PaperClipAI/.github/workflows/docker-cloud.yml

name: Docker cloud

on:
  workflow_dispatch:
  workflow_call:

permissions: {}

# Independent SHAs can build immediately on separate runners.
# Repeated requests for the same source serialize without cancelling a build.
# No mutable canary channel is promoted here; docker.yml owns that operation.
concurrency:
  group: docker-cloud-${{ github.sha }}
  cancel-in-progress: false

jobs:
  build-and-push-cloud:
    # Only canonical master builds can consume the release Fleet. The runner
    # group must also allow this workflow only at refs/heads/master.
    # Keep an operator switch for a full-run retry on GitHub-hosted runners.
    runs-on: ${{ vars.AWS_CLOUD_BUILDS_ENABLED == 'true' && github.repository == 'paperclipai/paperclip' && github.repository_id == '1170821064' && github.ref == 'refs/heads/master' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && 'runs-on/fleet=paperclip-cloud-build-x64/env=public-ci' || 'ubuntu-latest' }}
    # Fleet instances expire after 45 minutes, including bootstrap and cleanup.
    timeout-minutes: ${{ vars.AWS_CLOUD_BUILDS_ENABLED == 'true' && github.repository == 'paperclipai/paperclip' && github.repository_id == '1170821064' && github.ref == 'refs/heads/master' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && 40 || 60 }}
    permissions:
      contents: read
      packages: write
    steps:
      - name: Checkout
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          # Full history and tags so `git describe` below can compute the
          # release version to stamp into the image.
          fetch-depth: 0

      # `.git` is dockerignored, so a running image cannot derive its own
      # version and otherwise reports the source package.json placeholder in
      # analytics and the debug panel. Compute it here from the pristine
      # checkout (real CalVer drift from the nearest release tag) and pass it
      # into the build. Empty when no release tag is reachable — the server
      # then keeps its existing fallbacks.
      - name: Compute build version
        id: build-version
        run: |
          set -euo pipefail
          case "${GITHUB_REF}" in
            refs/tags/nightly/v*)
              # Lane tags carry the exact published version; stamp it verbatim
              # instead of describing drift from the nearest stable tag.
              version="${GITHUB_REF#refs/tags/nightly/v}"
              ;;
            refs/tags/beta/v*)
              version="${GITHUB_REF#refs/tags/beta/v}"
              ;;
            *)
              version="$(git describe --tags --match 'v*' --long --dirty 2>/dev/null || true)"
              ;;
          esac
          echo "version=${version}" >> "$GITHUB_OUTPUT"
          echo "Stamping build version: ${version:-<none>}"

      # ISO week stamp for the Dockerfile's tool layer: the layer caches
      # across commits and re-pulls the @latest CLI tools when the week rolls
      # over, instead of on every build.
      - name: Compute tool cache epoch
        id: tools-epoch
        run: echo "epoch=$(date -u +%G-W%V)" >> "$GITHUB_OUTPUT"

      # Each SHA exports its own cache. Import recent first-parent caches so
      # a late older build cannot overwrite a newer build's cache manifest.
      # The legacy ref keeps the first builds warm during the transition.
      - name: Select cloud cache ancestry
        id: cloud-cache
        env:
          CACHE_IMAGE: ghcr.io/${{ github.repository }}
        run: |
          set -euo pipefail
          {
            echo 'sources<<CACHE_SOURCES'
            for commit in $(git rev-list --first-parent --max-count=10 HEAD); do
              echo "type=registry,ref=$CACHE_IMAGE:buildcache-cloud-$commit"
            done
            echo "type=registry,ref=$CACHE_IMAGE:buildcache-cloud"
            echo 'CACHE_SOURCES'
          } >> "$GITHUB_OUTPUT"

      - name: Setup pnpm
        uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        with:
          version: 9.15.4
          run_install: false

      # No dependency cache here: this workflow publishes release images, and
      # restoring a shared Actions cache into the build inputs would let a
      # poisoned cache entry reach the published artifact.
      - name: Setup Node.js
        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - name: Refresh lockfile for Docker build context
        run: |
          set -euo pipefail
          pnpm install --resolution-only --ignore-scripts --no-frozen-lockfile

          changed="$(git status --porcelain)"
          if [ -z "$changed" ]; then
            echo "Lockfile already matches package metadata."
            exit 0
          fi

          if printf '%s\n' "$changed" | grep -Fvq ' pnpm-lock.yaml'; then
            echo "Unexpected files changed during lockfile refresh:"
            echo "$changed"
            exit 1
          fi

          echo "Using refreshed pnpm-lock.yaml in the Docker build context."

      - name: Free runner disk
        run: |
          set -euo pipefail
          echo "Disk before cleanup:"
          df -h

          # A measured hosted cloud build started with 86 GB available.
          # Keep ample headroom for BuildKit and image verification, but
          # avoid minutes deleting SDKs when neither filesystem needs space.
          minimum_free_kib=$((64 * 1024 * 1024))
          if docker_root="$(docker info --format '{{.DockerRootDir}}')" \
            && available_kib="$(df -Pk "$docker_root" "$GITHUB_WORKSPACE" | awk 'NR > 1 { rows++; if ($4 !~ /^[0-9]+$/) invalid = 1; if (min == "" || $4 < min) min = $4 } END { if (invalid || rows != 2) exit 1; print min }')" \
            && [[ "$available_kib" =~ ^[0-9]+$ ]] \
            && (( available_kib >= minimum_free_kib )); then
            echo "At least 64 GiB is available for Docker and the workspace; skipping cleanup."
            exit 0
          fi

          pnpm store prune || true
          sudo apt-get clean || true
          sudo rm -rf \
            /usr/share/dotnet \
            /usr/share/swift \
            /usr/local/lib/android \
            /usr/local/share/boost \
            /usr/local/share/powershell \
            /opt/ghc \
            /opt/hostedtoolcache/CodeQL \
            /opt/hostedtoolcache/PyPy \
            /opt/hostedtoolcache/Ruby || true
          docker system prune -af || true

          echo "Disk after cleanup:"
          df -h

      - name: Login to GitHub Container Registry
        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4

      # Deployment tooling reads these labels from the registry to verify an
      # image's schema expectations against a migrator before deploying it,
      # without pulling the image. The server refuses to start when the
      # database is missing bundled migrations, so orchestrators need a cheap
      # way to check image/migrator compatibility up front.
      - name: Compute schema migration labels
        id: schema
        run: |
          set -euo pipefail
          last=$(ls packages/db/src/migrations/*.sql | sed 's|.*/||' | LC_ALL=C sort | tail -1)
          count=$(ls packages/db/src/migrations/*.sql | wc -l | tr -d ' ')
          echo "last=${last}" >> "$GITHUB_OUTPUT"
          echo "count=${count}" >> "$GITHUB_OUTPUT"

      # Published under the same lane tag set as the self-hosted image, with a
      # `-cloud` suffix (nightly-cloud, latest-cloud, <version>-cloud,
      # sha-<short>-cloud). `:canary-cloud` follows the same retag-step
      # ownership rule as `:canary` above.
      - name: Docker meta (cloud)
        id: meta-cloud
        uses: docker/metadata-action@dc802804100637a589fabce1cb79ff13a1411302 # v6
        with:
          images: ghcr.io/${{ github.repository }}
          flavor: |
            suffix=-cloud,onlatest=true
          tags: |
            type=raw,value=nightly,enable=${{ startsWith(github.ref, 'refs/tags/nightly/v') }}
            type=raw,value=beta,enable=${{ startsWith(github.ref, 'refs/tags/beta/v') }}
            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/v') }}
            type=semver,pattern={{version}},enable=${{ startsWith(github.ref, 'refs/tags/v') }}
            type=semver,pattern={{major}}.{{minor}},enable=${{ startsWith(github.ref, 'refs/tags/v') }}
            type=sha
          labels: |
            io.github.paperclipai.schema.last-migration=${{ steps.schema.outputs.last }}
            io.github.paperclipai.schema.migration-count=${{ steps.schema.outputs.count }}

      - name: Build and push (cloud)
        id: build-cloud
        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
        with:
          context: .
          target: cloud
          # Space-separated sandbox-provider directory names to build into
          # the variant; add here when managed deployments need another.
          # CLOUD_BUNDLED_SERVER_DEPS names the optional peer packages the
          # variant installs from server/package.json's declared version;
          # add another name there when a managed tenant needs it.
          build-args: |
            USER_UID=1001
            USER_GID=1001
            CLOUD_BUNDLED_PLUGINS=daytona
            CLOUD_BUNDLED_SERVER_DEPS=@sentry/node
            PAPERCLIP_BUILD_VERSION=${{ steps.build-version.outputs.version }}
            PAPERCLIP_BUILD_COMMIT=${{ github.sha }}
            CLI_TOOLS_CACHE_EPOCH=${{ steps.tools-epoch.outputs.epoch }}
          # amd64 only, unlike the self-hosted image above: the cloud variant
          # is consumed exclusively by managed-deployment hosts, which run
          # amd64. The QEMU-emulated arm64 half dominated this job's wall
          # clock, and dropping it roughly halves time-to-deployable-image.
          platforms: linux/amd64
          push: true
          # Same-SHA builds serialize above; different SHAs never share a
          # writable cache ref. Registry layers are content-addressed and
          # shared even when cache manifests have separate tags.
          cache-from: ${{ steps.cloud-cache.outputs.sources }}
          cache-to: type=registry,ref=ghcr.io/${{ github.repository }}:buildcache-cloud-${{ github.sha }},mode=max
          tags: ${{ steps.meta-cloud.outputs.tags }}
          labels: ${{ steps.meta-cloud.outputs.labels }}

      # The cloud target installs @sentry/node at the version
      # server/package.json declares, into a directory the server's own
      # module resolution walks. Verify the image this job just pushed, not
      # a local build, so a build-cache or layer-ordering regression is
      # caught before any tenant runs the image.

      - name: Verify the pushed image resolves the declared Sentry version
        env:
          IMAGE: ghcr.io/${{ github.repository }}@${{ steps.build-cloud.outputs.digest }}
        run: |
          set -euo pipefail

          expected="$(node -e "process.stdout.write(require('./server/package.json').peerDependencies['@sentry/node'])")"
          test -n "$expected"

          installed="$(docker run --rm --pull always \
            -v "$PWD/scripts/assert-cloud-image-sentry.mjs:/app/server/.ci-sentry-probe.mjs:ro" \
            --entrypoint node "$IMAGE" /app/server/.ci-sentry-probe.mjs)"

          echo "Declared optional peer version: $expected"
          echo "Installed in the pushed image: $installed"
          if [ "$installed" != "$expected" ]; then
            echo "ERROR: the pushed image resolves @sentry/node@$installed, expected @sentry/node@$expected" >&2
            exit 1
          fi
          echo "The pushed image resolves the declared @sentry/node version."

      # Managed hosts run node as 1001:1001. Bake that identity into the image
      # so usermod does not walk the mounted home on every container start.
      # Check before the entrypoint can repair a wrongly built identity.
      - name: Verify cloud runtime user
        env:
          IMAGE: ghcr.io/${{ github.repository }}@${{ steps.build-cloud.outputs.digest }}
        run: |
          set -euo pipefail
          docker run --rm --entrypoint sh "$IMAGE" -ec '
            test "$(id -u node)" = 1001
            test "$(id -g node)" = 1001
            test "$USER_UID" = 1001
            test "$USER_GID" = 1001
          '
          docker run --rm -e USER_UID=1001 -e USER_GID=1001 "$IMAGE" sh -ec '
            test "$(id -u)" = 1001
            test "$(id -g)" = 1001
            test -w "$PAPERCLIP_HOME"
          '

      # Verify the independently published cloud image without waiting for
      # the self-hosted manifest job. The Sentry check already pulled it.
      - name: Verify cloud PID 1 reaps orphaned processes
        env:
          IMAGE: ghcr.io/${{ github.repository }}@${{ steps.build-cloud.outputs.digest }}
        run: docker run --rm -i "$IMAGE" sh -s < scripts/assert-orphan-reaping.sh

      # Cloud's commit resolver and preview-artifact planner use the full SHA.
      # Publish that address only after checking this build's exact digest.
      # Retagging reuses the registry manifest and does not rebuild the image.
      - name: Publish verified full-SHA cloud tag
        env:
          IMAGE: ghcr.io/${{ github.repository }}@${{ steps.build-cloud.outputs.digest }}
          FULL_SHA_TAG: ghcr.io/${{ github.repository }}:sha-${{ github.sha }}-cloud
        run: |
          set -euo pipefail
          revision="$(docker image inspect "$IMAGE" --format '{{ index .Config.Labels "org.opencontainers.image.revision" }}')"
          platform="$(docker image inspect "$IMAGE" --format '{{ .Os }}/{{ .Architecture }}')"
          test "$revision" = "$GITHUB_SHA"
          test "$platform" = linux/amd64
          docker buildx imagetools create --prefer-index=false --tag "$FULL_SHA_TAG" "$IMAGE"