio::fs::create_dir_all(&thumbs_dir).await?;
 
@@ -168,18 +302,14 @@ impl CompressionWorker {
             .spawn()
             .context("failed to spawn ffmpeg")?;
 
-        let status = match tokio::time::timeout(
-            std::time::Duration::from_secs(120),
-            child.wait(),
-        )
-        .await
-        {
-            Ok(res) => res.context("ffmpeg wait failed")?,
-            Err(_) => {
-                let _ = child.kill().await;
-                anyhow::bail!("ffmpeg timeout after 120s");
-            }
-        };
+        let status =
+            match tokio::time::timeout(std::time::Duration::from_secs(120), child.wait()).await {
+                Ok(res) => res.context("ffmpeg wait failed")?,
+                Err(_) => {
+                    let _ = child.kill().await;
+                    anyhow::bail!("ffmpeg timeout after 120s");
+                }
+            };
 
         if !status.success() {
             // Best-effort: drain stderr for the log.
@@ -188,10 +318,7 @@ impl CompressionWorker {
                 use tokio::io::AsyncReadExt;
                 let _ = handle.read_to_end(&mut stderr).await;
             }
-            anyhow::bail!(
-                "ffmpeg failed: {}",
-                String::from_utf8_lossy(&stderr)
-            );
+            anyhow::bail!("ffmpeg failed: {}", String::from_utf8_lossy(&stderr));
         }
 
         Ok(format!("thumbnails/{thumb_filename}"))

backend/src/services/config.rs

@@ -1,46 +1,147 @@
-//! Reads of the runtime-tunable `config` table.
+//! Reads of the runtime-tunable `config` table, fronted by an in-memory cache.
 //!
 //! Each handler used to keep a small local copy of these helpers; consolidating them
 //! here means one place to add a parser, one place to mock for tests, and one place to
 //! find when a key changes. New keys do not require code changes — they're picked up
-//! the next time someone calls `get_*`.
+//! the next time the cache reloads.
+//!
+//! ## Why a cache
+//!
+//! The `config` table is effectively static during an event, yet it was the busiest
+//! query in the system: every request re-read each key with its own `SELECT`
+//! (an upload touched it ~8 times). Against the small connection pool that was the
+//! throughput ceiling. [`ConfigCache`] loads the whole table once and serves reads
+//! from memory.
+//!
+//! ## Consistency contract
+//!
+//! Correctness comes from **synchronous invalidation on every write**, not from the
+//! TTL. The two runtime write paths — the admin `PATCH /admin/config` handler and the
+//! test-mode truncate/reseed — both call [`ConfigCache::invalidate`] after committing,
+//! so the *next* read reloads from the DB and sees the new value immediately. The
+//! [`RELOAD_TTL`] is only a safety net for out-of-band changes (e.g. a migration or a
+//! manual DB edit); it is deliberately short but never the primary mechanism.
 //!
 //! Values are read with a default fallback so the app still starts if a key is missing
 //! (e.g. during a migration window). Production seeds keys via migrations 005 and 009.
 
+use std::collections::HashMap;
+use std::sync::{Arc, RwLock};
+use std::time::{Duration, Instant};
+
 use sqlx::PgPool;
 
-async fn fetch_raw(pool: &PgPool, key: &str) -> Option<String> {
-    sqlx::query_as::<_, (String,)>("SELECT value FROM config WHERE key = $1")
-        .bind(key)
-        .fetch_optional(pool)
+/// How long a loaded snapshot is trusted before the next read reloads it. This is a
+/// backstop for out-of-band DB changes only — every in-process write invalidates the
+/// cache synchronously, so tests that PATCH-then-assert never depend on this expiring.
+const RELOAD_TTL: Duration = Duration::from_secs(30);
+
+struct Snapshot {
+    values: HashMap<String, String>,
+    loaded_at: Instant,
+}
+
+/// In-memory cache of the entire `config` table. Cheap to `clone` (shares the pool and
+/// the `Arc`), so it lives in `AppState` and every handler reads through it.
+#[derive(Clone)]
+pub struct ConfigCache {
+    pool: PgPool,
+    inner: Arc<RwLock<Option<Snapshot>>>,
+}
+
+impl ConfigCache {
+    pub fn new(pool: PgPool) -> Self {
+        Self {
+            pool,
+            inner: Arc::new(RwLock::new(None)),
+        }
+    }
+
+    /// Drop the cached snapshot so the next read reloads the whole table from the DB.
+    /// Call this after any write to the `config` table (admin PATCH, test reseed).
+    pub fn invalidate(&self) {
+        *self.inner.write().unwrap() = None;
+    }
+
+    /// Return the fresh snapshot if one is loaded and still within [`RELOAD_TTL`].
+    fn fresh_snapshot(&self) -> Option<HashMap<String, String>> {
+        let guard = self.inner.read().unwrap();
+        match guard.as_ref() {
+            Some(snap) if snap.loaded_at.elapsed() < RELOAD_TTL => Some(snap.values.clone()),
+            _ => None,
+        }
+    }
+
+    /// Read one key, loading the whole table into the cache on a miss/expiry. On a DB
+    /// error we return `None` (callers fall back to their default) without poisoning
+    /// the cache.
+    async fn get_raw(&self, key: &str) -> Option<String> {
+        if let Some(values) = self.fresh_snapshot() {
+            return values.get(key).cloned();
+        }
+
+        // Cache miss or stale — reload the entire table in one query.
+        let rows: Vec<(String, String)> = match sqlx::query_as::<_, (String, String)>(
+            "SELECT key, value FROM config",
+        )
+        .fetch_all(&self.pool)
         .await
-        .ok()
-        .flatten()
-        .map(|(v,)| v)
+        {
+            Ok(rows) => rows,
+            Err(e) => {
+                tracing::warn!(error = ?e, "config reload failed; using defaults for this read");
+                return None;
+            }
+        };
+
+        let values: HashMap<String, String> = rows.into_iter().collect();
+        let result = values.get(key).cloned();
+        *self.inner.write().unwrap() = Some(Snapshot {
+            values,
+            loaded_at: Instant::now(),
+        });
+        result
+    }
 }
 
-pub async fn get_str(pool: &PgPool, key: &str, default: &str) -> String {
-    fetch_raw(pool, key).await.unwrap_or_else(|| default.to_string())
+pub async fn get_str(cache: &ConfigCache, key: &str, default: &str) -> String {
+    cache
+        .get_raw(key)
+        .await
+        .unwrap_or_else(|| default.to_string())
 }
 
-pub async fn get_i64(pool: &PgPool, key: &str, default: i64) -> i64 {
-    fetch_raw(pool, key).await.and_then(|v| v.parse().ok()).unwrap_or(default)
+pub async fn get_i64(cache: &ConfigCache, key: &str, default: i64) -> i64 {
+    cache
+        .get_raw(key)
+        .await
+        .and_then(|v| v.parse().ok())
+        .unwrap_or(default)
 }
 
-pub async fn get_usize(pool: &PgPool, key: &str, default: usize) -> usize {
-    fetch_raw(pool, key).await.and_then(|v| v.parse().ok()).unwrap_or(default)
+pub async fn get_usize(cache: &ConfigCache, key: &str, default: usize) -> usize {
+    cache
+        .get_raw(key)
+        .await
+        .and_then(|v| v.parse().ok())
+        .unwrap_or(default)
 }
 
-pub async fn get_f64(pool: &PgPool, key: &str, default: f64) -> f64 {
-    fetch_raw(pool, key).await.and_then(|v| v.parse().ok()).unwrap_or(default)
+pub async fn get_f64(cache: &ConfigCache, key: &str, default: f64) -> f64 {
+    cache
+        .get_raw(key)
+        .await
+        .and_then(|v| v.parse().ok())
+        .unwrap_or(default)
 }
 
 /// Parses common truthy spellings used by both the migration seeds and the admin form.
 /// Accepts `true/false`, `1/0`, `yes/no`, `on/off` — case-insensitive. Anything else
 /// returns `default`.
-pub async fn get_bool(pool: &PgPool, key: &str, default: bool) -> bool {
-    let Some(raw) = fetch_raw(pool, key).await else { return default };
+pub async fn get_bool(cache: &ConfigCache, key: &str, default: bool) -> bool {
+    let Some(raw) = cache.get_raw(key).await else {
+        return default;
+    };
     match raw.trim().to_ascii_lowercase().as_str() {
         "true" | "1" | "yes" | "on" => true,
         "false" | "0" | "no" | "off" => false,

backend/src/services/disk.rs

@@ -0,0 +1,158 @@
+//! Cached view of the filesystem backing the media directory.
+//!
+//! Free/total disk space is needed on two hot paths — the per-user storage quota
+//! (checked on every upload *and* every `GET /me/quota` poll) and the admin stats
+//! endpoint. Reading it means `sysinfo::Disks::new_with_refreshed_list()`, which stats
+//! every mounted filesystem; doing that per request is wasteful for a number that
+//! barely moves. [`DiskCache`] refreshes it at most once per [`TTL`] and serves the
+//! rest from memory.
+
+use std::path::{Path, PathBuf};
+use std::sync::{Arc, RwLock};
+use std::time::{Duration, Instant};
+
+/// How long a disk reading is trusted before the next call re-stats the filesystem.
+const TTL: Duration = Duration::from_secs(15);
+
+#[derive(Clone, Copy)]
+pub struct DiskInfo {
+    pub total: u64,
+    pub free: u64,
+}
+
+/// Cheap-to-clone cache of the media filesystem's total/free bytes. Lives in
+/// `AppState`.
+#[derive(Clone)]
+pub struct DiskCache {
+    inner: Arc<RwLock<Option<(PathBuf, DiskInfo, Instant)>>>,
+}
+
+impl DiskCache {
+    pub fn new() -> Self {
+        Self {
+            inner: Arc::new(RwLock::new(None)),
+        }
+    }
+
+    /// Drop the cached reading so the next `snapshot()` re-measures the filesystem.
+    ///
+    /// Used by the e2e TRUNCATE endpoint. Truncating deletes every uploaded file, which materially
+    /// changes free space — but the cached reading survives for up to the TTL, so the next test can
+    /// compute a quota from the PREVIOUS test's disk. That matters now that the quota tests steer
+    /// the per-user limit off `free_disk_bytes`: a stale reading makes the limit wrong and the test
+    /// flaky, for reasons that have nothing to do with the code under test.
+    pub fn invalidate(&self) {
+        *self.inner.write().unwrap() = None;
+    }
+
+    /// Cached `(total, free)` bytes for the filesystem that holds `media_path`.
+    ///
+    /// Returns `None` when the mount can't be resolved — callers MUST treat that as
+    /// "unknown", never "zero free". (The quota path in particular fails *open* on
+    /// `None`: enforcing a 0-byte limit would lock every user out of uploading.)
+    /// Cached free-space reading for `path`.
+    ///
+    /// The cache is keyed BY PATH. It used to hold a single slot and ignore its argument on a hit,
+    /// so it would happily return the media volume's numbers for any other path within the TTL.
+    /// That was invisible only because every caller happened to pass `media_path` — the first
+    /// caller to ask about a different volume (e.g. the exports volume, which is a separate mount)
+    /// would have silently got the wrong filesystem's free space.
+    pub fn snapshot(&self, path: &Path) -> Option<DiskInfo> {
+        if let Some((cached_path, info, at)) = self.inner.read().unwrap().as_ref()
+            && cached_path == path
+            && at.elapsed() < TTL
+        {
+            return Some(*info);
+        }
+        let info = read_disk_for_path(path)?;
+        *self.inner.write().unwrap() = Some((path.to_path_buf(), info, Instant::now()));
+        Some(info)
+    }
+}
+
+impl Default for DiskCache {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+/// 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
+/// [`select_disk`] so the (fiddly, edge-case-prone) matching logic is unit-testable
+/// without touching the real filesystem.
+fn read_disk_for_path(media_path: &Path) -> Option<DiskInfo> {
+    let disks = sysinfo::Disks::new_with_refreshed_list();
+    let mounts: Vec<(String, u64, u64)> = disks
+        .iter()
+        .map(|d| {
+            (
+                d.mount_point().to_string_lossy().to_string(),
+                d.total_space(),
+                d.available_space(),
+            )
+        })
+        .collect();
+    select_disk(&mounts, &media_path.to_string_lossy())
+}
+
+/// Pick the filesystem for `media_path` from a `(mount_point, total, free)` table.
+///
+/// Chooses the **longest** mount point that is a prefix of `media_path` (the most
+/// specific filesystem) rather than the first match — otherwise the root `/` mount,
+/// which prefixes every absolute path, could shadow a dedicated `/media` volume. Falls
+/// back to `/` when nothing prefixes the path (e.g. a relative media path), and to
+/// `None` when even that is absent — the caller treats `None` as "unknown" and fails
+/// open on quota.
+fn select_disk(mounts: &[(String, u64, u64)], media_path: &str) -> Option<DiskInfo> {
+    mounts
+        .iter()
+        .filter(|(mp, _, _)| media_path.starts_with(mp.as_str()))
+        .max_by_key(|(mp, _, _)| mp.len())
+        .or_else(|| mounts.iter().find(|(mp, _, _)| mp == "/"))
+        .map(|(_, total, free)| DiskInfo {
+            total: *total,
+            free: *free,
+        })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::select_disk;
+
+    #[test]
+    fn picks_longest_matching_mount() {
+        // Both "/" and "/media" prefix the path; the dedicated volume must win.
+        let mounts = vec![("/".to_string(), 100, 40), ("/media".to_string(), 200, 150)];
+        let d = select_disk(&mounts, "/media/originals/x.jpg").unwrap();
+        assert_eq!((d.total, d.free), (200, 150));
+    }
+
+    #[test]
+    fn falls_back_to_root_when_no_specific_mount_matches() {
+        let mounts = vec![("/".to_string(), 100, 40), ("/media".to_string(), 200, 150)];
+        // "/var/lib" is only prefixed by "/".
+        let d = select_disk(&mounts, "/var/lib/data").unwrap();
+        assert_eq!((d.total, d.free), (100, 40));
+    }
+
+    #[test]
+    fn relative_path_uses_root_fallback() {
+        let mounts = vec![("/".to_string(), 100, 40)];
+        // A relative path prefixes nothing, so the explicit "/" fallback applies.
+        let d = select_disk(&mounts, "media/originals").unwrap();
+        assert_eq!((d.total, d.free), (100, 40));
+    }
+
+    #[test]
+    fn none_when_no_mount_matches_and_no_root() {
+        // No "/" present and nothing prefixes the relative path → unknown (fail-open).
+        let mounts = vec![("/data".to_string(), 100, 40)];
+        assert!(select_disk(&mounts, "relative/path").is_none());
+    }
+
+    #[test]
+    fn none_on_empty_mount_table() {
+        assert!(select_disk(&[], "/media/x").is_none());
+    }
+}

backend/src/services/jobs.rs

@@ -1,73 +0,0 @@
-//! Shared shape for long-running background work.
-//!
-//! Today's [`compression`](crate::services::compression) and [`export`](crate::services::export)
-//! pipelines each implement their own progress + SSE plumbing. They could converge on the
-//! trait sketched here so future jobs (analytics, archival, ...) plug into one progress
-//! pipeline.
-//!
-//! This module is intentionally a *sketch*: the existing services are not yet wired to
-//! it. The aim is to (a) document the convention so new jobs follow it, (b) make the
-//! refactor mechanical when someone is ready to do it. See `docs/IDEAS.md` —
-//! "Maintainability principles" — for the rationale.
-//!
-//! Example of an eventual implementor:
-//!
-//! ```ignore
-//! struct ZipExport { event_id: Uuid, /* … */ }
-//!
-//! impl BackgroundJob for ZipExport {
-//!     fn name(&self) -> &'static str { "zip-export" }
-//!     async fn run(self, ctx: JobContext) -> Result<()> {
-//!         for (i, item) in items.iter().enumerate() {
-//!             ctx.report(percent(i, items.len())).await?;
-//!             // … write to zip …
-//!         }
-//!         Ok(())
-//!     }
-//! }
-//! ```
-
-use anyhow::Result;
-
-/// Handle handed to a running job: reports progress and emits SSE events.
-///
-/// Wraps the existing SSE broadcaster and an optional `export_job` row. Implementors
-/// don't need to know about `state.sse_tx` directly — they call [`JobContext::report`]
-/// and get the same effect.
-pub struct JobContext {
-    pub job_id: Option<uuid::Uuid>,
-    pub event_kind: &'static str,
-    pub sse_tx: tokio::sync::broadcast::Sender<crate::state::SseEvent>,
-    pub pool: sqlx::PgPool,
-}
-
-impl JobContext {
-    /// Update progress (0..=100) and broadcast an SSE tick. Cheap to call often —
-    /// rate-limit at the call site if a job emits at > 10 Hz.
-    pub async fn report(&self, percent: u8) -> Result<()> {
-        if let Some(job_id) = self.job_id {
-            sqlx::query("UPDATE export_job SET progress_pct = $1 WHERE id = $2")
-                .bind(percent as i16)
-                .bind(job_id)
-                .execute(&self.pool)
-                .await?;
-        }
-        let _ = self.sse_tx.send(crate::state::SseEvent::new(
-            self.event_kind,
-            serde_json::json!({ "progress_pct": percent }).to_string(),
-        ));
-        Ok(())
-    }
-}
-
-/// One unit of work that publishes progress through a [`JobContext`].
-///
-/// `run` consumes `self`; spawn with `tokio::spawn` at the caller. Errors propagate;
-/// the caller is responsible for mapping them to `export_job.error_message` or
-/// equivalent. Implementors stay small — the trait deliberately has no `cancel`
-/// or `pause`; we have not needed those yet.
-#[allow(async_fn_in_trait)]
-pub trait BackgroundJob: Send + 'static {
-    fn name(&self) -> &'static str;
-    async fn run(self, ctx: JobContext) -> Result<()>;
-}

backend/src/services/maintenance.rs

@@ -44,8 +44,23 @@ pub async fn startup_recovery(pool: &PgPool) {
         Err(e) => tracing::error!("startup recovery: failed to sweep uploads: {e:#}"),
     }
 
-    // Export jobs interrupted mid-run. Mark 'failed' so the host can re-trigger.
-    // The `UNIQUE(event_id, type)` constraint would otherwise block re-release.
+    // Export jobs interrupted mid-run are marked 'failed' here so they aren't left
+    // 'running' forever. The host CANNOT re-trigger a released export (release_gallery
+    // rejects an already-released event), so `export::recover_exports` re-spawns these
+    // failed-but-released jobs from `main` once `AppState` exists (it needs the media
+    // paths + SSE sender this fn doesn't have).
+    //
+    // SINGLE-INSTANCE ASSUMPTION: this sweep is unscoped — it reaps every `running` row, not just
+    // this process's. That is correct for the supported deployment (one app container; see
+    // docker-compose.yml), where no other process can own a job at boot. If EventSnap is ever run
+    // with more than one replica, a booting replica would mark a peer's live workers `failed`.
+    // This is NOT merely wasteful — do not assume the epoch model contains it. Recovery re-arms the
+    // job at the SAME epoch, so the reaped-but-still-alive worker and the fresh one would BOTH hold
+    // that epoch; the guards carry no owner/lease token, so they share the same artifact paths and
+    // either can win the other's `finalize_job`. That can corrupt or delete the keepsake. Running
+    // more than one replica therefore requires an owner/lease/heartbeat on export_job first. That
+    // machinery is not worth building for a single-container app — so this is a documented
+    // CONSTRAINT, not a hidden assumption: do not scale this service horizontally as-is.
     match sqlx::query(
         "UPDATE export_job
          SET status = 'failed',
@@ -72,11 +87,7 @@ 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) {
     tokio::spawn(async move {
         let mut tick = tokio::time::interval(Duration::from_secs(3600));
         // Fire the first tick immediately, then hourly.

backend/src/services/mod.rs

@@ -1,7 +1,7 @@
 pub mod compression;
 pub mod config;
+pub mod disk;
 pub mod export;
-pub mod jobs;
 pub mod maintenance;
 pub mod rate_limiter;
 pub mod sse_tickets;

backend/src/services/rate_limiter.rs

@@ -24,7 +24,12 @@ impl RateLimiter {
 
     /// 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.
-    pub fn check_with_retry(&self, key: impl Into<String>, max: usize, window: Duration) -> Result<(), u64> {
+    pub fn check_with_retry(
+        &self,
+        key: impl Into<String>,
+        max: usize,
+        window: Duration,
+    ) -> Result<(), u64> {
         let now = Instant::now();
         let key = key.into();
         let mut map = self.windows.lock().unwrap();
@@ -71,14 +76,21 @@ impl RateLimiter {
     }
 }
 
-/// Extract the client IP from X-Forwarded-For (Caddy sets this) or fall back
-/// to a provided socket address string.
+/// Extract the client IP from X-Forwarded-For or fall back to a provided socket
+/// address string.
+///
+/// We take the **right-most** entry, not the left-most. Caddy is the sole ingress
+/// and the app port is only `expose`d (never published), so the last hop Caddy
+/// 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.
 pub fn client_ip(headers: &axum::http::HeaderMap, fallback: &str) -> String {
     headers
         .get("x-forwarded-for")
         .and_then(|v| v.to_str().ok())
-        .and_then(|s| s.split(',').next())
+        .and_then(|s| s.rsplit(',').next())
         .map(|s| s.trim().to_owned())
+        .filter(|s| !s.is_empty())
         .unwrap_or_else(|| fallback.to_owned())
 }
 
@@ -113,15 +125,67 @@ mod tests {
         assert!(rl.check("k", 1, w));
         assert!(!rl.check("k", 1, w));
         std::thread::sleep(Duration::from_millis(55));
-        assert!(rl.check("k", 1, w), "the slot should expire once the window passes");
+        assert!(
+            rl.check("k", 1, w),
+            "the slot should expire once the window passes"
+        );
+    }
+
+    /// `retry_after` is not a "some number in range" — it is the time until the oldest slot
+    /// in the window frees up, and it is surfaced to clients as the backoff they sleep for
+    /// (see `upload-queue.ts`). Asserting only `(1..=60)` spans the entire reachable domain
+    /// of a 60s window, so a hardcoded `Err(1)` would satisfy it while telling every client
+    /// to hammer the server a second later. Pin the actual value.
+    #[test]
+    fn retry_after_is_the_remaining_window() {
+        let rl = RateLimiter::new();
+
+        // The slot was consumed just now, so essentially the whole window remains.
+        // `as_secs()` truncates the sub-second remainder, so a 30s window reports 29.
+        let w30 = Duration::from_secs(30);
+        assert!(rl.check_with_retry("a", 1, w30).is_ok());
+        let a = rl.check_with_retry("a", 1, w30).unwrap_err();
+        assert_eq!(a, 29, "retry_after must be the remaining window, got {a}");
+
+        // A different window must yield a different retry_after: no single constant can
+        // satisfy both this and the assertion above.
+        let w10 = Duration::from_secs(10);
+        assert!(rl.check_with_retry("b", 1, w10).is_ok());
+        let b = rl.check_with_retry("b", 1, w10).unwrap_err();
+        assert_eq!(b, 9, "retry_after must scale with the window, got {b}");
     }
 
     #[test]
-    fn retry_after_is_between_one_and_window() {
+    fn retry_after_counts_down_as_the_window_elapses() {
         let rl = RateLimiter::new();
-        assert!(rl.check_with_retry("k", 1, MIN).is_ok());
-        let retry = rl.check_with_retry("k", 1, MIN).unwrap_err();
-        assert!((1..=60).contains(&retry), "retry_after {retry} out of range");
+        let w = Duration::from_secs(30);
+        assert!(rl.check_with_retry("k", 1, w).is_ok());
+        let first = rl.check_with_retry("k", 1, w).unwrap_err();
+
+        std::thread::sleep(Duration::from_millis(1200));
+        let second = rl.check_with_retry("k", 1, w).unwrap_err();
+
+        // A client that waits 1.2s must be told to wait ~1.2s less — otherwise the advertised
+        // backoff is a constant, not a deadline.
+        let shaved = first - second;
+        assert!(
+            (1..=2).contains(&shaved),
+            "1.2s of waiting must shorten the advertised backoff by ~1s (got {first} then {second})"
+        );
+    }
+
+    #[test]
+    fn retry_after_floors_at_one_second() {
+        let rl = RateLimiter::new();
+        let w = Duration::from_millis(800);
+        assert!(rl.check_with_retry("k", 1, w).is_ok());
+        let retry = rl.check_with_retry("k", 1, w).unwrap_err();
+        // The sub-second remainder truncates to 0; clients must never be told "retry in 0s"
+        // (that's a busy-loop). The `.max(1)` floor is what prevents it.
+        assert_eq!(
+            retry, 1,
+            "a sub-second remainder must floor to 1, got {retry}"
+        );
     }
 
     #[test]
@@ -133,10 +197,75 @@ mod tests {
         assert!(rl.check("k", 1, MIN), "clear() must free the window");
     }
 
+    /// `prune()` is a memory-leak guard: without it a long-lived process keeps one HashMap
+    /// entry per IP that ever connected. Nothing in the public API observes the map size, so
+    /// the only way to catch a no-op body (`fn prune(&self) {}`) is to look at the map — the
+    /// tests module can see the private field.
     #[test]
-    fn client_ip_prefers_first_forwarded_for_entry() {
+    fn prune_drops_keys_whose_windows_have_fully_expired() {
+        let rl = RateLimiter::new();
+
+        // A key whose only timestamp is older than the 24h ceiling. We can't sleep for a day,
+        // so backdate the Instant directly.
+        let ancient = Instant::now()
+            .checked_sub(Duration::from_secs(25 * 60 * 60))
+            .expect("backdating an Instant by 25h");
+        rl.windows
+            .lock()
+            .unwrap()
+            .insert("stale".to_string(), vec![ancient]);
+
+        // ...alongside a key that is still inside its window.
+        assert!(rl.check("live", 5, MIN));
+        assert_eq!(rl.windows.lock().unwrap().len(), 2);
+
+        rl.prune();
+
+        let map = rl.windows.lock().unwrap();
+        assert!(
+            !map.contains_key("stale"),
+            "prune() must drop keys whose timestamps have all expired"
+        );
+        assert!(
+            map.contains_key("live"),
+            "prune() must keep keys that still have live timestamps"
+        );
+        assert_eq!(map.len(), 1, "exactly one key should survive the prune");
+    }
+
+    #[test]
+    fn prune_does_not_reset_a_live_window() {
+        // The counterpart to the test above: pruning must reclaim memory, never quota. If
+        // prune() dropped live keys, every background sweep would hand attackers a fresh
+        // budget.
+        let rl = RateLimiter::new();
+        assert!(rl.check("k", 1, MIN));
+        assert!(!rl.check("k", 1, MIN));
+
+        rl.prune();
+
+        assert!(
+            !rl.check("k", 1, MIN),
+            "prune() must not clear a window that is still active"
+        );
+    }
+
+    #[test]
+    fn client_ip_takes_rightmost_forwarded_for_entry() {
+        // The right-most entry is the hop our trusted proxy (Caddy) appended.
         let mut h = HeaderMap::new();
-        h.insert("x-forwarded-for", "203.0.113.7, 10.0.0.1".parse().unwrap());
+        h.insert("x-forwarded-for", "10.0.0.1, 203.0.113.7".parse().unwrap());
+        assert_eq!(client_ip(&h, "fallback"), "203.0.113.7");
+    }
+
+    #[test]
+    fn client_ip_ignores_spoofed_leftmost_entry() {
+        // A client prepending a fake IP to dodge throttles must not win.
+        let mut h = HeaderMap::new();
+        h.insert(
+            "x-forwarded-for",
+            "1.2.3.4, 9.9.9.9, 203.0.113.7".parse().unwrap(),
+        );
         assert_eq!(client_ip(&h, "fallback"), "203.0.113.7");
     }
 
@@ -151,4 +280,14 @@ mod tests {
     fn client_ip_falls_back_when_header_absent() {
         assert_eq!(client_ip(&HeaderMap::new(), "127.0.0.1"), "127.0.0.1");
     }
+
+    #[test]
+    fn client_ip_falls_back_on_trailing_comma_empty_entry() {
+        // A trailing comma leaves an empty right-most segment after trimming; the
+        // `.filter(!is_empty)` must reject it and fall through to the fallback
+        // rather than returning "" (which would collapse callers into one bucket).
+        let mut h = HeaderMap::new();
+        h.insert("x-forwarded-for", "203.0.113.7, ".parse().unwrap());
+        assert_eq!(client_ip(&h, "127.0.0.1"), "127.0.0.1");
+    }
 }

backend/src/services/sse_tickets.rs

@@ -31,6 +31,13 @@ impl SseTicketStore {
         }
     }
 
+    /// Drop every outstanding ticket. Used by the e2e TRUNCATE endpoint: tickets are bound to a
+    /// session token hash, and TRUNCATE deletes the sessions out from under them, so anything left
+    /// here is a dangling reference to a user that no longer exists.
+    pub fn clear(&self) {
+        self.inner.lock().unwrap().clear();
+    }
+
     /// Mint a new ticket bound to the caller's session (identified by token hash).
     pub fn issue(&self, token_hash: String) -> String {
         let ticket = random_ticket();
@@ -83,7 +90,11 @@ mod tests {
         let ticket = store.issue("hash-1".into());
         assert_eq!(store.consume(&ticket).as_deref(), Some("hash-1"));
         // Single-use: a replay of the same ticket is rejected.
-        assert_eq!(store.consume(&ticket), None, "a consumed ticket must not be reusable");
+        assert_eq!(
+            store.consume(&ticket),
+            None,
+            "a consumed ticket must not be reusable"
+        );
     }
 
     #[test]
@@ -124,6 +135,10 @@ mod tests {
                     .expect("host uptime should exceed the ticket TTL"),
             },
         );
-        assert_eq!(store.consume(&stale), None, "an expired ticket must not authenticate");
+        assert_eq!(
+            store.consume(&stale),
+            None,
+            "an expired ticket must not authenticate"
+        );
     }
 }

backend/src/state.rs

@@ -3,6 +3,8 @@ use tokio::sync::broadcast;
 
 use crate::config::AppConfig;
 use crate::services::compression::CompressionWorker;
+use crate::services::config::ConfigCache;
+use crate::services::disk::DiskCache;
 use crate::services::rate_limiter::RateLimiter;
 use crate::services::sse_tickets::SseTicketStore;
 
@@ -31,13 +33,27 @@ pub struct AppState {
     pub compression: CompressionWorker,
     pub rate_limiter: RateLimiter,
     pub sse_tickets: SseTicketStore,
+    /// In-memory cache in front of the `config` table. Reads go through here; the
+    /// admin PATCH handler and the test reseed invalidate it after committing.
+    pub config_cache: ConfigCache,
+    /// Cached total/free bytes for the media filesystem (quota + admin stats).
+    pub disk_cache: DiskCache,
 }
 
 impl AppState {
     pub fn new(pool: PgPool, config: AppConfig) -> Self {
-        let (sse_tx, _) = broadcast::channel(256);
-        let compression =
-            CompressionWorker::new(pool.clone(), config.media_path.clone(), 2, sse_tx.clone());
+        // Broadcast buffer for live SSE fan-out. Sized to absorb a burst (e.g. many
+        // uploads landing at once during a busy moment) before a slow consumer lags and
+        // has to `resync`. The resync path is a correctness backstop, not the happy path —
+        // a roomier buffer keeps ~1000 concurrent clients from all resyncing at once.
+        let (sse_tx, _) = broadcast::channel(1024);
+        let compression = CompressionWorker::new(
+            pool.clone(),
+            config.media_path.clone(),
+            config.compression_concurrency,
+            sse_tx.clone(),
+        );
+        let config_cache = ConfigCache::new(pool.clone());
         Self {
             pool,
             config,
@@ -45,6 +61,8 @@ impl AppState {
             compression,
             rate_limiter: RateLimiter::new(),
             sse_tickets: SseTicketStore::new(),
+            config_cache,
+            disk_cache: DiskCache::new(),
         }
     }
 }

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

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

backend/tests/export_epoch.rs

@@ -0,0 +1,435 @@
+//! DB-backed integration tests for the export epoch state machine (migration 014).
+//!
+//! These run against a REAL Postgres: `#[sqlx::test]` creates a throwaway database per test and
+//! runs `backend/migrations/` into it, so the schema, the enums, the `UNIQUE (event_id, type)`
+//! constraint and the `export_current` view are the production ones — not a mock.
+//!
+//! THE INVARIANT, from migration 014:
+//!
+//!     An export is downloadable IFF
+//!         event.export_released_at IS NOT NULL
+//!     AND export_job.epoch = event.export_epoch
+//!     AND export_job.status = 'done'
+//!
+//! Readiness is DERIVED (the `export_current` view), never stored. Every test below pins one leg of
+//! that invariant with the exact SQL `src/` executes (see `tests/common/mod.rs`).
+
+mod common;
+
+use common::*;
+use sqlx::PgPool;
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 1. Epoch monotonicity
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// Release, reopen and re-release each bump `export_epoch`, and `RETURNING export_epoch` hands the
+/// caller the POST-increment value.
+///
+/// PREVENTS: a worker born with the PRE-increment epoch. It would be inert from the instant it
+/// started — every one of its writes is `epoch`-guarded, so `claim_job`/`finalize_job` would match
+/// nothing, the job row would sit at `pending` 0% forever with no live worker, and the host's
+/// download button would spin and then 404. The keepsake would never be built at all.
+#[sqlx::test]
+async fn release_returns_post_increment_epoch(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    assert_eq!(
+        event_epoch(&pool, event_id).await,
+        0,
+        "a fresh event starts at epoch 0"
+    );
+
+    let released = release_gallery(&pool, "wedding")
+        .await
+        .expect("release claims the event");
+    assert_eq!(
+        released, 1,
+        "RETURNING must give the epoch AFTER the +1, not before"
+    );
+    assert_eq!(
+        event_epoch(&pool, event_id).await,
+        released,
+        "worker's epoch == event's epoch"
+    );
+
+    // The jobs armed by the release carry exactly that epoch — this is what makes the worker's
+    // guarded writes match.
+    for t in ["zip", "html"] {
+        let (status, epoch, _) = job_row(&pool, event_id, t).await.expect("job armed");
+        assert_eq!(status, "pending");
+        assert_eq!(
+            epoch, released,
+            "{t} job must be armed at the epoch the worker was born with"
+        );
+    }
+}
+
+/// Epoch is strictly monotonic across the whole release/reopen/re-release cycle, and a second
+/// release attempt while already released is rejected WITHOUT bumping.
+///
+/// PREVENTS: epoch reuse. If a reopen could return the event to an epoch some old `done` row still
+/// carries, a retired keepsake — one that a guest asked to be taken down from — would silently
+/// become downloadable again.
+#[sqlx::test]
+async fn epoch_is_strictly_monotonic_across_reopen(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+
+    assert_eq!(release_gallery(&pool, "wedding").await, Some(1));
+
+    // A duplicate release is a no-op (`WHERE export_released_at IS NULL`) and must NOT bump.
+    assert_eq!(
+        release_gallery(&pool, "wedding").await,
+        None,
+        "already released"
+    );
+    assert_eq!(
+        event_epoch(&pool, event_id).await,
+        1,
+        "a rejected release must not move the epoch"
+    );
+
+    // Reopen retires the generation with ONE write.
+    assert_eq!(open_event(&pool, "wedding").await, 1);
+    assert_eq!(event_epoch(&pool, event_id).await, 2, "reopen bumps");
+
+    // And re-releasing bumps again — never back to 1.
+    assert_eq!(
+        release_gallery(&pool, "wedding").await,
+        Some(3),
+        "re-release bumps again"
+    );
+    assert_eq!(event_epoch(&pool, event_id).await, 3);
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 2. A retired-epoch worker is inert
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// A worker holding a retired epoch cannot write anything anybody can see: once the rows have been
+/// re-armed at a newer epoch, its `update_progress` and `finalize_job` both match 0 rows, and
+/// `export_current` never exposes its output.
+///
+/// PREVENTS: the classic lost race — a slow worker from BEFORE a takedown finishing afterwards and
+/// publishing an archive that still contains the photo a guest asked to have removed. "Please take
+/// my photo out" is the one request that most needs to reach the keepsake, and the keepsake is the
+/// artifact people keep forever.
+#[sqlx::test]
+async fn retired_epoch_worker_writes_are_no_ops(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let old_epoch = release_gallery(&pool, "wedding").await.unwrap();
+
+    // Worker A is born at epoch 1 and claims the ZIP.
+    assert!(
+        claim_job(&pool, event_id, "zip", old_epoch).await,
+        "worker A wins its claim"
+    );
+    assert!(
+        update_progress(&pool, event_id, "zip", old_epoch, 40).await,
+        "still live at 40%"
+    );
+
+    // ── A takedown lands mid-export: `invalidate_and_arm(Affects::Both)` bumps and re-arms. ──
+    let (_, _, new_epoch) = bump_epoch(&pool, "wedding")
+        .await
+        .expect("bump on a released event");
+    assert_eq!(new_epoch, old_epoch + 1);
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, new_epoch, &["zip", "html"]).await;
+    drop(conn);
+
+    // Worker A is now INERT BY CONSTRUCTION. Every write is guarded on its own birth epoch.
+    assert!(
+        !update_progress(&pool, event_id, "zip", old_epoch, 90).await,
+        "the liveness check must report `false` so worker A stops grinding through the gallery"
+    );
+    assert!(
+        !finalize_job(&pool, event_id, "zip", old_epoch, "exports/Gallery.1.zip").await,
+        "worker A's finalize MUST affect 0 rows — this is the write that would have published a \
+         keepsake still containing the taken-down photo"
+    );
+
+    // The re-armed row is untouched by the loser: still pending at the LIVE epoch, waiting for the
+    // fresh worker. (If worker A had won, this row would read `done` at epoch 1.)
+    let (status, epoch, file_path) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!((status.as_str(), epoch), ("pending", new_epoch));
+    assert_eq!(
+        file_path, None,
+        "the loser's file_path must never be recorded"
+    );
+
+    // And nothing is downloadable — not the stale archive, not anything.
+    assert_eq!(downloadable(&pool, event_id, "zip").await, None);
+}
+
+/// The documented, deliberate nuance in `claim_job`: after a bare `open_event` (which writes
+/// NOTHING to `export_job` — that is the point of the design), a worker at the old epoch still WINS
+/// its claim and can still write `done`. That is wasted work, not incorrectness: retirement is
+/// enforced at READ time. `export_current` must refuse to expose the row.
+///
+/// PREVENTS: someone "optimising" `claim_job` into a cross-table `EXISTS (SELECT ... FROM event)`
+/// guard — the exact unsound guard migration 014 removed (under READ COMMITTED, a blocked UPDATE
+/// re-evaluates same-row predicates but answers other-table subqueries from a stale snapshot).
+/// This test pins the read-time enforcement so the write-time guard is never re-added.
+#[sqlx::test]
+async fn reopen_retires_at_read_time_not_write_time(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let epoch = release_gallery(&pool, "wedding").await.unwrap();
+
+    assert!(claim_job(&pool, event_id, "zip", epoch).await);
+
+    // Host reopens uploads. No export_job row is touched.
+    assert_eq!(open_event(&pool, "wedding").await, 1);
+
+    // The in-flight worker's row-local writes still match — it was never told to stop.
+    assert!(
+        finalize_job(&pool, event_id, "zip", epoch, "exports/Gallery.1.zip").await,
+        "documented: the claim/finalize is guarded on the JOB row's epoch, not the event's"
+    );
+    let (status, _, _) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!(status, "done", "the row really does say done");
+
+    // …and yet it is invisible. `export_current` requires the event to be released AND the epochs to
+    // match; the reopen broke both. A worker at a dead epoch writes a row nobody can see.
+    assert!(!in_export_current(&pool, event_id, "zip").await);
+    assert_eq!(
+        downloadable(&pool, event_id, "zip").await,
+        None,
+        "a reopened event must serve NO keepsake, however finished the job row looks"
+    );
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 3. `export_current` exactness (table-driven)
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// The view is the ONE definition of "downloadable". Released + `done` + matching epoch ⇒ present;
+/// break ANY single leg ⇒ absent. Nothing else may make it appear or disappear.
+///
+/// PREVENTS, leg by leg:
+///  * `released` — serving a keepsake for an event whose uploads are still open, i.e. an archive
+///    missing every photo taken after the snapshot.
+///  * `done` — handing out a half-written ZIP (a corrupt keepsake, downloaded once, kept forever).
+///  * `epoch` — the retired-generation download: the 404-forever keepsake, or worse, the archive
+///    still containing content that was taken down.
+#[sqlx::test]
+async fn export_current_is_exactly_the_invariant(pool: PgPool) {
+    // (name, released?, status, job epoch offset from the event epoch, expected visible)
+    let cases: &[(&str, bool, &str, i64, bool)] = &[
+        ("released + done + current epoch", true, "done", 0, true),
+        (
+            "NOT released (done, epoch matches)",
+            false,
+            "done",
+            0,
+            false,
+        ),
+        ("NOT done: pending", true, "pending", 0, false),
+        ("NOT done: running", true, "running", 0, false),
+        ("NOT done: failed", true, "failed", 0, false),
+        ("stale epoch (done, released)", true, "done", -1, false),
+        ("future epoch (done, released)", true, "done", 1, false),
+        (
+            "migration-014 retired sentinel epoch -1",
+            true,
+            "done",
+            -2,
+            false,
+        ),
+    ];
+
+    for (i, (name, released, status, offset, expect_visible)) in cases.iter().enumerate() {
+        let slug = format!("case{i}");
+        let event_id = seed_event(&pool, &slug).await;
+
+        // Get the event to a known epoch (1) either by releasing it, or — for the unreleased case —
+        // by releasing and reopening, which leaves it unreleased at a non-zero epoch.
+        let event_epoch_now = if *released {
+            release_gallery(&pool, &slug).await.unwrap()
+        } else {
+            release_gallery(&pool, &slug).await.unwrap();
+            open_event(&pool, &slug).await;
+            event_epoch(&pool, event_id).await
+        };
+
+        // Plant a single ZIP job row in the exact state under test. `-2` encodes "the sentinel the
+        // migration stamps on retired rows", which must never equal a non-negative event epoch.
+        // (Clear the rows the release armed first — `UNIQUE (event_id, type)`.)
+        sqlx::query("DELETE FROM export_job WHERE event_id = $1")
+            .bind(event_id)
+            .execute(&pool)
+            .await
+            .expect("clear armed jobs");
+
+        let job_epoch = if *offset == -2 {
+            -1
+        } else {
+            event_epoch_now + offset
+        };
+        sqlx::query(
+            "INSERT INTO export_job (event_id, type, status, progress_pct, epoch, file_path)
+             VALUES ($1, 'zip', $2::export_status, 100, $3, 'exports/Gallery.zip')",
+        )
+        .bind(event_id)
+        .bind(*status)
+        .bind(job_epoch)
+        .execute(&pool)
+        .await
+        .expect("plant job row");
+
+        let visible = downloadable(&pool, event_id, "zip").await.is_some();
+        assert_eq!(
+            visible, *expect_visible,
+            "export_current exactness violated for case: {name} \
+             (released={released}, status={status}, job_epoch={job_epoch}, event_epoch={event_epoch_now})"
+        );
+    }
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// 4. The ViewerOnly ZIP carry-forward
+// ─────────────────────────────────────────────────────────────────────────────
+
+/// Branch A — the ZIP is `done` at the outgoing epoch: the carry-forward re-stamps it to the new
+/// epoch (rows_affected = 1), so only the HTML viewer is rebuilt and the finished ZIP stays
+/// downloadable throughout.
+///
+/// PREVENTS: rebuilding a multi-GB archive because someone deleted a comment. The ZIP holds media,
+/// not comments — a needless rebuild would 404 the photo download for minutes to change nothing
+/// inside it.
+#[sqlx::test]
+async fn viewer_only_carries_a_done_zip_forward(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let e1 = release_gallery(&pool, "wedding").await.unwrap();
+
+    // Both halves finish at epoch 1 — the keepsake is live.
+    for t in ["zip", "html"] {
+        assert!(claim_job(&pool, event_id, t, e1).await);
+        assert!(finalize_job(&pool, event_id, t, e1, &format!("exports/{t}.{e1}.zip")).await);
+    }
+    let zip_file = downloadable(&pool, event_id, "zip")
+        .await
+        .expect("zip is live");
+
+    // ── A comment is moderated: invalidate_and_arm(Affects::ViewerOnly). ──
+    let (_, _, e2) = bump_epoch(&pool, "wedding").await.unwrap();
+    let carried = carry_zip_forward(&pool, event_id, e2).await;
+    assert!(
+        carried,
+        "a `done` ZIP at epoch-1 MUST be carried forward (rows_affected == 1)"
+    );
+
+    // Only the viewer is re-armed…
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, e2, &["html"]).await;
+    drop(conn);
+
+    // …and the ZIP is STILL DOWNLOADABLE, at the new epoch, pointing at the same, unrenamed file.
+    let (status, epoch, _) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!(
+        (status.as_str(), epoch),
+        ("done", e2),
+        "the ZIP row rode the epoch bump"
+    );
+    assert_eq!(
+        downloadable(&pool, event_id, "zip").await,
+        Some(zip_file),
+        "the carried archive must never stop being served — same file, new epoch"
+    );
+
+    // The viewer, meanwhile, is correctly retired and pending a rebuild.
+    assert_eq!(job_row(&pool, event_id, "html").await.unwrap().0, "pending");
+    assert_eq!(downloadable(&pool, event_id, "html").await, None);
+}
+
+/// Branch B — THE BUG WE JUST FIXED. If the ZIP is still `pending`/`running` when the comment is
+/// moderated (which is MINUTES for a real multi-GB gallery, and deleting a comment right after
+/// release is an utterly ordinary thing to do), the carry-forward matches NOTHING
+/// (rows_affected = 0) — so the caller must NOT assume it carried, and must re-arm the ZIP too.
+///
+/// PREVENTS: the stranded ZIP. Blindly re-arming only the viewer would leave the ZIP row at the
+/// retired epoch; the in-flight worker then finishes and writes `done` at an epoch `export_current`
+/// no longer matches, nothing ever re-arms it, and `GET /export/zip` 404s FOREVER — a keepsake the
+/// couple paid for that simply never appears, short of a reboot.
+#[sqlx::test]
+async fn viewer_only_carry_forward_matches_nothing_when_zip_unfinished(pool: PgPool) {
+    for zip_state in ["pending", "running"] {
+        let slug = format!("wedding-{zip_state}");
+        let event_id = seed_event(&pool, &slug).await;
+        let e1 = release_gallery(&pool, &slug).await.unwrap();
+
+        // The ZIP worker is still going; only the viewer has finished.
+        if zip_state == "running" {
+            assert!(claim_job(&pool, event_id, "zip", e1).await);
+        }
+        assert!(claim_job(&pool, event_id, "html", e1).await);
+        assert!(finalize_job(&pool, event_id, "html", e1, "exports/Memories.1.zip").await);
+
+        // ── The comment is moderated. ──
+        let (_, _, e2) = bump_epoch(&pool, &slug).await.unwrap();
+        let carried = carry_zip_forward(&pool, event_id, e2).await;
+
+        assert!(
+            !carried,
+            "a {zip_state} ZIP has nothing to carry forward — the UPDATE must affect 0 rows \
+             (its `status = 'done'` predicate is the whole precondition)"
+        );
+
+        // The carry-forward's OWN result decides. It didn't match ⇒ rebuild the ZIP as well.
+        let types: &[&str] = if carried { &["html"] } else { &["zip", "html"] };
+        let mut conn = pool.acquire().await.unwrap();
+        enqueue_types_at_epoch(&mut conn, event_id, e2, types).await;
+        drop(conn);
+
+        // THE ASSERTION THAT WOULD HAVE CAUGHT THE BUG: the ZIP must not be stranded at the dead
+        // epoch. It is re-armed at the live one, so a fresh worker will actually build it.
+        let (status, epoch, _) = job_row(&pool, event_id, "zip").await.unwrap();
+        assert_eq!(
+            (status.as_str(), epoch),
+            ("pending", e2),
+            "the unfinished ZIP MUST be re-armed at the new epoch, not left stranded at {e1}"
+        );
+
+        // Even if the old in-flight worker now "finishes", it is inert and cannot resurrect itself.
+        assert!(!finalize_job(&pool, event_id, "zip", e1, "exports/Gallery.1.zip").await);
+        assert_eq!(downloadable(&pool, event_id, "zip").await, None);
+    }
+}
+
+/// The re-arm upsert must never clobber the archive it just carried forward.
+///
+/// `enqueue_types_at_epoch`'s `WHERE export_job.status <> 'done' OR export_job.epoch <> EXCLUDED.epoch`
+/// is the "startup recovery must not clobber a good half" rule, expressed as the readiness predicate
+/// itself. PREVENTS: boot recovery resetting a perfectly good, downloadable ZIP back to `pending`
+/// and making the keepsake 404 while it needlessly rebuilds.
+#[sqlx::test]
+async fn enqueue_preserves_a_done_half_at_the_current_epoch(pool: PgPool) {
+    let event_id = seed_event(&pool, "wedding").await;
+    let e1 = release_gallery(&pool, "wedding").await.unwrap();
+
+    // The ZIP finished; the HTML worker was killed mid-flight (crash) and sits at `running`.
+    assert!(claim_job(&pool, event_id, "zip", e1).await);
+    assert!(finalize_job(&pool, event_id, "zip", e1, "exports/Gallery.1.zip").await);
+    assert!(claim_job(&pool, event_id, "html", e1).await);
+
+    // Boot recovery re-arms both types at the SAME epoch.
+    let mut conn = pool.acquire().await.unwrap();
+    enqueue_types_at_epoch(&mut conn, event_id, e1, &["zip", "html"]).await;
+    drop(conn);
+
+    // The good half survives untouched…
+    let (status, epoch, file_path) = job_row(&pool, event_id, "zip").await.unwrap();
+    assert_eq!(
+        (status.as_str(), epoch),
+        ("done", e1),
+        "a done half at the live epoch is preserved"
+    );
+    assert_eq!(
+        file_path.as_deref(),
+        Some("exports/Gallery.1.zip"),
+        "file_path not nulled"
+    );
+    assert!(downloadable(&pool, event_id, "zip").await.is_some());
+
+    // …and only the missing half is re-armed.
+    assert_eq!(job_row(&pool, event_id, "html").await.unwrap().0, "pending");
+}

backend/tests/upload_concurrency.rs

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

docker-compose.dev.yml

@@ -6,3 +6,36 @@ services:
   db:
     ports:
       - "5432:5432"
+  app:
+    # Relax the production secret guard for local dev — the dev sentinel JWT_SECRET
+    # 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

@@ -14,6 +14,10 @@ services:
       interval: 5s
       timeout: 5s
       retries: 10
+    deploy:
+      resources:
+        limits:
+          memory: 512M
 
   app:
     build:
@@ -21,13 +25,42 @@ services:
       dockerfile: Dockerfile
     restart: unless-stopped
     env_file: .env
+    environment:
+      # 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
     volumes:
       - media_data:/media
+      # Export archives live OUTSIDE /media so the public media ServeDir can't
+      # serve them — downloads go only through the ticket-gated handler.
+      - exports_data:/exports
     expose:
       - "3000"
+    healthcheck:
+      # 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
+      start_period: 20s
+    deploy:
+      resources:
+        limits:
+          # Bounds a runaway ffmpeg transcode (large uploads, 2 workers) so it can't
+          # OOM the single box and take down Postgres.
+          memory: 1G
 
   frontend:
     build:
@@ -35,14 +68,36 @@ services:
       dockerfile: Dockerfile
     restart: unless-stopped
     env_file: .env
+    environment:
+      # adapter-node behind Caddy TLS needs the public origin for CSRF checks on
+      # POST form actions — without it they fail only in production.
+      ORIGIN: "https://${DOMAIN}"
     depends_on:
       - app
     expose:
       - "3001"
+    healthcheck:
+      # 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
+      start_period: 15s
+    deploy:
+      resources:
+        limits:
+          memory: 256M
 
   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"
@@ -50,10 +105,17 @@ services:
       - ./Caddyfile:/etc/caddy/Caddyfile:ro
       - caddy_data:/data
     depends_on:
-      - app
-      - frontend
+      app:
+        condition: service_healthy
+      frontend:
+        condition: service_healthy
+    deploy:
+      resources:
+        limits:
+          memory: 256M
 
 volumes:
   postgres_data:
   media_data:
+  exports_data:
   caddy_data:

docs/SECURITY-BACKLOG.md

@@ -51,15 +51,28 @@ item below is tagged with its **current status in `main`**:
 
 ## ✅ Fixed in main since the audit (for the record)
 
-These audit findings are present in `main` today (verified 2026-06-30): event-scoped social
-handlers (cross-event authz), server-side MIME/ext allowlist on upload, recovery-PIN lockout
-backoff, unspoofable client IP in the rate limiter, effective JWT production-secret guard, DB port
-no longer publicly exposed, container healthchecks, bcrypt offloaded via `spawn_blocking`,
-bounded compression concurrency (semaphore), bounded feed queries (`LIMIT ≤ 100`), and the
-viewport-fit / reduced-motion / aria a11y pass. **New since the audit:** an image-decode
-decompression-bomb cap (`image::Limits` 12000×12000 / 256 MiB) ported into
+These audit findings are present in `main` today (verified 2026-06-30): server-side MIME/ext
+allowlist on upload, recovery-PIN lockout backoff, DB port no longer publicly exposed, bcrypt
+offloaded via `spawn_blocking`, bounded compression concurrency (semaphore), bounded feed queries
+(`LIMIT ≤ 100`), and the viewport-fit / reduced-motion / aria a11y pass. An image-decode
+decompression-bomb cap (`image::Limits` 12000×12000 / 256 MiB) lives in
 `backend/src/services/compression.rs`.
 
+**Fixed in the 2026-07 review pass** (previously *claimed* fixed here but were not — corrected):
+- **Effective JWT production-secret guard** — `APP_ENV=production` is now set for the app service,
+  and `config.rs::validate_secrets` rejects any placeholder-ish `JWT_SECRET`/`ADMIN_PASSWORD_HASH`
+  (not just the exact dev sentinel) and enforces `len ≥ 32` unconditionally in prod.
+- **Unspoofable client IP in the rate limiter** — `client_ip` now takes the right-most
+  `X-Forwarded-For` entry (the hop Caddy appends), so a client-supplied left-most value is ignored.
+- **Live role/ban re-check** — the auth extractor re-reads the user row and trusts the DB `role`
+  and `is_banned` flag rather than the JWT claim, so a demote/ban takes effect immediately (no
+  30-day token window). Bans are enforced on write handlers + the host/admin extractors, preserving
+  the documented read-only access for banned guests (USER_JOURNEYS §10); demoted hosts lose host
+  powers at once.
+- **Container healthchecks** — `app` and `frontend` now have healthchecks and Caddy waits on
+  `service_healthy`.
+- **Event-scoped `ban_user`** — the ban UPDATE is now scoped by `event_id` like its siblings.
+
 ## 🅲 Consciously won't-fix at ~100-guest single-box scale
 
 Diminishing returns vs. the deployment's actual threat model. Revisit only if the scale or
@@ -71,6 +84,12 @@ tenancy model changes.
 - Performance micro-indexes (`idx_like_user_upload`, comment pagination index) — current queries
   are sub-ms at this row count.
 - Optimistic-like in-flight guard, ownership-snapshot-at-mount, assorted copy tweaks — UX polish.
+- **Mid-session ban does not tear down an already-open SSE stream.** The live-ban check lives in the
+  `AuthUser` extractor, but the stream authenticates via ticket→session (`handlers/sse.rs::stream`),
+  so a user banned while connected keeps receiving broadcast events until their stream drops. New
+  tickets *are* blocked (`issue_ticket` uses `AuthUser`), so they cannot reconnect. Low blast radius
+  (read-only feed events, no re-subscribe); tearing live streams down would need a per-session
+  broadcast filter. Revisit only if bans must take effect within seconds.
 
 ## By-design notes (audit branch's signed-media model — see DECISION-media-auth.md)
 

docs/USER_JOURNEYS.md

@@ -129,30 +129,49 @@ the Host can clean up later).
    viewer). Progress is visible in the Admin dashboard's Export tab; SSE
    `export-progress` keeps it live; `export-available` notifies all guests when ready.
 5. **Nutzerverwaltung** — search users; per-user controls:
-   - **Sperren** opens a confirmation modal with a checkbox "Uploads aus der Galerie
-     ausblenden" — Host chooses whether to hide the user's existing uploads or leave them
-     visible. Submitting calls `POST /host/users/{id}/ban` with `hide_uploads`.
-   - **Entsperren** lifts the ban.
-   - **Host** promotes a guest to host.
-   - **Degradieren** — visible on Host rows. A Host can demote *other* Hosts back to
-     guest (planned). The button is hidden on the Host's own row to prevent self-lockout;
-     only an Admin can demote themselves out of moderation. Admins see Degradieren on
-     every Host row.
-   - **PIN zurücksetzen** (planned) — generates a new PIN and shows it once in a modal.
-     See journey §4. Hosts see this on Guest rows only; Admins see it on Guest + Host
-     rows.
+   - **Sperren** opens a confirmation modal. Banning **always hides** the user's existing
+     uploads (a banned user's content is "gone" everywhere) — there is no opt-out. Submitting
+     calls `POST /host/users/{id}/ban` (no body).
+   - **Entsperren** lifts the ban. Same authority boundary as ban (below): a plain Host may
+     only unban Guests; only an Admin may unban a Host.
+   - **Host** promotes a guest to host (Hosts and Admins may do this).
+   - **Degradieren** — demote a Host back to guest. **Only an Admin may change a Host's
+     role.** A plain Host may *not* demote a peer Host: doing so would let them then ban or
+     PIN-reset (→ `/recover` account-takeover) that ex-peer, since those guards key off the
+     target's *current* role. So the backend rejects it (403) and the button is hidden for
+     non-admin Hosts. Nobody may change their own role (self-lockout / self-escalation guard),
+     and Admins are un-demotable and un-bannable by anyone. (This tightens an earlier
+     "Hosts may demote other Hosts" design — see the F1 security fix.)
+   - **Sperren / PIN zurücksetzen** — a plain Host may act on Guests only; an Admin may act on
+     Guests + Hosts; nobody may act on an Admin. The buttons are hidden where they'd 403.
+     PIN reset generates a new PIN, shows it once in a modal, and revokes the target's
+     existing sessions (forcing re-auth with the new PIN). See journey §4.
 6. **Deleting content** — Host can delete any upload or comment via the moderation routes
    (`DELETE /host/upload/{id}`, `DELETE /host/comment/{id}`). On mobile this is also
    reachable by long-pressing the content (planned, see §15).
 
 ## 10. Banned-guest experience
 
-1. The banned user's next authenticated request returns HTTP 403 with a clear message
-   ("Du bist gesperrt.").
-2. They can still browse the read-only feed (and download the export once it's released).
-3. They cannot upload, like, or comment.
-4. If `hide_uploads` was set on the ban, their existing uploads are filtered out of the
-   feed for everyone (the `v_feed` view already enforces this).
+1. The ban takes effect immediately on the banned user's existing session — the auth
+   layer re-reads the live `is_banned` flag on every request rather than trusting the
+   JWT, so there's no 30-day token-lifetime window.
+2. Their next authenticated *write* request returns HTTP 403 with a clear message
+   ("Du bist gesperrt."). Ban enforcement lives on the write handlers and the
+   host/admin extractors, not the base auth extractor.
+3. They can still browse the read-only feed (and download the export once it's released).
+   Their sessions are **not** revoked — this is a read-only ban, not a logout. Their own
+   live SSE stream is dropped by the `is_banned` revalidation (no live pushes), but plain
+   feed reads still work.
+4. They cannot upload, like, or comment; a banned host also loses all host/admin
+   actions (including unbanning themselves).
+5. Banning **always hides**: the user's existing uploads are filtered out of the feed for
+   everyone (`v_feed`, `find_visible_media`, and the export query all enforce
+   `is_banned = FALSE`), and a live `user-hidden` SSE event evicts their cards from every
+   open feed + the diashow without a reload. A client that was offline/disconnected during
+   the live event doesn't miss the eviction: `uploads_hidden_at` is stamped at ban time
+   (migration 013) and the reconnect delta (`GET /feed/delta`) returns the banned users in
+   `hidden_user_ids`, so the feed and diashow replay the eviction on the next reconnect —
+   the projector-missed-the-live-push case is exactly why this exists.
 
 ## 11. Admin — instance configuration
 
@@ -174,7 +193,18 @@ the Host can clean up later).
 ## 12. Releasing the export and downloading
 
 1. Host (or Admin) taps **Galerie freigeben** in the dashboard.
-2. Server sets `event.export_released_at` and enqueues two background jobs.
+2. Server sets `event.export_released_at`, locks uploads, **bumps `event.export_epoch`**, and
+   enqueues two background jobs — all in ONE transaction (workers spawn after it commits, so a
+   client disconnecting mid-request can never leave the event released with no export to build).
+
+   The **epoch** is the whole generation model (migration 014). It is bumped in the same UPDATE as
+   any change to `export_released_at` — release and reopen are its only writers — and each
+   `export_job` row carries a copy of the epoch it was enqueued for. An export is downloadable
+   **iff** `released AND job.epoch = event.export_epoch AND job.status = 'done'`. Readiness is
+   therefore *derived*, never stored: it cannot drift, and a worker whose epoch has been retired
+   (by a reopen, a re-release, or a takedown) is inert — anything it writes is simply invisible.
+   A reopen retires the current keepsake instantly, which is why a reopened event serves no export
+   until the host releases again.
 3. ZIP job: streams `Gallery.zip` (`Photos/` + `Videos/`, full-quality originals) directly
    to disk via `async-zip`. Progress updates via `export-progress` SSE.
 4. HTML-viewer job: copies the pre-built viewer assets from
@@ -182,6 +212,11 @@ the Host can clean up later).
    `include_dir!`), generates `data.json` from the database, processes `_thumb`/`_full`
    variants for each upload, and assembles `Memories.zip`.
 5. Both jobs complete → server broadcasts `export-available` SSE.
+   **Takedowns:** if a host deletes an upload (or a comment) while the gallery is released, the
+   epoch is bumped and the keepsake is REGENERATED without it. Otherwise a photo removed on request
+   would live on forever in the already-generated archive — the one place it most needs to be gone.
+   The download 404s for the few seconds it takes to rebuild, which is the correct answer: serving
+   the old archive would serve the deleted photo.
 6. Any user opens `/export`:
    - Before release: friendly "Export not yet available" banner.
    - During generation: progress bars per artifact.

e2e/.prettierignore

@@ -0,0 +1,4 @@
+node_modules/
+playwright-report/
+test-results/
+package-lock.json

e2e/.prettierrc

@@ -0,0 +1,7 @@
+{
+  "useTabs": false,
+  "tabWidth": 2,
+  "singleQuote": true,
+  "trailingComma": "es5",
+  "printWidth": 100
+}

e2e/Caddyfile.test

@@ -4,7 +4,17 @@
 # of HTTPS/Let's Encrypt.
 
 :3101 {
-    encode zstd gzip
+    # Mirror prod: exclude the SSE stream from compression so buffering doesn't
+    # delay real-time events (and so the test stack exercises the real behavior).
+    @compressible not path /api/v1/stream
+    encode @compressible zstd gzip
+
+    # 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"
+    }
 
     reverse_proxy /api/* app:3000
     reverse_proxy /media/* app:3000

e2e/README.md

@@ -6,6 +6,7 @@ backend) and `:55432` (Postgres), and exercises the SvelteKit frontend
 against a real Rust backend with rate limits and quotas disabled.
 
 **Phases 1, 2, and 3-mobile-gestures are landed**:
+
 - **Phase 1** — happy-path coverage of every documented user journey, plus a
   smoke matrix across nine browser/UA profiles to catch engine-level
   divergences.
@@ -47,25 +48,25 @@ The CI workflow at `.github/workflows/e2e.yml` runs both jobs on every PR.
 Every spec covers a journey from [`docs/USER_JOURNEYS.md`](../docs/USER_JOURNEYS.md)
 or a security/chaos scenario. One folder per area:
 
-| Folder | Phase | Journeys / Topic | Tests | Notes |
-|---|---|---|---|---|
-| `specs/01-auth/` | 1 | §1, §2, §3, §11, §15 | 13 | Join, recover, PIN lockout, admin login, leave event. |
-| `specs/02-upload/` | 1 | §5, §6, §18 | 5 | Gallery picker, multi-file, rate-limit, admin toggle. |
-| `specs/03-feed/` | 1 | §7, §8, §17 | 5 | Like/comment SSE, filter chips, SSE reconnect. |
-| `specs/04-host/` | 1 | §9 | 5 | Event lock, ban/unban, role change. |
-| `specs/05-admin/` | 1 | §11, §16 | 11 | Config validation, foundational auth guards, stats. |
-| `specs/06-export/` | 1 | §12 | 3 | Status, release, download stub. |
-| `specs/__smoke/` | 1 | (matrix) | 1 × 9 UAs | `@smoke`-tagged happy-path on every UA project. |
-| `specs/07-adversarial/` | **2** | Input attacks, file upload boundaries, JWT forgery, brute-force, deep authorization, small DDoS | ~40 | See breakdown below. |
-| `specs/08-browser-chaos/` | **2** | Storage purge, IndexedDB, offline/slow-3G, multi-tab, no-JS, clock skew, quota | ~20 | See breakdown below. |
-| `specs/09-mobile/` | **3** | Touch-target audit, safe-area, long-press, double-tap, viewport reflow, fixme stubs | 23 | Runs only on `chromium-mobile` (Pixel 7 viewport). See below. |
+| Folder                    | Phase | Journeys / Topic                                                                                | Tests     | Notes                                                         |
+| ------------------------- | ----- | ----------------------------------------------------------------------------------------------- | --------- | ------------------------------------------------------------- |
+| `specs/01-auth/`          | 1     | §1, §2, §3, §11, §15                                                                            | 13        | Join, recover, PIN lockout, admin login, leave event.         |
+| `specs/02-upload/`        | 1     | §5, §6, §18                                                                                     | 5         | Gallery picker, multi-file, rate-limit, admin toggle.         |
+| `specs/03-feed/`          | 1     | §7, §8, §17                                                                                     | 5         | Like/comment SSE, filter chips, SSE reconnect.                |
+| `specs/04-host/`          | 1     | §9                                                                                              | 5         | Event lock, ban/unban, role change.                           |
+| `specs/05-admin/`         | 1     | §11, §16                                                                                        | 11        | Config validation, foundational auth guards, stats.           |
+| `specs/06-export/`        | 1     | §12                                                                                             | 3         | Status, release, download stub.                               |
+| `specs/__smoke/`          | 1     | (matrix)                                                                                        | 1 × 9 UAs | `@smoke`-tagged happy-path on every UA project.               |
+| `specs/07-adversarial/`   | **2** | Input attacks, file upload boundaries, JWT forgery, brute-force, deep authorization, small DDoS | ~40       | See breakdown below.                                          |
+| `specs/08-browser-chaos/` | **2** | Storage purge, IndexedDB, offline/slow-3G, multi-tab, no-JS, clock skew, quota                  | ~20       | See breakdown below.                                          |
+| `specs/09-mobile/`        | **3** | Touch-target audit, safe-area, long-press, double-tap, viewport reflow, fixme stubs             | 23        | Runs only on `chromium-mobile` (Pixel 7 viewport). See below. |
 
 ### Phase 2 — adversarial (`specs/07-adversarial/`)
 
 - **`xss-injection.spec.ts`** — 13 tests. Six XSS payloads × display-name path
-  + four SQLi patterns + length/encoding edge cases (NUL byte, RTL override,
-  caption overflow). Asserts `window.__xssFired` never gets set and no
-  `dialog` event fires.
+  - four SQLi patterns + length/encoding edge cases (NUL byte, RTL override,
+    caption overflow). Asserts `window.__xssFired` never gets set and no
+    `dialog` event fires.
 - **`ui-rendering.spec.ts`** — 2 tests. Belt-and-braces: even when a script-
   payload sits in localStorage as the user's display name, rendering through
   `/account` keeps it as text.
@@ -104,17 +105,17 @@ are marked `test.fixme` and will activate when that helper lands.
 
 ## Browser & UA matrix
 
-| Project | Engine | UA / Device | Why |
-|---|---|---|---|
-| `chromium-desktop` | Chromium | Desktop Chrome | Baseline. Full suite runs here. |
-| `chromium-pixel7` | Chromium | Pixel 7 device descriptor | Chrome Android. |
-| `chromium-galaxy-s22` | Chromium | Galaxy viewport + Samsung phone UA | Chrome on Samsung hardware. |
-| `samsung-internet` | Chromium | Galaxy viewport + SamsungBrowser UA | **Tier-A Samsung Internet baseline.** |
-| `edge-android` | Chromium | Pixel viewport + EdgA UA | Edge Mobile (Blink-based). |
-| `chrome-ios` | Chromium | iPhone viewport + CriOS UA | Chrome iOS (actually WebKit, but UA differs). |
-| `webkit-iphone` | WebKit | iPhone 14 Pro | Real iOS Safari engine. |
-| `firefox-android` | Firefox | Pixel viewport + Firefox Android UA | Gecko engine. |
-| `firefox-desktop` | Firefox | Desktop Firefox | FF-specific quirks. |
+| Project               | Engine   | UA / Device                         | Why                                           |
+| --------------------- | -------- | ----------------------------------- | --------------------------------------------- |
+| `chromium-desktop`    | Chromium | Desktop Chrome                      | Baseline. Full suite runs here.               |
+| `chromium-pixel7`     | Chromium | Pixel 7 device descriptor           | Chrome Android.                               |
+| `chromium-galaxy-s22` | Chromium | Galaxy viewport + Samsung phone UA  | Chrome on Samsung hardware.                   |
+| `samsung-internet`    | Chromium | Galaxy viewport + SamsungBrowser UA | **Tier-A Samsung Internet baseline.**         |
+| `edge-android`        | Chromium | Pixel viewport + EdgA UA            | Edge Mobile (Blink-based).                    |
+| `chrome-ios`          | Chromium | iPhone viewport + CriOS UA          | Chrome iOS (actually WebKit, but UA differs). |
+| `webkit-iphone`       | WebKit   | iPhone 14 Pro                       | Real iOS Safari engine.                       |
+| `firefox-android`     | Firefox  | Pixel viewport + Firefox Android UA | Gecko engine.                                 |
+| `firefox-desktop`     | Firefox  | Desktop Firefox                     | FF-specific quirks.                           |
 
 Only the `@smoke` happy-path runs across all projects (controlled by
 `grep` in `playwright.config.ts`). The full Phase 1 suite is
@@ -127,14 +128,14 @@ It's **Blink-based**, so Tier-A catches ~90% of regressions. Real Samsung
 divergences (Smart Switch save-data mode, dark-mode injection, custom
 autoplay, in-browser ad blocking) are only reproducible at Tier B+:
 
-- **Tier A** *(this repo, free, in CI)*: Playwright Chromium with the
+- **Tier A** _(this repo, free, in CI)_: Playwright Chromium with the
   Samsung Internet user-agent + Galaxy viewport. See the `samsung-internet`
   project in `playwright.config.ts`.
-- **Tier B** *(free, manual, future)*: Android Studio emulator on Linux →
+- **Tier B** _(free, manual, future)_: Android Studio emulator on Linux →
   install Samsung Internet APK → enable `--remote-debugging-port=9222` →
   `chromium.connectOverCDP('http://localhost:9222')`. Setup docs live in
   `docs/samsung-emulator.md` (to be written).
-- **Tier C** *(paid, optional)*: BrowserStack or LambdaTest cloud devices.
+- **Tier C** _(paid, optional)_: BrowserStack or LambdaTest cloud devices.
   Real Galaxy S22/S23 hardware via Playwright's cloud integration.
 
 ## Test isolation
@@ -223,7 +224,7 @@ Known findings surfaced (documented in tests, not silent failures):
    clears it).
 3. SVG uploads currently pass the magic-byte check (depends on `infer`'s
    detection coverage) — consider adding `X-Content-Type-Options: nosniff`
-   + CSP on `/media/*` if SVGs are ever expected as user content.
+   - CSP on `/media/*` if SVGs are ever expected as user content.
 
 ### Phase 3 — Mobile gestures (`specs/09-mobile/`) ✅ landed
 
@@ -273,6 +274,7 @@ ignores this folder via `testIgnore` in [playwright.config.ts](playwright.config
   values.
 
 ### Phase 3 — Real-device compat & visual / a11y (not landed)
+
 - Long-press own/other post, swipe lightbox L/R, swipe-down dismiss, pull-to-refresh, double-tap like.
 - Safe-area inset visual diff on iPhone notch.
 - Touch-target ≥ 44 px audit.
@@ -282,6 +284,7 @@ ignores this folder via `testIgnore` in [playwright.config.ts](playwright.config
 - Visual regression with screenshot diffs.
 
 ### Out of scope (handed to other tools)
+
 - Load testing → k6 / Vegeta.
 - API contract testing → backend `cargo test` integration tests.
 - Static asset auditing → Lighthouse CI.

e2e/docker-compose.test.yml

@@ -17,12 +17,12 @@ services:
       POSTGRES_PASSWORD: eventsnap_test
       POSTGRES_DB: eventsnap_test
     healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U eventsnap_test -d eventsnap_test"]
+      test: ['CMD-SHELL', 'pg_isready -U eventsnap_test -d eventsnap_test']
       interval: 3s
       timeout: 3s
       retries: 30
     ports:
-      - "55432:5432"               # exposed so the e2e harness can connect via pg for fixture setup
+      - '55432:5432' # exposed so the e2e harness can connect via pg for fixture setup
 
   app:
     build:
@@ -40,15 +40,15 @@ services:
       ADMIN_PASSWORD_HASH: $$2b$$04$$XKJJkNX6BOi6y3S42DA5JOWwk4oxc8DHPL6.MrPfJI2vpnccZjP32
       EVENT_SLUG: e2e-test-event
       EVENT_NAME: E2E Test Event
-      APP_PORT: "3000"
+      APP_PORT: '3000'
       MEDIA_PATH: /media
-      SESSION_EXPIRY_DAYS: "30"
-      EVENTSNAP_TEST_MODE: "1"     # ENABLES /admin/__truncate — never set in prod
+      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
     expose:
-      - "3000"
+      - '3000'
 
   frontend:
     build:
@@ -57,11 +57,11 @@ services:
     depends_on:
       - app
     environment:
-      PORT: "3001"
-      HOST: "0.0.0.0"
-      ORIGIN: "http://localhost:3101"
+      PORT: '3001'
+      HOST: '0.0.0.0'
+      ORIGIN: 'http://localhost:3101'
     expose:
-      - "3001"
+      - '3001'
 
   caddy:
     image: caddy:2-alpine
@@ -71,7 +71,7 @@ services:
     volumes:
       - ./Caddyfile.test:/etc/caddy/Caddyfile:ro
     ports:
-      - "3101:3101"
+      - '3101:3101'
 
 volumes:
   media_data:

e2e/eslint.config.js

@@ -0,0 +1,47 @@
+import js from '@eslint/js';
+import ts from 'typescript-eslint';
+import prettier from 'eslint-config-prettier';
+import globals from 'globals';
+
+/**
+ * Flat-config ESLint for the Playwright TypeScript suite. Prettier owns formatting (its config is
+ * last so it disables every stylistic rule). The rules kept here catch real test bugs — unused
+ * setup, floating promises that make a test race, `any` that hides a wrong assertion shape.
+ */
+export default ts.config(
+  js.configs.recommended,
+  ...ts.configs.recommended,
+  prettier,
+  {
+    languageOptions: {
+      globals: { ...globals.node },
+    },
+  },
+  {
+    rules: {
+      '@typescript-eslint/no-unused-vars': [
+        'error',
+        { argsIgnorePattern: '^_', varsIgnorePattern: '^_', caughtErrorsIgnorePattern: '^_' },
+      ],
+      // A floating promise in a test is a real hazard: an un-awaited request or assertion can let
+      // the test end before it runs, passing vacuously. Keep it on.
+      '@typescript-eslint/no-floating-promises': 'error',
+      // Off for the suite: this is all test code, where `any` is the honest type for an untyped
+      // `res.json()` body or a `page.evaluate()` return. Threading DTO types through every
+      // assertion is churn that buys nothing — the assertion values are what's checked, not the
+      // static shape. (no-floating-promises and no-unused-vars, which catch real test bugs, stay on.)
+      '@typescript-eslint/no-explicit-any': 'off',
+      // Off: Playwright fixtures with no dependencies are declared `async ({}, use) => {}` — the
+      // empty destructure is required by the fixtures API, not an accident.
+      'no-empty-pattern': 'off',
+    },
+  },
+  {
+    languageOptions: {
+      parserOptions: { projectService: true },
+    },
+  },
+  {
+    ignores: ['node_modules/', 'playwright-report/', 'test-results/', '*.config.js'],
+  }
+);

e2e/fixtures/api-client.ts

@@ -47,7 +47,9 @@ export class ApiClient {
   }
 
   // ── Auth ───────────────────────────────────────────────────────────────
-  async join(displayName: string): Promise<{ jwt: string; pin: string; user_id: string; is_new: boolean }> {
+  async join(
+    displayName: string
+  ): Promise<{ jwt: string; pin: string; user_id: string; is_new: boolean }> {
     const { body } = await this.request<any>('POST', '/join', {
       body: { display_name: displayName },
       expectedStatus: [201],
@@ -55,7 +57,11 @@ export class ApiClient {
     return body;
   }
 
-  async recover(displayName: string, pin: string, opts: { expectedStatus?: number | number[] } = {}) {
+  async recover(
+    displayName: string,
+    pin: string,
+    opts: { expectedStatus?: number | number[] } = {}
+  ) {
     return this.request<any>('POST', '/recover', {
       body: { display_name: displayName, pin },
       expectedStatus: opts.expectedStatus ?? [200],
@@ -91,7 +97,9 @@ export class ApiClient {
   }
 
   async getConfig(adminToken: string): Promise<Record<string, string>> {
-    const { body } = await this.request<Record<string, string>>('GET', '/admin/config', { token: adminToken });
+    const { body } = await this.request<Record<string, string>>('GET', '/admin/config', {
+      token: adminToken,
+    });
     return body;
   }
 
@@ -109,14 +117,43 @@ export class ApiClient {
     });
   }
 
-  async banUser(token: string, userId: string, hideUploads = false) {
+  // A ban ALWAYS hides the user's uploads — the backend takes no body and ignores any
+  // `hide_uploads` flag (the old opt-out was removed). No per-request options.
+  async banUser(token: string, userId: string) {
     return this.request<void>('POST', `/host/users/${userId}/ban`, {
       token,
-      body: { hide_uploads: hideUploads },
       expectedStatus: [200, 204],
     });
   }
 
+  async unbanUser(
+    token: string,
+    userId: string,
+    opts: { expectedStatus?: number | number[] } = {}
+  ) {
+    return this.request<void>('POST', `/host/users/${userId}/unban`, {
+      token,
+      expectedStatus: opts.expectedStatus ?? [200, 204],
+    });
+  }
+
+  /** Reset another user's PIN. Returns the plaintext PIN the host must relay once. */
+  async resetUserPin(
+    token: string,
+    userId: string,
+    opts: { expectedStatus?: number | number[] } = {}
+  ): Promise<{ status: number; body: { pin?: string } }> {
+    return this.request<{ pin?: string }>('POST', `/host/users/${userId}/pin-reset`, {
+      token,
+      expectedStatus: opts.expectedStatus ?? [200],
+    });
+  }
+
+  async listPinResetRequests(token: string): Promise<any[]> {
+    const { body } = await this.request<any[]>('GET', '/host/pin-reset-requests', { token });
+    return body;
+  }
+
   async closeEvent(token: string) {
     return this.request<void>('POST', '/host/event/close', { token, expectedStatus: [200, 204] });
   }

e2e/fixtures/db.ts

@@ -39,11 +39,16 @@ export const db = {
 
   async expireSession(userId: string) {
     await withClient((c) =>
-      c.query(`UPDATE session SET expires_at = NOW() - interval '1 hour' WHERE user_id = $1`, [userId])
+      c.query(`UPDATE session SET expires_at = NOW() - interval '1 hour' WHERE user_id = $1`, [
+        userId,
+      ])
     );
   },
 
-  async setUploadCompressionStatus(uploadId: string, status: 'pending' | 'processing' | 'done' | 'failed') {
+  async setUploadCompressionStatus(
+    uploadId: string,
+    status: 'pending' | 'processing' | 'done' | 'failed'
+  ) {
     await withClient((c) =>
       c.query(`UPDATE upload SET compression_status = $2 WHERE id = $1`, [uploadId, status])
     );
@@ -59,6 +64,26 @@ export const db = {
     });
   },
 
+  async countSessionsForUser(userId: string): Promise<number> {
+    return withClient(async (c) => {
+      const r = await c.query<{ count: string }>(
+        `SELECT COUNT(*)::text AS count FROM session WHERE user_id = $1`,
+        [userId]
+      );
+      return Number(r.rows[0].count);
+    });
+  },
+
+  async countPinResetRequestsForUser(userId: string): Promise<number> {
+    return withClient(async (c) => {
+      const r = await c.query<{ count: string }>(
+        `SELECT COUNT(*)::text AS count FROM pin_reset_request WHERE user_id = $1`,
+        [userId]
+      );
+      return Number(r.rows[0].count);
+    });
+  },
+
   async setExportReleased(slug: string, released: boolean) {
     await withClient((c) =>
       c.query(`UPDATE event SET export_released_at = $2 WHERE slug = $1`, [
@@ -69,26 +94,55 @@ export const db = {
   },
 
   /**
-   * Flip the `export_zip_ready` gate directly. The download handler serves bytes
-   * only when this boolean is true AND the file exists on disk, so setting it true
-   * without a file lets tests exercise the "ready but file missing" 404 branch.
+   * Make an export "ready" (or not) in the epoch model. There is no `export_zip_ready` column any
+   * more — readiness is DERIVED (`released AND job.epoch = event.export_epoch AND status='done'`),
+   * so a job is ready exactly when its row carries the event's live epoch. To make a `done` job NOT
+   * ready we retire it to a dead epoch (-1), which is what a reopen effectively does.
+   *
+   * `file_path` is deliberately left NULL, so a "ready" job with no file on disk still exercises
+   * the download's missing-file 404 branch.
    */
   async setExportZipReady(slug: string, ready: boolean) {
     await withClient((c) =>
-      c.query(`UPDATE event SET export_zip_ready = $2 WHERE slug = $1`, [slug, ready])
+      c.query(
+        `UPDATE export_job ej
+            SET epoch = CASE WHEN $2 THEN e.export_epoch ELSE -1 END
+           FROM event e
+          WHERE e.id = ej.event_id AND e.slug = $1 AND ej.type = 'zip'`,
+        [slug, ready]
+      )
     );
   },
 
-  /** Insert a pre-baked export job row to skip the (slow) real compression path. */
-  async fakeExportJob(eventSlug: string, type: 'zip' | 'html', status: 'pending' | 'running' | 'done') {
+  /**
+   * Insert a pre-baked export job row to skip the (slow) real compression path. Stamped with the
+   * event's CURRENT epoch so it counts as the live generation.
+   */
+  async fakeExportJob(
+    eventSlug: string,
+    type: 'zip' | 'html',
+    status: 'pending' | 'running' | 'done'
+  ) {
     await withClient(async (c) => {
-      const ev = await c.query<{ id: string }>(`SELECT id FROM event WHERE slug = $1`, [eventSlug]);
+      const ev = await c.query<{ id: string; export_epoch: string }>(
+        `SELECT id, export_epoch FROM event WHERE slug = $1`,
+        [eventSlug]
+      );
       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)
-         VALUES ($1, $2::export_type, $3::export_status, $4, $5)
-         ON CONFLICT (event_id, type) DO UPDATE SET status = EXCLUDED.status, progress_pct = EXCLUDED.progress_pct`,
-        [ev.rows[0].id, type, status, status === 'done' ? 100 : 0, status === 'done' ? new Date() : null]
+        `INSERT INTO export_job (event_id, type, status, progress_pct, completed_at, epoch)
+         VALUES ($1, $2::export_type, $3::export_status, $4, $5, $6)
+         ON CONFLICT (event_id, type) DO UPDATE
+           SET status = EXCLUDED.status, progress_pct = EXCLUDED.progress_pct,
+               epoch = EXCLUDED.epoch`,
+        [
+          ev.rows[0].id,
+          type,
+          status,
+          status === 'done' ? 100 : 0,
+          status === 'done' ? new Date() : null,
+          ev.rows[0].export_epoch,
+        ]
       );
     });
   },

e2e/fixtures/test.ts

@@ -84,16 +84,13 @@ export const test = base.extend<Fixtures>({
     const fn = async (page: Page, handle: GuestHandle) => {
       // Visit any in-app URL first so localStorage is scoped to the right origin.
       await page.goto('/');
-      await page.evaluate(
-        ({ jwt, pin, userId, displayName }) => {
-          localStorage.setItem('eventsnap_jwt', jwt);
-          localStorage.setItem('eventsnap_pin', pin);
-          localStorage.setItem('eventsnap_user_id', userId);
-          localStorage.setItem('eventsnap_display_name', displayName);
-          localStorage.setItem('eventsnap_guide_seen', 'true');
-        },
-        handle
-      );
+      await page.evaluate(({ jwt, pin, userId, displayName }) => {
+        localStorage.setItem('eventsnap_jwt', jwt);
+        localStorage.setItem('eventsnap_pin', pin);
+        localStorage.setItem('eventsnap_user_id', userId);
+        localStorage.setItem('eventsnap_display_name', displayName);
+        localStorage.setItem('eventsnap_guide_seen', 'true');
+      }, handle);
       await page.goto('/feed');
     };
     await use(fn);

e2e/helpers/env.ts

@@ -0,0 +1,5 @@
+/**
+ * Shared test environment constants. The frontend base URL was redeclared verbatim in ~23 specs;
+ * one source of truth means a port/scheme change is a single edit, not a sweep.
+ */
+export const BASE = process.env.E2E_FRONTEND_URL ?? 'http://localhost:3101';

e2e/helpers/seed.ts

@@ -3,10 +3,24 @@
  * flow. Centralising the API contract (routes, field names, expected statuses)
  * means an API change is a one-file edit, not a 7-file hunt.
  */
-import { uploadRaw, JPEG_MAGIC } from './upload-client';
+import { readFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { uploadRaw } from './upload-client';
 import { db } from '../fixtures/db';
+import { BASE } from './env';
 
-const BASE = process.env.E2E_FRONTEND_URL ?? 'http://localhost:3101';
+// A real, decodable JPEG. Magic-bytes-only fakes now get auto-cleaned by the
+// backend when compression fails (a failed transcode refunds quota + deletes the
+// row), which would delete the seeded upload out from under the test. Read lazily
+// at call time (cwd is the e2e dir at runtime, like the gallery-path spec) so test
+// collection can't trip on a module-load read.
+let sampleJpg: Buffer | null = null;
+function sampleImage(): Buffer {
+  if (!sampleJpg) {
+    sampleJpg = readFileSync(join(process.cwd(), 'fixtures', 'media', 'sample.jpg'));
+  }
+  return sampleJpg;
+}
 
 export type SeedUploadOptions = {
   caption?: string;
@@ -16,9 +30,7 @@ export type SeedUploadOptions = {
 
 /** Seed a real, accepted upload owned by `jwt` and return its id. */
 export async function seedUpload(jwt: string, opts: SeedUploadOptions = {}): Promise<string> {
-  const body = new Uint8Array(1024);
-  body.set(JPEG_MAGIC, 0);
-  const res = await uploadRaw(jwt, body, {
+  const res = await uploadRaw(jwt, sampleImage(), {
     filename: 'a.jpg',
     contentType: 'image/jpeg',
     caption: opts.caption,

e2e/helpers/sse-listener.ts

@@ -30,7 +30,8 @@ export class SseListener {
     const reader = res.body.getReader();
     const decoder = new TextDecoder();
     let buffer = '';
-    (async () => {
+    // Fire-and-forget reader loop; the caller drives lifecycle via stop()/the AbortController.
+    void (async () => {
       try {
         while (!this.closed) {
           const { done, value } = await reader.read();
@@ -61,7 +62,9 @@ export class SseListener {
       if (hit) return hit;
       await new Promise((r) => setTimeout(r, 50));
     }
-    throw new Error(`SSE event ${type} did not arrive within ${timeoutMs}ms. Got: ${this.events.map((e) => e.type).join(', ')}`);
+    throw new Error(
+      `SSE event ${type} did not arrive within ${timeoutMs}ms. Got: ${this.events.map((e) => e.type).join(', ')}`
+    );
   }
 
   allEvents(): SseEvent[] {

e2e/helpers/sse.ts

@@ -4,8 +4,7 @@
  * it lives in one place instead of being re-inlined per spec.
  */
 import type { Page } from '@playwright/test';
-
-const BASE = process.env.E2E_FRONTEND_URL ?? 'http://localhost:3101';
+import { BASE } from './env';
 
 /** Exchange a JWT for a single-use SSE ticket via POST /api/v1/stream/ticket. */
 export async function mintSseTicket(jwt: string): Promise<string> {
@@ -13,7 +12,8 @@ export async function mintSseTicket(jwt: string): Promise<string> {
     method: 'POST',
     headers: { Authorization: `Bearer ${jwt}` },
   });
-  if (res.status !== 200) throw new Error(`mintSseTicket failed: ${res.status} ${await res.text()}`);
+  if (res.status !== 200)
+    throw new Error(`mintSseTicket failed: ${res.status} ${await res.text()}`);
   return (await res.json()).ticket;
 }
 

e2e/helpers/touch.ts

@@ -34,6 +34,47 @@ export async function longPress(page: Page, locator: Locator, durationMs = 600)
   await page.mouse.up();
 }
 
+/**
+ * A sub-threshold press dispatched ENTIRELY in-browser: `pointerdown`, an in-browser
+ * `setTimeout(holdMs)`, then `pointerup` — all on the element carrying `use:longpress`.
+ *
+ * Why not `longPress` (page.mouse + waitForTimeout) for the "quick tap must NOT long-press"
+ * case: those are three independent CDP round-trips with a Node-side wait between the down
+ * and the up. Under cross-test load the browser can process the `pointerup` far later than
+ * `holdMs` of *browser* time, so the app's real 500 ms long-press timer fires and the
+ * ContextSheet opens on what the test intended as a quick tap. (Observed: a 200 ms-intended
+ * tap opening the sheet ~1 % of full-suite runs.) Dispatching both events from one
+ * `evaluate` puts the down→up gap and the app's 500 ms timer on the SAME clock: even if the
+ * event loop stalls, the earlier-scheduled `pointerup` (holdMs) still fires before the
+ * later 500 ms timer, so the relationship holds. Mirrors `doubleTap`.
+ *
+ * No trusted `click` follows a synthetic `pointerup`, so use this ONLY where the assertion is
+ * that the long-press did NOT fire — not where a real click must land (see `longPress`).
+ */
+export async function quickTap(locator: Locator, holdMs = 200) {
+  await locator.evaluate((el: HTMLElement, ms: number) => {
+    const rect = el.getBoundingClientRect();
+    const x = rect.left + rect.width / 2;
+    const y = rect.top + rect.height / 2;
+    const mk = (type: string) =>
+      new PointerEvent(type, {
+        bubbles: true,
+        cancelable: true,
+        clientX: x,
+        clientY: y,
+        pointerType: 'touch',
+        isPrimary: true,
+      });
+    el.dispatchEvent(mk('pointerdown'));
+    return new Promise<void>((resolve) =>
+      setTimeout(() => {
+        el.dispatchEvent(mk('pointerup'));
+        resolve();
+      }, ms)
+    );
+  }, holdMs);
+}
+
 /**
  * Two rapid pointer-event pairs within the doubletap action's 300 ms window.
  *

e2e/helpers/upload-client.ts

@@ -1,3 +1,4 @@
+import { BASE } from './env';
 /**
  * Node-side multipart upload helper. Lets adversarial specs post arbitrary
  * bytes with arbitrary `Content-Type` claims to /api/v1/upload without
@@ -11,8 +12,6 @@
  */
 // Node 22+ ships FormData and Blob as globals — no import needed.
 
-const BASE = process.env.E2E_FRONTEND_URL ?? 'http://localhost:3101';
-
 export type UploadOptions = {
   filename?: string;
   contentType?: string;
@@ -20,7 +19,11 @@ export type UploadOptions = {
   hashtags?: string;
 };
 
-export async function uploadRaw(token: string, body: Uint8Array | Buffer, opts: UploadOptions = {}) {
+export async function uploadRaw(
+  token: string,
+  body: Uint8Array | Buffer,
+  opts: UploadOptions = {}
+) {
   const form = new FormData();
   const blob = new Blob([body as any], { type: opts.contentType ?? 'application/octet-stream' });
   form.append('file', blob as any, opts.filename ?? 'upload.bin');
@@ -41,8 +44,74 @@ export async function uploadFile(token: string, path: string, opts: UploadOption
 }
 
 /** Tiny valid JPEG header — magic bytes only, useful for "claim image but is N MB of zeros" tests. */
-export const JPEG_MAGIC = new Uint8Array([0xff, 0xd8, 0xff, 0xe0, 0x00, 0x10, 0x4a, 0x46, 0x49, 0x46]);
+export const JPEG_MAGIC = new Uint8Array([
+  0xff, 0xd8, 0xff, 0xe0, 0x00, 0x10, 0x4a, 0x46, 0x49, 0x46,
+]);
 /** Tiny valid PNG magic bytes. */
 export const PNG_MAGIC = new Uint8Array([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a]);
 /** ELF header — the magic bytes of a Linux executable. `infer` reports `application/x-executable`. */
 export const ELF_MAGIC = new Uint8Array([0x7f, 0x45, 0x4c, 0x46]);
+
+/**
+ * Upload whose request body PAUSES mid-stream until you release it.
+ *
+ * This exists to make the release-vs-upload race deterministic instead of hoped-for. The bug it
+ * guards is a TOCTOU: `upload` checks `uploads_locked_at` BEFORE reading the body (minutes, for a
+ * big video) and commits the row afterwards — so a release landing in between used to let the photo
+ * commit AFTER the export snapshot, leaving it in the live feed but permanently absent from the
+ * keepsake.
+ *
+ * Racing N normal uploads against a release can't prove anything: if they all happen to commit
+ * first (or all get rejected), the assertion passes on broken code too. Here the server is *stuck*
+ * mid-body with its pre-flight check already passed, so the release provably lands inside the
+ * window. Await `checkPassed`, fire the release, then `finish()`.
+ */
+export function uploadPausedMidStream(
+  token: string,
+  head: Buffer,
+  tail: Buffer,
+  opts: UploadOptions = {}
+): { checkPassed: Promise<void>; finish: () => void; response: Promise<Response> } {
+  const boundary = '----eventsnapPausedBoundary' + Math.random().toString(16).slice(2);
+  const filename = opts.filename ?? 'paused.jpg';
+  const contentType = opts.contentType ?? 'image/jpeg';
+
+  const preamble = Buffer.from(
+    `--${boundary}\r\n` +
+      `Content-Disposition: form-data; name="file"; filename="${filename}"\r\n` +
+      `Content-Type: ${contentType}\r\n\r\n`
+  );
+  const epilogue = Buffer.from(`\r\n--${boundary}--\r\n`);
+
+  let releaseBody: () => void;
+  const gate = new Promise<void>((r) => (releaseBody = r));
+  let markCheckPassed: () => void;
+  const checkPassed = new Promise<void>((r) => (markCheckPassed = r));
+
+  const body = new ReadableStream<Uint8Array>({
+    async pull(controller) {
+      controller.enqueue(new Uint8Array(preamble));
+      controller.enqueue(new Uint8Array(head));
+      // The server has now read the part headers and the first bytes — which means it is PAST its
+      // pre-flight lock check and is sitting in the body loop. This is the window.
+      markCheckPassed();
+      await gate;
+      controller.enqueue(new Uint8Array(tail));
+      controller.enqueue(new Uint8Array(epilogue));
+      controller.close();
+    },
+  });
+
+  const response = fetch(`${BASE}/api/v1/upload`, {
+    method: 'POST',
+    headers: {
+      Authorization: `Bearer ${token}`,
+      'Content-Type': `multipart/form-data; boundary=${boundary}`,
+    },
+    body,
+    // Node's fetch requires this for a streaming request body.
+    duplex: 'half',
+  } as RequestInit & { duplex: 'half' });
+
+  return { checkPassed, finish: () => releaseBody(), response };
+}

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 +1,78 @@
+// 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');