# syntax=docker/dockerfile:1 # ============================================ # SnapOtter - Unified Production Dockerfile # Single image: GPU auto-detected on amd64, CPU on arm64 # ============================================ # ============================================ # Stage 0: Static FFmpeg/FFprobe binaries # ============================================ # Multi-arch (amd64 + arm64) static builds for video/audio processing. FROM mwader/static-ffmpeg:8.1.2 AS ffmpeg # ============================================ # Stage 0b: Static pdfcpu binary (pure Go, no CGO) # ============================================ # CGO_ENABLED=0 produces a fully static binary; no cross-compiler needed. FROM --platform=$BUILDPLATFORM golang:1.25-bookworm@sha256:a1ae6b6c564f3e0072d70081036827a2705dbcf6b38aaa6d97f5de97fe9abdb4 AS pdfcpu-builder ARG TARGETOS=linux ARG TARGETARCH RUN CGO_ENABLED=0 GOOS=$TARGETOS GOARCH=$TARGETARCH \ go install github.com/pdfcpu/pdfcpu/cmd/pdfcpu@v0.13.0 \ && cp "$(find /go/bin -type f -name pdfcpu | head -1)" /tmp/pdfcpu # ============================================ # Stage 1: Build the frontend (Vite + React) # ============================================ # Run on the native build platform to avoid QEMU crashes with esbuild on # Apple Silicon. The output (HTML/CSS/JS) is architecture-agnostic so it # is safe to build on arm64 and copy into the amd64 production layer. FROM --platform=$BUILDPLATFORM node:22-bookworm@sha256:e0d149b4727ac0c20d9774e801e423d7a946a0bffced886f42cfe9cd3c67820a AS builder RUN corepack enable && corepack prepare pnpm@9.15.4 --activate WORKDIR /app # Copy workspace config first (for layer caching) COPY pnpm-workspace.yaml pnpm-lock.yaml package.json turbo.json tsconfig.base.json ./ # Copy all package.json files for dependency install COPY apps/web/package.json apps/web/tsconfig.json apps/web/vite.config.ts apps/web/index.html ./apps/web/ COPY apps/web/postcss.config.js ./apps/web/ COPY apps/api/package.json apps/api/tsconfig.json ./apps/api/ COPY packages/shared/package.json packages/shared/tsconfig.json ./packages/shared/ COPY packages/image-engine/package.json packages/image-engine/tsconfig.json ./packages/image-engine/ COPY packages/media-engine/package.json packages/media-engine/tsconfig.json ./packages/media-engine/ COPY packages/doc-engine/package.json packages/doc-engine/tsconfig.json ./packages/doc-engine/ COPY packages/ai/package.json packages/ai/tsconfig.json ./packages/ai/ # pnpm patchedDependencies (package.json) needs the patch files present before # install, or `pnpm install` aborts with ENOENT on the patch. COPY patches/ ./patches/ # Install ALL dependencies (dev + prod needed for building) RUN --mount=type=cache,id=pnpm-store,target=/root/.local/share/pnpm/store/v3 \ pnpm install --frozen-lockfile # Copy only frontend-relevant source (API/Python changes don't bust this cache) COPY packages/shared/src ./packages/shared/src COPY apps/web/src ./apps/web/src COPY apps/web/public ./apps/web/public # Bake analytics config into the shared package before building the frontend. # The published image ships with analytics ON; self-builders can override: # docker compose build --build-arg SNAPOTTER_ANALYTICS=off # The real Sentry DSN + PostHog key are supplied as build args (public values, # sourced from CI secrets in the official build); a build without them stays # silent, so building from source never phones home. ARG SNAPOTTER_ANALYTICS=on ARG SNAPOTTER_POSTHOG_KEY= ARG SNAPOTTER_SENTRY_DSN= COPY scripts/bake-analytics.mjs ./scripts/ RUN SNAPOTTER_POSTHOG_KEY="${SNAPOTTER_POSTHOG_KEY}" \ SNAPOTTER_SENTRY_DSN="${SNAPOTTER_SENTRY_DSN}" \ node scripts/bake-analytics.mjs ${SNAPOTTER_ANALYTICS} # Build only the web frontend (API runs from TS source via tsx) RUN --mount=type=cache,id=turbo-cache,target=/app/.turbo \ pnpm --filter @snapotter/web build # ============================================ # Stage 2: Build caire (content-aware resize) # ============================================ # Run the Go toolchain on the native build platform to avoid QEMU crashes # on Apple Silicon when cross-compiling for linux/amd64. # caire imports gioui.org/app which requires CGO on Linux, so we use a # proper C cross-compiler instead of CGO_ENABLED=0. FROM --platform=$BUILDPLATFORM golang:1.25-bookworm@sha256:a1ae6b6c564f3e0072d70081036827a2705dbcf6b38aaa6d97f5de97fe9abdb4 AS caire-builder ARG TARGETOS=linux ARG TARGETARCH # Install graphics libs and (for cross-arch builds) the appropriate C cross-compiler. # Debian multi-arch lets us install target-arch headers alongside the native toolchain. RUN set -e; \ NATIVE=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/'); \ if [ "$TARGETARCH" = "$NATIVE" ]; then \ apt-get update && apt-get install -y --no-install-recommends \ libwayland-dev libx11-dev libx11-xcb-dev libxkbcommon-x11-dev \ libgles2-mesa-dev libegl1-mesa-dev libffi-dev libxcursor-dev \ libxrandr-dev libxinerama-dev libxi-dev libxxf86vm-dev \ libvulkan-dev libxfixes-dev pkg-config \ && rm -rf /var/lib/apt/lists/*; \ elif [ "$TARGETARCH" = "amd64" ]; then \ dpkg --add-architecture amd64 && \ apt-get update && apt-get install -y --no-install-recommends \ crossbuild-essential-amd64 \ libwayland-dev:amd64 libx11-dev:amd64 libx11-xcb-dev:amd64 \ libxkbcommon-x11-dev:amd64 libgles2-mesa-dev:amd64 libegl1-mesa-dev:amd64 \ libffi-dev:amd64 libxcursor-dev:amd64 libxrandr-dev:amd64 \ libxinerama-dev:amd64 libxi-dev:amd64 libxxf86vm-dev:amd64 \ libvulkan-dev:amd64 libxfixes-dev:amd64 pkg-config \ && rm -rf /var/lib/apt/lists/*; \ elif [ "$TARGETARCH" = "arm64" ]; then \ dpkg --add-architecture arm64 && \ apt-get update && apt-get install -y --no-install-recommends \ crossbuild-essential-arm64 \ libwayland-dev:arm64 libx11-dev:arm64 libx11-xcb-dev:arm64 \ libxkbcommon-x11-dev:arm64 libgles2-mesa-dev:arm64 libegl1-mesa-dev:arm64 \ libffi-dev:arm64 libxcursor-dev:arm64 libxrandr-dev:arm64 \ libxinerama-dev:arm64 libxi-dev:arm64 libxxf86vm-dev:arm64 \ libvulkan-dev:arm64 libxfixes-dev:arm64 pkg-config \ && rm -rf /var/lib/apt/lists/*; \ fi # Build caire and stage to /tmp/caire (stable path for the COPY below). # Cross-compiled CGO binaries land in $GOPATH/bin/${GOOS}_${GOARCH}/ not $GOPATH/bin/. RUN set -e; \ NATIVE=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/'); \ if [ "$TARGETARCH" = "$NATIVE" ]; then \ go install github.com/esimov/caire/cmd/caire@v1.5.0 && \ cp /go/bin/caire /tmp/caire; \ elif [ "$TARGETARCH" = "amd64" ]; then \ CC=x86_64-linux-gnu-gcc \ PKG_CONFIG_LIBDIR=/usr/lib/x86_64-linux-gnu/pkgconfig:/usr/share/pkgconfig \ CGO_ENABLED=1 GOOS=$TARGETOS GOARCH=$TARGETARCH \ go install github.com/esimov/caire/cmd/caire@v1.5.0 && \ cp /go/bin/${TARGETOS}_${TARGETARCH}/caire /tmp/caire; \ elif [ "$TARGETARCH" = "arm64" ]; then \ CC=aarch64-linux-gnu-gcc \ PKG_CONFIG_LIBDIR=/usr/lib/aarch64-linux-gnu/pkgconfig:/usr/share/pkgconfig \ CGO_ENABLED=1 GOOS=$TARGETOS GOARCH=$TARGETARCH \ go install github.com/esimov/caire/cmd/caire@v1.5.0 && \ cp /go/bin/${TARGETOS}_${TARGETARCH}/caire /tmp/caire; \ fi # ============================================ # Stage 2b: Build libheif (HEIC/HEIF tools) # ============================================ # Distro packages ship libheif 1.15-1.17 which cannot decode iPhone HEIC # files with multiple auxiliary images (depth maps, HDR gain maps). # Build libheif >= 1.19 from source for the fix (GitHub #183). # Base images match production to avoid shared-library ABI mismatches. FROM debian:bookworm@sha256:49ba348354a28e39c70beffd6cf43bdb8d55d81ce4b746b0428717d054b8bbc4 AS libheif-base-arm64 FROM ubuntu:24.04@sha256:786a8b558f7be160c6c8c4a54f9a57274f3b4fb1491cf65146521ae77ff1dc54 AS libheif-base-amd64 ARG TARGETARCH FROM libheif-base-${TARGETARCH} AS libheif-builder ARG LIBHEIF_VERSION=1.21.2 RUN apt-get update && apt-get install -y --no-install-recommends \ cmake pkg-config gcc g++ make curl ca-certificates \ libde265-dev libx265-dev libjpeg-dev libpng-dev \ && rm -rf /var/lib/apt/lists/* RUN curl -fsSL --retry 3 --retry-delay 5 "https://github.com/strukturag/libheif/releases/download/v${LIBHEIF_VERSION}/libheif-${LIBHEIF_VERSION}.tar.gz" \ | tar xz \ && cmake -B build -S "libheif-${LIBHEIF_VERSION}" \ -DCMAKE_INSTALL_PREFIX=/opt/libheif \ -DWITH_EXAMPLES=ON \ -DWITH_GDK_PIXBUF=OFF \ -DWITH_AOM_DECODER=OFF \ -DWITH_AOM_ENCODER=OFF \ -DWITH_DAV1D=OFF \ && cmake --build build -j$(nproc) \ && cmake --install build # ============================================ # Stage 3: Platform-specific base images # Pin tags to specific major.minor for reproducible builds. # ============================================ FROM node:22-bookworm@sha256:e0d149b4727ac0c20d9774e801e423d7a946a0bffced886f42cfe9cd3c67820a AS base-linux-arm64 # CUDA base must match the AI bundles' wheels (torch/paddle/onnxruntime-gpu are all # cu126) and the libcublas-12-6 install below. It also sets the NVIDIA_REQUIRE_CUDA # driver gate enforced by nvidia-container-toolkit at container start: a 12.6 base # needs driver R560+, vs 12.9 which needs R575+ and fails to start on common # production drivers (e.g. 570.x / CUDA 12.8). Keep this at 12.6.x. FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04@sha256:8aef630a54bc5c5146ae5ce68e6af5caa3df0fb690bb91544175c91f307e4356 AS base-linux-amd64 # Node.js donor: provides Node binaries for the CUDA amd64 image without # relying on NodeSource apt repos or Ubuntu mirrors (which are flaky on CI). FROM node:22-bookworm@sha256:e0d149b4727ac0c20d9774e801e423d7a946a0bffced886f42cfe9cd3c67820a AS node-bins # ============================================ # Stage 4: Production runtime # ============================================ ARG TARGETOS ARG TARGETARCH FROM base-${TARGETOS}-${TARGETARCH} AS production ARG TARGETARCH # Pin corepack's cache to a system-wide path so all users share the same pnpm # binary without downloading it on each container start. ENV COREPACK_HOME=/usr/local/share/corepack # Install Node.js on amd64 by copying from the official node image. # This avoids flaky Ubuntu/NodeSource apt mirrors that frequently fail on CI. COPY --from=node-bins /usr/local/bin/node /usr/local/bin/ COPY --from=node-bins /usr/local/lib/node_modules /usr/local/lib/node_modules RUN ln -sf ../lib/node_modules/corepack/dist/corepack.js /usr/local/bin/corepack && \ ln -sf ../lib/node_modules/npm/bin/npm-cli.js /usr/local/bin/npm && \ ln -sf ../lib/node_modules/npm/bin/npx-cli.js /usr/local/bin/npx RUN corepack enable && corepack prepare pnpm@9.15.4 --activate && \ chmod -R a+rX /usr/local/share/corepack # System dependencies (all platforms) # Split into runtime deps and build deps to minimize final image size. # Retry apt-get update with backoff — Ubuntu mirrors can be flaky on CI runners # `apt-get upgrade` pulls security patches for base-image packages (e.g. # libgnutls30t64, libgcrypt20, liblzma5) that the pinned base digest ships at an # outdated patch level -- closes the Trivy OS-package CVEs on every rebuild. RUN for i in 1 2 3; do apt-get -o Acquire::Retries=3 update && break || sleep $((i * 15)); done && \ apt-get upgrade -y && \ apt-get install -y --no-install-recommends \ tini \ imagemagick \ libjxl-tools \ libraw-dev libraw-bin \ libopenexr-dev \ potrace \ ghostscript \ libopenjp2-tools \ curl \ gosu \ libde265-0 \ libimage-exiftool-perl \ python3 python3-pip python3-venv python3-dev \ tesseract-ocr tesseract-ocr-eng tesseract-ocr-deu tesseract-ocr-fra tesseract-ocr-spa \ tesseract-ocr-chi-sim tesseract-ocr-jpn tesseract-ocr-kor \ # Document engine: qpdf + LibreOffice headless + pandoc + WeasyPrint runtime deps # calibre deferred (5.2 GB ruling; pandoc covers epub/markdown families) pandoc \ qpdf \ libpango-1.0-0 libpangocairo-1.0-0 libcairo2 libgdk-pixbuf-2.0-0 \ fonts-dejavu-core \ libreoffice-calc libreoffice-impress libreoffice-writer \ gcc g++ \ libgl1 libglib2.0-0 libgles2 \ libegl1 libwayland-egl1 libwayland-client0 libwayland-cursor0 \ libxkbcommon-x11-0 libxkbcommon0 libxcursor1 \ && if apt-cache show libmagickcore-6.q16-7-extra >/dev/null 2>&1; then \ apt-get install -y --no-install-recommends libmagickcore-6.q16-7-extra; \ elif apt-cache show libmagickcore-6.q16-6-extra >/dev/null 2>&1; then \ apt-get install -y --no-install-recommends libmagickcore-6.q16-6-extra; \ fi \ && if apt-cache show libx265-199 >/dev/null 2>&1; then \ apt-get install -y --no-install-recommends libx265-199; \ elif apt-cache show libx265-209 >/dev/null 2>&1; then \ apt-get install -y --no-install-recommends libx265-209; \ fi \ && if apt-cache show libcublas-12-6 >/dev/null 2>&1; then \ apt-get install -y --no-install-recommends libcublas-12-6; \ fi \ && rm -rf /var/lib/apt/lists/* # Allow ImageMagick to use Ghostscript delegate for EPS (read for decode, # write for the convert tool's EPS output). PS/PDF/XPS stay read-only. RUN POLICY_FILE=$(find /etc/ImageMagick* -name policy.xml 2>/dev/null | head -1) && \ if [ -n "$POLICY_FILE" ]; then \ sed -i 's/ /opt/venv/.venv-version # On-demand AI feature installer and manifest COPY docker/feature-manifest.json /app/docker/feature-manifest.json COPY packages/ai/python/install_feature.py /app/packages/ai/python/install_feature.py WORKDIR /app # Copy workspace config COPY pnpm-workspace.yaml pnpm-lock.yaml package.json turbo.json tsconfig.base.json ./ # Copy ALL package manifests COPY apps/api/package.json apps/api/tsconfig.json ./apps/api/ COPY packages/shared/package.json packages/shared/tsconfig.json ./packages/shared/ COPY packages/image-engine/package.json packages/image-engine/tsconfig.json ./packages/image-engine/ COPY packages/media-engine/package.json packages/media-engine/tsconfig.json ./packages/media-engine/ COPY packages/doc-engine/package.json packages/doc-engine/tsconfig.json ./packages/doc-engine/ COPY packages/ai/package.json packages/ai/tsconfig.json ./packages/ai/ # packages/enterprise is required for ALL commercial features (license validation, # SAML/SCIM/MFA gates, S3 storage, OTel tracing gate, GDPR/audit/SIEM routes). # Without it, apps/api's `@snapotter/enterprise: workspace:*` link dangles and every # `import("@snapotter/enterprise")` throws (silently caught) -> enterprise.active=false # regardless of license. Manifest copied before install so pnpm wires the workspace link. COPY packages/enterprise/package.json packages/enterprise/tsconfig.json ./packages/enterprise/ # pnpm patchedDependencies (package.json) needs the patch files present before # install, or `pnpm install` aborts with ENOENT on the patch. COPY patches/ ./patches/ # Install production dependencies (tsx is now in prod deps) # Skip the root prepare script (husky is a devDep, not available in prod) RUN --mount=type=cache,id=pnpm-store,target=/root/.local/share/pnpm/store/v3 \ npm pkg delete scripts.prepare && \ pnpm install --frozen-lockfile --prod # Install Playwright Chromium for HTML-to-Image tool. # PLAYWRIGHT_BROWSERS_PATH puts browsers in a shared location so the # non-root snapotter user can find and execute them at runtime. # Use the workspace's pinned Playwright (not `npx playwright`, which fetches a # NEWER version and installs a chromium build the runtime playwright cannot # resolve) so the installed browser matches chromium.executablePath(). ENV PLAYWRIGHT_BROWSERS_PATH=/opt/playwright-browsers RUN pnpm --filter @snapotter/api exec playwright install chromium --with-deps && \ chmod -R a+rX /opt/playwright-browsers && \ rm -rf /tmp/* # Copy source code for API (tsx runs TS directly - no build step needed) COPY apps/api/src ./apps/api/src COPY apps/api/drizzle ./apps/api/drizzle COPY apps/api/static ./apps/api/static # Copy workspace packages source (referenced by API at runtime) COPY packages/shared/src ./packages/shared/src # The builder stage ran scripts/bake-analytics.mjs to bake the analytics config # (driven by SNAPOTTER_ANALYTICS). The line above re-copies the committed baked.ts # from the build context, which would clobber that bake and leave the API runtime # with analytics permanently off -- so SNAPOTTER_ANALYTICS had no effect on the API # (and, since the SPA reads /api/v1/config/analytics, no effect anywhere). Pull the # baked version from the builder so the build arg actually controls runtime analytics. COPY --from=builder /app/packages/shared/src/analytics/baked.ts ./packages/shared/src/analytics/baked.ts COPY packages/image-engine/src ./packages/image-engine/src COPY packages/media-engine/src ./packages/media-engine/src COPY packages/doc-engine/src ./packages/doc-engine/src COPY packages/ai/src ./packages/ai/src COPY packages/ai/python ./packages/ai/python COPY packages/enterprise/src ./packages/enterprise/src # Copy built frontend from builder stage COPY --from=builder /app/apps/web/dist ./apps/web/dist # Create required directories RUN mkdir -p /data /data/files /data/ai/models /data/ai/pip-cache /tmp/workspace # Environment defaults ENV PORT=1349 \ NODE_ENV=production \ STORAGE_MODE=local \ WORKSPACE_PATH=/tmp/workspace \ FILES_STORAGE_PATH=/data/files \ PYTHON_VENV_PATH=/data/ai/venv \ MODELS_PATH=/data/ai/models \ DATA_DIR=/data \ U2NET_HOME=/data/ai/models/rembg \ DEFAULT_THEME=light \ DEFAULT_LOCALE=en \ DEFAULT_TOOL_VIEW=sidebar \ FILE_MAX_AGE_HOURS=72 \ CLEANUP_INTERVAL_MINUTES=60 \ MAX_UPLOAD_SIZE_MB=0 \ MAX_BATCH_SIZE=0 \ CONCURRENT_JOBS=0 \ MAX_MEGAPIXELS=0 \ RATE_LIMIT_PER_MIN=0 \ MAX_USERS=0 \ MAX_WORKER_THREADS=0 \ PROCESSING_TIMEOUT_S=0 \ MAX_PIPELINE_STEPS=20 \ MAX_CANVAS_PIXELS=0 \ MAX_SVG_SIZE_MB=50 \ MAX_SPLIT_GRID=100 \ MAX_PDF_PAGES=0 \ SESSION_DURATION_HOURS=168 \ LOGIN_ATTEMPT_LIMIT=30 \ LOG_LEVEL=info \ LOG_DIR=/data/logs \ TRUST_PROXY=true \ OIDC_ENABLED=false \ EXTERNAL_URL= # COOKIE_SECRET is intentionally not baked in: the app auto-generates and persists one # on first boot if unset (see apps/api/src/index.ts). Override via runtime env to pin it. # NVIDIA Container Toolkit env vars (harmless on non-GPU systems) ENV NVIDIA_VISIBLE_DEVICES=all \ NVIDIA_DRIVER_CAPABILITIES=compute,utility # Suppress noisy ML library output in docker logs ENV PYTHONWARNINGS=default \ TF_CPP_MIN_LOG_LEVEL=3 \ PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK=True # Create non-root user for runtime RUN groupadd -r snapotter && useradd -r -g snapotter -d /app -s /sbin/nologin snapotter # /app and /opt/venv are read-only at runtime -> owned by snapotter. # /data and /tmp/workspace are written at runtime: make them group-0 (root group) # owned and group-writable with the setgid bit so the app can still write when the # container is launched under an arbitrary/foreign UID (Kubernetes runAsUser, # OpenShift, TrueNAS), which always lands in the root (GID 0) supplementary group. # The root entrypoint re-chowns these to snapotter for the default gosu path. RUN chown -R snapotter:snapotter /app /opt/venv && \ chmod -R a+rX /opt/venv && \ chown -R snapotter:0 /data /tmp/workspace && \ chmod -R g+rwX /data /tmp/workspace && \ find /data /tmp/workspace -type d -exec chmod g+s {} + # Entrypoint fixes volume permissions then drops to snapotter via gosu. # entrypoint-lib.sh holds the writability helpers it sources at startup. COPY docker/entrypoint.sh /usr/local/bin/entrypoint.sh COPY docker/entrypoint-lib.sh /usr/local/bin/entrypoint-lib.sh COPY docker/wait-for-postgres.mjs /app/docker/wait-for-postgres.mjs RUN chmod +x /usr/local/bin/entrypoint.sh EXPOSE 1349 HEALTHCHECK --interval=30s --timeout=5s --start-period=60s --retries=3 \ CMD curl -sf --max-time 5 http://localhost:1349/api/v1/health || exit 1 # tini as PID 1 for zombie reaping + signal forwarding ENTRYPOINT ["tini", "--", "entrypoint.sh"] CMD ["pnpm", "--filter", "@snapotter/api", "run", "start"]