fix(docker): overhaul fragile setup, adopt proven container patterns (#2716)

Split fake multi-stage Dockerfile into independent CI builder and runtime images. Add proper entrypoint with UID/GID remapping via PUID/PGID, sentinel-based first-boot bootstrap, pre-creation of critical file targets, and signal-forwarding privilege drop via gosu. Standardize on Node 24, split compose into minimal + full reference. Closes #9
2026-03-26 18:10:49 -04:00 · 2026-03-26 18:10:49 -04:00 · 0e07c647c5
commit 0e07c647c5
parent a952391b33
11 changed files with 299 additions and 76 deletions
--- a/25
+++ b/25
@ -1,30 +1,9 @@
 # ──────────────────────────────────────────────
-# Stage 1: CI Builder
-# Image: ghcr.io/gsd-build/gsd-ci-builder
-# Used by: pipeline.yml Dev stage
-# ──────────────────────────────────────────────
-FROM node:24-bookworm AS builder
-
-# Rust toolchain (stable, minimal profile)
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Cross-compilation for linux-arm64
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    gcc-aarch64-linux-gnu \
-    g++-aarch64-linux-gnu \
-    && rustup target add aarch64-unknown-linux-gnu \
-    && rm -rf /var/lib/apt/lists/*
-
-# Verify toolchain
-RUN node --version && rustc --version && cargo --version
-
-# ──────────────────────────────────────────────
-# Stage 2: Runtime
+# Runtime
 # Image: ghcr.io/gsd-build/gsd-pi
 # Used by: end users via docker run
 # ──────────────────────────────────────────────
-FROM node:24-slim AS runtime
+FROM node:24-slim

 # Git is required for GSD's git operations
 RUN apt-get update && apt-get install -y --no-install-recommends \
--- a/docker/.env.example
+++ b/docker/.env.example
@ -3,6 +3,12 @@
 # Copy this file to .env and fill in your keys.
 # ──────────────────────────────────────────────

+# ── Container User Identity ──
+# Match your host UID/GID to avoid permission issues on bind mounts.
+# Run `id -u` and `id -g` on your host to find the right values.
+PUID=1000
+PGID=1000
+
 # ── LLM Provider API Keys (at least one required) ──

 # Anthropic (Claude)
--- a/docker/Dockerfile.ci-builder
+++ b/docker/Dockerfile.ci-builder
@ -0,0 +1,20 @@
+# ──────────────────────────────────────────────
+# CI Builder
+# Image: ghcr.io/gsd-build/gsd-ci-builder
+# Used by: pipeline.yml Dev stage
+# ──────────────────────────────────────────────
+FROM node:24-bookworm
+
+# Rust toolchain (stable, minimal profile)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+# Cross-compilation for linux-arm64
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc-aarch64-linux-gnu \
+    g++-aarch64-linux-gnu \
+    && rustup target add aarch64-unknown-linux-gnu \
+    && rm -rf /var/lib/apt/lists/*
+
+# Verify toolchain
+RUN node --version && rustc --version && cargo --version
--- a/docker/Dockerfile.sandbox
+++ b/docker/Dockerfile.sandbox
@ -4,7 +4,7 @@
 # Purpose: Isolated environment for GSD auto mode
 # Usage: docker sandbox create --template ./docker
 # ──────────────────────────────────────────────
-FROM node:22-bookworm-slim
+FROM node:24-bookworm-slim

 # System dependencies required by GSD
 RUN apt-get update && apt-get install -y --no-install-recommends \
@ -12,6 +12,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    ca-certificates \
    openssh-client \
+    gosu \
    && rm -rf /var/lib/apt/lists/*

 # Install GSD globally — version controlled via build arg
@ -29,10 +30,13 @@ RUN mkdir -p /home/gsd/.gsd && chown -R gsd:gsd /home/gsd/.gsd
 WORKDIR /workspace
 RUN chown gsd:gsd /workspace

-USER gsd
+# Entrypoint handles UID/GID remapping, bootstrap, and drops to gsd user
+COPY entrypoint.sh /usr/local/bin/entrypoint.sh
+COPY bootstrap.sh /usr/local/bin/bootstrap.sh
+RUN chmod +x /usr/local/bin/entrypoint.sh /usr/local/bin/bootstrap.sh

 # Expose default GSD web UI port
 EXPOSE 3000

-ENTRYPOINT ["gsd"]
-CMD ["--help"]
+ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
+CMD ["gsd", "--help"]
--- a/docker/README.md
+++ b/docker/README.md
@ -7,6 +7,22 @@ Run GSD auto mode inside an isolated Docker sandbox so it cannot touch your host
 - Docker Desktop 4.58+ (macOS or Windows; Linux support is experimental)
 - At least one LLM provider API key

+## Docker Images
+
+| File | Purpose |
+|------|---------|
+| `Dockerfile.sandbox` | Runtime sandbox with entrypoint (UID remapping, bootstrap) |
+| `Dockerfile.ci-builder` | CI builds — includes build tools, no entrypoint magic |
+
+## Compose Files
+
+| File | Purpose |
+|------|---------|
+| `docker-compose.yaml` | Minimal zero-config setup — just works with sensible defaults |
+| `docker-compose.full.yaml` | Fully documented reference with all options, resource limits, health checks |
+
+Start with `docker-compose.yaml`. Copy options from `docker-compose.full.yaml` when you need them.
+
 ## Quick Start

 ### Option A: Docker Sandbox CLI (recommended)
@ -34,7 +50,7 @@ cp docker/.env.example docker/.env
 # Edit docker/.env with your keys

 # 2. Start the sandbox
-docker compose -f docker/docker-compose.yml up -d
+docker compose -f docker/docker-compose.yaml up -d

 # 3. Shell into the container
 docker exec -it gsd-sandbox bash
@ -43,6 +59,29 @@ docker exec -it gsd-sandbox bash
 gsd auto "implement the feature described in issue #42"
 ```

+## UID/GID Remapping
+
+The entrypoint handles UID/GID remapping via `PUID` and `PGID` environment variables. This avoids permission issues on bind-mounted volumes by matching the container's `gsd` user to your host UID/GID.
+
+```bash
+# Find your host UID/GID
+id -u  # PUID
+id -g  # PGID
+```
+
+Set these in your `.env` file or in the `environment` section of the compose file. Defaults to `1000:1000`.
+
+## Entrypoint Behavior
+
+The container entrypoint (`entrypoint.sh`) runs four steps on every start:
+
+1. **UID/GID remapping** — adjusts the `gsd` user to match `PUID`/`PGID`
+2. **Pre-create critical files** — prevents Docker bind-mount from creating directories where files are expected
+3. **Sentinel-based bootstrap** — runs `bootstrap.sh` exactly once on first boot
+4. **Drop privileges** — `exec gosu gsd` for proper PID 1 signal forwarding
+
+No hardcoded `user:` directive in compose — the entrypoint starts as root, remaps, then drops to `gsd`.
+
 ## Two-Terminal Workflow

 GSD's recommended workflow uses two terminals — one for auto mode, one for interactive discussion:
@ -85,7 +124,7 @@ If you restrict outbound network access in your sandbox, GSD needs these endpoin
 Build with a specific GSD version:

 ```bash
-docker compose -f docker/docker-compose.yml build --build-arg GSD_VERSION=2.43.0
+docker compose -f docker/docker-compose.yaml build --build-arg GSD_VERSION=2.51.0
 ```

 ## Cleanup
@ -95,7 +134,7 @@ docker compose -f docker/docker-compose.yml build --build-arg GSD_VERSION=2.43.0
 docker sandbox rm gsd-sandbox

 # Docker Compose
-docker compose -f docker/docker-compose.yml down -v
+docker compose -f docker/docker-compose.yaml down -v
 ```

 ## Known Limitations
--- a/docker/bootstrap.sh
+++ b/docker/bootstrap.sh
@ -0,0 +1,27 @@
+#!/bin/bash
+set -e
+
+# ──────────────────────────────────────────────
+# GSD First-Boot Bootstrap
+#
+# Runs once on initial container creation.
+# Called by entrypoint.sh as the gsd user.
+#
+# This script is idempotent — safe to run multiple
+# times, but the sentinel in entrypoint.sh ensures
+# it only runs once in practice.
+# ──────────────────────────────────────────────
+
+# ── Git Identity ────────────────────────────────────────
+# Without this, git commits inside the container will fail
+# or use garbage defaults.
+
+if [ -n "${GIT_AUTHOR_NAME}" ]; then
+    git config --global user.name "${GIT_AUTHOR_NAME}"
+fi
+
+if [ -n "${GIT_AUTHOR_EMAIL}" ]; then
+    git config --global user.email "${GIT_AUTHOR_EMAIL}"
+fi
+
+echo "Bootstrap complete."
--- a/docker/docker-compose.full.yaml
+++ b/docker/docker-compose.full.yaml
@ -0,0 +1,61 @@
+services:
+  gsd:
+    build:
+      context: .                        # Build context is the docker/ directory
+      dockerfile: Dockerfile.sandbox    # Runtime sandbox image with entrypoint
+      args:
+        GSD_VERSION: latest             # Pin a specific version: GSD_VERSION=2.51.0
+
+    container_name: gsd-sandbox
+
+    ports:
+      - "3000:3000"                     # GSD web UI
+
+    volumes:
+      - ../:/workspace                  # Project root mounted into the container
+      - gsd-state:/home/gsd/.gsd        # Persistent GSD state across restarts
+      # - ~/.ssh:/home/gsd/.ssh:ro      # SSH keys for git operations (read-only)
+      # - ~/.gitconfig:/home/gsd/.gitconfig:ro  # Host git config
+
+    env_file:
+      - .env                            # API keys and secrets (see .env.example)
+
+    environment:
+      - NODE_ENV=development
+      # UID/GID remapping — match your host user to avoid permission issues
+      # on bind-mounted volumes. The entrypoint remaps the container's gsd
+      # user to these IDs at startup. Run `id -u` / `id -g` to find yours.
+      - PUID=1000
+      - PGID=1000
+      # Git identity inside the container (overrides .env if set here)
+      # - GIT_AUTHOR_NAME=Your Name
+      # - GIT_AUTHOR_EMAIL=you@example.com
+
+    stdin_open: true                    # Keep stdin open for interactive use
+    tty: true                           # Allocate a pseudo-TTY
+
+    # Health check — verify GSD is installed and responsive
+    healthcheck:
+      test: ["CMD", "gsd", "--version"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+      start_period: 10s
+
+    # Resource limits — uncomment to constrain container resources
+    # deploy:
+    #   resources:
+    #     limits:
+    #       cpus: "4.0"
+    #       memory: 8G
+    #     reservations:
+    #       cpus: "1.0"
+    #       memory: 2G
+
+    # Network mode — uncomment ONE if you need host networking
+    # network_mode: host               # Full host network access (no port mapping needed)
+    # network_mode: bridge             # Default Docker bridge (already the default)
+
+volumes:
+  gsd-state:
+    driver: local
--- a/docker/docker-compose.yaml
+++ b/docker/docker-compose.yaml
@ -0,0 +1,23 @@
+services:
+  gsd:
+    build:
+      context: .
+      dockerfile: Dockerfile.sandbox
+      args:
+        GSD_VERSION: latest
+    container_name: gsd-sandbox
+    ports:
+      - "3000:3000"
+    volumes:
+      - ../:/workspace
+      - gsd-state:/home/gsd/.gsd
+    env_file:
+      - .env
+    environment:
+      - NODE_ENV=development
+    stdin_open: true
+    tty: true
+
+volumes:
+  gsd-state:
+    driver: local
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@ -1,34 +0,0 @@
-# Docker Compose for running GSD in a sandbox
-# Usage: docker compose -f docker/docker-compose.yml up
-#
-# Copy docker/.env.example to docker/.env and fill in your API keys first.
-# See docker/README.md for full setup instructions.
-
-services:
-  gsd:
-    build:
-      context: .
-      dockerfile: Dockerfile.sandbox
-      args:
-        GSD_VERSION: latest
-    container_name: gsd-sandbox
-    ports:
-      - "3000:3000"
-    volumes:
-      # Sync project code into the sandbox
-      - ../:/workspace
-      # Persistent GSD state across container restarts
-      - gsd-state:/home/gsd/.gsd
-    env_file:
-      - .env
-    environment:
-      - NODE_ENV=development
-    user: "1000:1000"
-    stdin_open: true
-    tty: true
-    # Override entrypoint for interactive shell access
-    # entrypoint: /bin/bash
-
-volumes:
-  gsd-state:
-    driver: local
--- a/docker/entrypoint.sh
+++ b/docker/entrypoint.sh
@ -0,0 +1,81 @@
+#!/bin/bash
+set -e
+
+# ──────────────────────────────────────────────
+# GSD Container Entrypoint
+#
+# Responsibilities:
+#   1. UID/GID remapping — match host user via PUID/PGID
+#   2. Pre-create critical files — prevent Docker bind-mount
+#      from creating directories where files are expected
+#   3. Sentinel-based bootstrap — one-time first-boot setup
+#   4. Signal forwarding — exec into the final process
+# ──────────────────────────────────────────────
+
+GSD_USER="gsd"
+GSD_HOME="/home/${GSD_USER}"
+GSD_DIR="${GSD_HOME}/.gsd"
+
+# ── 1. UID/GID Remapping ────────────────────────────────
+# Accept PUID/PGID from the environment so the container
+# can run with the same UID/GID as the host user, avoiding
+# permission headaches on bind-mounted volumes.
+
+PUID="${PUID:-1000}"
+PGID="${PGID:-1000}"
+
+CURRENT_UID=$(id -u "${GSD_USER}")
+CURRENT_GID=$(id -g "${GSD_USER}")
+
+REMAPPED=0
+
+if [ "${PGID}" != "${CURRENT_GID}" ]; then
+    groupmod -o -g "${PGID}" "${GSD_USER}"
+    REMAPPED=1
+fi
+
+if [ "${PUID}" != "${CURRENT_UID}" ]; then
+    usermod -o -u "${PUID}" "${GSD_USER}"
+    REMAPPED=1
+fi
+
+# Fix ownership only when UID/GID actually changed
+if [ "${REMAPPED}" -eq 1 ]; then
+    chown -R "${PUID}:${PGID}" "${GSD_HOME}"
+    chown "${PUID}:${PGID}" /workspace
+fi
+
+# ── 2. Pre-create Critical Files ────────────────────────
+# Docker bind-mounts will create a *directory* if the target
+# path doesn't exist. We need these to be files, so touch
+# them before Docker gets a chance to mangle things.
+
+mkdir -p "${GSD_DIR}"
+
+if [ ! -f "${GSD_DIR}/settings.json" ]; then
+    echo '{}' > "${GSD_DIR}/settings.json"
+fi
+
+chown "${PUID}:${PGID}" "${GSD_DIR}" "${GSD_DIR}/settings.json"
+
+# ── 3. Sentinel-based Bootstrap ─────────────────────────
+# Run first-boot setup exactly once. Subsequent container
+# starts (or restarts) skip this entirely.
+
+SENTINEL="${GSD_DIR}/.bootstrapped"
+
+if [ ! -f "${SENTINEL}" ]; then
+    if [ -x /usr/local/bin/bootstrap.sh ]; then
+        # Run bootstrap as the gsd user so files get correct ownership
+        gosu "${GSD_USER}" /usr/local/bin/bootstrap.sh
+    fi
+    touch "${SENTINEL}"
+    chown "${PUID}:${PGID}" "${SENTINEL}"
+fi
+
+# ── 4. Drop Privileges & Exec ──────────────────────────
+# Replace this shell process with the final command running
+# as the gsd user. exec + gosu = proper PID 1 = proper
+# signal forwarding (SIGTERM, SIGINT, etc.).
+
+exec gosu "${GSD_USER}" "$@"
--- a/src/tests/docker-template.test.ts
+++ b/src/tests/docker-template.test.ts
@ -15,9 +15,9 @@ function readFile(relativePath: string): string {

 // ── Dockerfile.sandbox ──

-test("docker/Dockerfile.sandbox exists and uses Node 22 base", () => {
+test("docker/Dockerfile.sandbox exists and uses Node 24 base", () => {
  const content = readFile("docker/Dockerfile.sandbox");
-  assert.match(content, /FROM node:22/);
+  assert.match(content, /FROM node:24/);
 });

 test("docker/Dockerfile.sandbox installs gsd-pi globally", () => {
@ -28,7 +28,6 @@ test("docker/Dockerfile.sandbox installs gsd-pi globally", () => {
 test("docker/Dockerfile.sandbox creates a non-root user", () => {
  const content = readFile("docker/Dockerfile.sandbox");
  assert.match(content, /useradd/);
-  assert.match(content, /USER gsd/);
 });

 test("docker/Dockerfile.sandbox exposes port 3000", () => {
@ -41,29 +40,47 @@ test("docker/Dockerfile.sandbox installs git", () => {
  assert.match(content, /git/);
 });

-// ── docker-compose.yml ──
+// ── docker-compose.yaml (minimal) ──

-test("docker/docker-compose.yml exists and defines gsd service", () => {
-  const content = readFile("docker/docker-compose.yml");
+test("docker/docker-compose.yaml exists and defines gsd service", () => {
+  const content = readFile("docker/docker-compose.yaml");
  assert.match(content, /services:/);
  assert.match(content, /gsd:/);
 });

-test("docker/docker-compose.yml mounts workspace volume", () => {
-  const content = readFile("docker/docker-compose.yml");
+test("docker/docker-compose.yaml mounts workspace volume", () => {
+  const content = readFile("docker/docker-compose.yaml");
  assert.match(content, /\/workspace/);
 });

-test("docker/docker-compose.yml references Dockerfile.sandbox", () => {
-  const content = readFile("docker/docker-compose.yml");
+test("docker/docker-compose.yaml references Dockerfile.sandbox", () => {
+  const content = readFile("docker/docker-compose.yaml");
  assert.match(content, /Dockerfile\.sandbox/);
 });

-test("docker/docker-compose.yml maps port 3000", () => {
-  const content = readFile("docker/docker-compose.yml");
+test("docker/docker-compose.yaml maps port 3000", () => {
+  const content = readFile("docker/docker-compose.yaml");
  assert.match(content, /3000:3000/);
 });

+test("docker/docker-compose.yaml has no hardcoded user directive", () => {
+  const content = readFile("docker/docker-compose.yaml");
+  assert.doesNotMatch(content, /^\s+user:/m);
+});
+
+// ── docker-compose.full.yaml (reference) ──
+
+test("docker/docker-compose.full.yaml exists with health check", () => {
+  const content = readFile("docker/docker-compose.full.yaml");
+  assert.match(content, /healthcheck:/);
+});
+
+test("docker/docker-compose.full.yaml documents PUID/PGID", () => {
+  const content = readFile("docker/docker-compose.full.yaml");
+  assert.match(content, /PUID/);
+  assert.match(content, /PGID/);
+});
+
 // ── .env.example ──

 test("docker/.env.example exists and lists ANTHROPIC_API_KEY", () => {