thermograph/.forgejo/workflows/infra-sync.yml

name: Sync infra to hosts

# The infra DOMAIN's own pipeline (new with the monorepo -- the split era had
# no infra deploy workflow at all; infra changes rode along lazily with the
# next app deploy's `git reset`). On a push touching infra/**, SSH to every
# host, fast-forward each ENVIRONMENT's monorepo checkout and re-render that
# environment's env file from the SOPS vault -- so a compose edit or a secret
# rotation lands push-button instead of waiting for the next app deploy.
#
# Deliberately does NOT roll any service: image tags are the app domains'
# axis, not infra's. A compose or stack change that must recreate containers
# takes effect on the next app deploy, or a by-hand
# `SERVICE=all ... infra/deploy/deploy.sh` run (see that script's header).
#
# THREE CHECKOUTS, TWO HOSTS. This is the shape the vps1/vps2 split forces:
#
#   vps1  /opt/thermograph-dev    branch dev    -> /etc/thermograph.env
#   vps2  /opt/thermograph-beta   branch main   -> /etc/thermograph-beta.env
#   vps2  /opt/thermograph        branch main   -> /etc/thermograph.env
#
# The two checkouts on vps2 are separate directories on purpose: a `git reset
# --hard` for beta must not be able to move prod's tree, and each environment
# renders its own env file from its own vault file. Because the paths differ,
# the beta and prod jobs below can safely run at the same time on one box.
#
# Beta and prod both track `main` (infra is not environment-staged -- only app
# IMAGES are, via tags). Dev tracks `dev`, which is why this workflow now
# triggers on both branches: a dev-branch infra change has to reach the dev
# checkout, and only that one.
#
# Each `render_thermograph_secrets` call passes the environment name and the
# output path EXPLICITLY. It used to rely on the host's
# /etc/thermograph/secrets-env marker, which cannot answer the question on vps2
# -- one marker, two environments. Passing them here means a beta sync can
# never render prod's vault, and vice versa.

on:
  push:
    branches: [dev, main]
    paths: ['infra/**']
  workflow_dispatch: {}

jobs:
  sync-dev:
    # Only the dev branch feeds the dev checkout.
    if: github.ref_name == 'dev'
    runs-on: docker
    concurrency:
      group: infra-sync-dev
      cancel-in-progress: false
    steps:
      - name: Sync dev checkout on vps1 + re-render secrets
        uses: https://github.com/appleboy/ssh-action@v1.2.0
        with:
          host: ${{ secrets.VPS1_SSH_HOST }}
          username: ${{ secrets.VPS1_SSH_USER }}
          key: ${{ secrets.VPS1_SSH_KEY }}
          port: ${{ secrets.VPS1_SSH_PORT }}
          script: |
            set -euo pipefail
            cd /opt/thermograph-dev
            git fetch --prune origin dev
            git reset --hard origin/dev
            echo "synced to $(git log --oneline -1)"

            # RENDER ONLY IF THIS HOST IS ACTUALLY DEV.
            #
            # dev's env file is /etc/thermograph.env — the same path beta uses,
            # and during the vps1/vps2 cutover beta is STILL ON VPS1. Rendering
            # unconditionally would overwrite the live env file of the
            # environment currently serving beta.thermograph.org with dev's
            # credentials: beta's running containers would survive (env_file is
            # read at container start) and then come up wrong on its next
            # deploy, pointed at dev's database password.
            #
            # The host marker is the box's own statement of which environment it
            # is, and it is the right authority for "is it safe to write this
            # file here". It flips to `dev` in provision-dev.sh, which is run
            # only after beta has vacated. Until then this skips loudly rather
            # than failing: the checkout sync above is still useful and correct.
            marker=$(cat /etc/thermograph/secrets-env 2>/dev/null || true)
            if [ "$marker" != dev ]; then
              echo "!! /etc/thermograph/secrets-env says '${marker:-<unset>}', not 'dev'."
              echo "!! Skipping the secrets render — this host is not dev yet, and"
              echo "!! /etc/thermograph.env here belongs to '${marker:-another environment}'."
              exit 0
            fi
            if [ -f infra/deploy/render-secrets.sh ]; then
              . infra/deploy/render-secrets.sh
              # SKIP_COMMON is dev's standing rule, not a preference: common.yaml
              # is the fleet's shared production credential set, and vps1 also
              # runs Forgejo and its CI. See render-secrets.sh.
              THERMOGRAPH_SECRETS_SKIP_COMMON=1 \
                render_thermograph_secrets /opt/thermograph-dev/infra dev /etc/thermograph.env
            fi

  sync-beta:
    if: github.ref_name == 'main'
    runs-on: docker
    concurrency:
      group: infra-sync-beta
      cancel-in-progress: false
    steps:
      - name: Sync beta checkout on vps2 + re-render secrets
        uses: https://github.com/appleboy/ssh-action@v1.2.0
        with:
          host: ${{ secrets.VPS2_SSH_HOST }}
          username: ${{ secrets.VPS2_SSH_USER }}
          key: ${{ secrets.VPS2_SSH_KEY }}
          port: ${{ secrets.VPS2_SSH_PORT }}
          script: |
            set -euo pipefail
            cd /opt/thermograph-beta
            git fetch --prune origin main
            git reset --hard origin/main
            if [ -f infra/deploy/render-secrets.sh ]; then
              . infra/deploy/render-secrets.sh
              render_thermograph_secrets /opt/thermograph-beta/infra beta /etc/thermograph-beta.env
            fi
            echo "synced to $(git log --oneline -1)"

  sync-prod:
    if: github.ref_name == 'main'
    runs-on: docker
    concurrency:
      group: infra-sync-prod
      cancel-in-progress: false
    steps:
      - name: Sync prod checkout on vps2 + re-render secrets
        uses: https://github.com/appleboy/ssh-action@v1.2.0
        with:
          host: ${{ secrets.VPS2_SSH_HOST }}
          username: ${{ secrets.VPS2_SSH_USER }}
          key: ${{ secrets.VPS2_SSH_KEY }}
          port: ${{ secrets.VPS2_SSH_PORT }}
          script: |
            set -euo pipefail
            cd /opt/thermograph
            git fetch --prune origin main
            git reset --hard origin/main
            if [ -f infra/deploy/render-secrets.sh ]; then
              . infra/deploy/render-secrets.sh
              render_thermograph_secrets /opt/thermograph/infra prod /etc/thermograph.env
            fi
            echo "synced to $(git log --oneline -1)"