fix(docker): use multi-stage build to remove build-essential from runtime image (#1846)

* fix(docker): use multi-stage build to remove build-essential from runtime image

The build-essential toolchain (~200 MB) was only needed for compiling
native Python extensions during `uv sync` but remained in the final
image, increasing size and attack surface. Split the Dockerfile into
a builder stage (with build-essential) and a clean runtime stage that
copies only the compiled artifacts, Node.js, Docker CLI, and uv.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(docker): add dev stage and pin docker:cli per review feedback

Address Copilot review comments:
- Add a `dev` build stage (FROM builder) that retains build-essential
  so startup-time `uv sync` in dev containers can compile from source
- Update docker-compose-dev.yaml to use `target: dev` for gateway and
  langgraph services
- Keep the clean runtime stage (no build-essential) as the default
  final stage for production builds

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

backend/Dockerfile

@@ -1,10 +1,14 @@
-# Backend Development Dockerfile
+# Backend Dockerfile — multi-stage build
+# Stage 1 (builder): compiles native Python extensions with build-essential
+# Stage 2 (dev):     retains toolchain for dev containers (uv sync at startup)
+# Stage 3 (runtime): clean image without compiler toolchain for production
 
 # UV source image (override for restricted networks that cannot reach ghcr.io)
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.7.20
 FROM ${UV_IMAGE} AS uv-source
 
-FROM python:3.12-slim-bookworm
+# ── Stage 1: Builder ──────────────────────────────────────────────────────────
+FROM python:3.12-slim-bookworm AS builder
 
 ARG NODE_MAJOR=22
 ARG APT_MIRROR
@@ -16,7 +20,7 @@ RUN if [ -n "${APT_MIRROR}" ]; then \
       sed -i "s|deb.debian.org|${APT_MIRROR}|g" /etc/apt/sources.list 2>/dev/null || true; \
     fi
 
-# Install system dependencies + Node.js (provides npx for MCP servers)
+# Install build tools + Node.js (build-essential needed for native Python extensions)
 RUN apt-get update && apt-get install -y \
     curl \
     build-essential \
@@ -29,6 +33,41 @@ RUN apt-get update && apt-get install -y \
     && apt-get install -y nodejs \
     && rm -rf /var/lib/apt/lists/*
 
+# Install uv (source image overridable via UV_IMAGE build arg)
+COPY --from=uv-source /uv /uvx /usr/local/bin/
+
+# Set working directory
+WORKDIR /app
+
+# Copy backend source code
+COPY backend ./backend
+
+# Install dependencies with cache mount
+RUN --mount=type=cache,target=/root/.cache/uv \
+    sh -c "cd backend && UV_INDEX_URL=${UV_INDEX_URL:-https://pypi.org/simple} uv sync"
+
+# ── Stage 2: Dev ──────────────────────────────────────────────────────────────
+# Retains compiler toolchain from builder so startup-time `uv sync` can build
+# source distributions in development containers.
+FROM builder AS dev
+
+# Install Docker CLI (for DooD: allows starting sandbox containers via host Docker socket)
+COPY --from=docker:cli /usr/local/bin/docker /usr/local/bin/docker
+
+EXPOSE 8001 2024
+
+CMD ["sh", "-c", "cd backend && PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001"]
+
+# ── Stage 3: Runtime ──────────────────────────────────────────────────────────
+# Clean image without build-essential — reduces size (~200 MB) and attack surface.
+FROM python:3.12-slim-bookworm
+
+# Copy Node.js runtime from builder (provides npx for MCP servers)
+COPY --from=builder /usr/bin/node /usr/bin/node
+COPY --from=builder /usr/lib/node_modules /usr/lib/node_modules
+RUN ln -s ../lib/node_modules/npm/bin/npm-cli.js /usr/bin/npm \
+    && ln -s ../lib/node_modules/npm/bin/npx-cli.js /usr/bin/npx
+
 # Install Docker CLI (for DooD: allows starting sandbox containers via host Docker socket)
 COPY --from=docker:cli /usr/local/bin/docker /usr/local/bin/docker
 
@@ -38,12 +77,8 @@ COPY --from=uv-source /uv /uvx /usr/local/bin/
 # Set working directory
 WORKDIR /app
 
-# Copy frontend source code
-COPY backend ./backend
-
-# Install dependencies with cache mount
-RUN --mount=type=cache,target=/root/.cache/uv \
-    sh -c "cd backend && UV_INDEX_URL=${UV_INDEX_URL:-https://pypi.org/simple} uv sync"
+# Copy backend with pre-built virtualenv from builder
+COPY --from=builder /app/backend ./backend
 
 # Expose ports (gateway: 8001, langgraph: 2024)
 EXPOSE 8001 2024

docker/docker-compose-dev.yaml

@@ -113,6 +113,7 @@ services:
     build:
       context: ../
       dockerfile: backend/Dockerfile
+      target: dev
       # cache_from disabled - requires manual setup: mkdir -p /tmp/docker-cache-gateway
       args:
         APT_MIRROR: ${APT_MIRROR:-}
@@ -169,6 +170,7 @@ services:
     build:
       context: ../
       dockerfile: backend/Dockerfile
+      target: dev
       # cache_from disabled - requires manual setup: mkdir -p /tmp/docker-cache-langgraph
       args:
         APT_MIRROR: ${APT_MIRROR:-}