molecule-core/.github/workflows/publish-workspace-server-image.yml

name: publish-workspace-server-image

# Builds and pushes Docker images to GHCR when staging is promoted to main.
# PRs target staging (default branch). Only main push triggers production builds.
# EC2 tenant instances pull the tenant image from GHCR.

on:
  push:
    branches: [main]
    paths:
      - 'workspace-server/**'
      - 'canvas/**'
      - 'manifest.json'
      - '.github/workflows/publish-platform-image.yml'
  workflow_dispatch:

permissions:
  contents: read
  packages: write

env:
  IMAGE_NAME: ghcr.io/molecule-ai/platform
  TENANT_IMAGE_NAME: ghcr.io/molecule-ai/platform-tenant

jobs:
  build-and-push:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Checkout sibling plugin repo
        # workspace-server/Dockerfile expects
        # ./molecule-ai-plugin-github-app-auth at build-context root because
        # the Go module has a `replace` directive pointing at /plugin inside
        # the image. Pre-repo-split the plugin lived in the monorepo; the
        # 2026-04-18 restructure moved it out but didn't add this clone step
        # — which is why publish was failing after that restructure.
        #
        # Uses a fine-grained PAT (PLUGIN_REPO_PAT) because the plugin repo
        # is private and the default GITHUB_TOKEN is scoped to THIS repo.
        # The PAT needs Contents:Read on Molecule-AI/molecule-ai-plugin-
        # github-app-auth. Falls back to the default token for the (rare)
        # case where an operator made the plugin repo public.
        uses: actions/checkout@v4
        with:
          repository: Molecule-AI/molecule-ai-plugin-github-app-auth
          path: molecule-ai-plugin-github-app-auth
          token: ${{ secrets.PLUGIN_REPO_PAT || secrets.GITHUB_TOKEN }}

      - name: Log in to GHCR
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

      - name: Compute tags
        id: tags
        run: |
          echo "sha=${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"          

      # Canary-gated release: we publish :staging-<sha> ONLY here. The
      # :latest tag (which existing prod tenants auto-pull every 5 min)
      # is promoted by .github/workflows/canary-verify.yml after the
      # staging canary fleet green-lights this digest.
      # That means:
      #   - Every main merge produces a :staging-<sha> image
      #   - Canary tenants (configured to pull :staging-<sha>) pick it up
      #   - canary-verify.yml runs smoke tests against them
      #   - On green → canary-verify retags :staging-<sha> → :latest
      #   - On red → :latest stays on the prior good digest, prod is safe
      # Every push of :staging-<sha> also retags the same digest as
      # :staging-latest so staging CP (which pins TENANT_IMAGE at
      # :staging-latest) picks up new builds automatically — no more manual
      # Railway env-var edits. Prod's :latest retag still happens in
      # canary-verify.yml after the canary fleet greenlights this digest;
      # :staging-latest is strictly the "most recent main build," not a
      # canary-verified promotion.
      #
      # Before this, TENANT_IMAGE on Railway staging was pinned to a static
      # :staging-<sha> and drifted months behind (2026-04-24 incident:
      # canary tenant ran :staging-a14cf86, 10 days stale, which lacked
      # applyRuntimeModelEnv and caused every E2E to route hermes+openai
      # through openrouter → 401). See issue filed with this PR.
      - name: Build & push platform image to GHCR (staging-<sha> + staging-latest)
        uses: docker/build-push-action@v6
        with:
          context: .
          file: ./workspace-server/Dockerfile
          platforms: linux/amd64
          push: true
          tags: |
            ${{ env.IMAGE_NAME }}:staging-${{ steps.tags.outputs.sha }}
            ${{ env.IMAGE_NAME }}:staging-latest            
          cache-from: type=gha
          cache-to: type=gha,mode=max
          labels: |
            org.opencontainers.image.source=https://github.com/${{ github.repository }}
            org.opencontainers.image.revision=${{ github.sha }}
            org.opencontainers.image.description=Molecule AI platform (Go API server) — pending canary verify            

      - name: Build & push tenant image to GHCR (staging-<sha> + staging-latest)
        uses: docker/build-push-action@v6
        with:
          context: .
          file: ./workspace-server/Dockerfile.tenant
          platforms: linux/amd64
          push: true
          tags: |
            ${{ env.TENANT_IMAGE_NAME }}:staging-${{ steps.tags.outputs.sha }}
            ${{ env.TENANT_IMAGE_NAME }}:staging-latest            
          cache-from: type=gha
          cache-to: type=gha,mode=max
          # Canvas uses same-origin fetches. The tenant Go platform
          # reverse-proxies /cp/* to the SaaS CP via its CP_UPSTREAM_URL
          # env; the tenant's /canvas/viewport, /approvals/pending,
          # /org/templates etc. live on the tenant platform itself.
          # Both legs share one origin (the tenant subdomain) so
          # PLATFORM_URL="" forces canvas to fetch paths as relative,
          # which land same-origin.
          #
          # Self-hosted / private-label deployments override this at
          # build time with a specific backend (e.g. local dev:
          # NEXT_PUBLIC_PLATFORM_URL=http://localhost:8080).
          build-args: |
            NEXT_PUBLIC_PLATFORM_URL=            
          labels: |
            org.opencontainers.image.source=https://github.com/${{ github.repository }}
            org.opencontainers.image.revision=${{ github.sha }}
            org.opencontainers.image.description=Molecule AI tenant platform + canvas — pending canary verify