# CI: every push of a branch runs the checks of the pre-push hook (tool/check.dart, every app's and
# shared package's); a push to main is then deployed to learn.halkyon.eu (deploy/redeploy.sh).
# Both jobs run on the runner on learn.halkyon.eu's server, directly on the host as an
# unprivileged user (deploy/runner/). A commit that passed the checks before isn't checked again
# (see "Checked before?").
#
# Pushes only, no pull requests: a pull request from a fork would run its own code on
# the production server's runner.
name: CI

on:
  push:
    # Branches only, not tags: a release pushes main and then its tag, both on the same
    # commit, and the tag's run would check that commit a second time while main's still
    # runs ("Checked before?" knows only runs that finished). A tag deploys nothing.
    branches: ['**']
  # Runs the workflow again from the web UI, e.g. to retry a failed deploy.
  workflow_dispatch:

jobs:
  check:
    runs-on: sahaquiel
    # A warm run took 42 minutes with Train's packages (30 Oct 2026), a new Flutter more:
    # the limit only catches a hung job.
    timeout-minutes: 60
    env:
      # The Flutter the app is developed with; move it together with the local one.
      FLUTTER_VERSION: 3.47.8
      # The Serverpod CLI, for the generated-code check: the servers' Serverpod version
      # (every package pins it; the root's tests hold it to the lock); move it together
      # with them.
      SERVERPOD_VERSION: 4.0.4
    steps:
      # Before anything else runs, the job proves it can neither see nor reach production
      # (the runner's sandbox, deploy/runner/). If it can, nothing else should run.
      - name: Sandbox
        run: |
          fail() { echo "The runner's sandbox leaks: $*" >&2; exit 1; }
          # Only the runner's own processes are visible. A container's process shows up
          # (in a process namespace of its own) if it runs under the runner's user ID,
          # and then its environment and files are readable too.
          [ "$(ps -e -o uid= | sort -u | wc -l)" -eq 1 ] || fail "other users' processes are visible"
          namespaces=$(for p in /proc/[0-9]*; do readlink "$p/ns/pid"; done 2>/dev/null | sort -u | wc -l)
          [ "$namespaces" -le 1 ] || fail "processes of $namespaces process namespaces are visible"
          # deploy's home (.env, the checkout, the dumps) and the Docker socket are out of
          # reach.
          [ ! -e /home/deploy ] || fail "/home/deploy is visible"
          { [ ! -r /run/docker.sock ] && [ ! -w /run/docker.sock ]; } || fail "the Docker socket is usable"
          # Docker's networks, where the database listens, are unreachable. Caddy listens on
          # every address of the host, the Docker bridge's included.
          if timeout 5 bash -c 'exec 3<>/dev/tcp/172.17.0.1/443' 2>/dev/null; then
            fail "Docker's network is reachable"
          fi
          # Caddy's own network by IPv6 too, where it has an address there.
          if timeout 5 bash -c 'exec 3<>/dev/tcp/fd4a:6c6b:7e80::2/443' 2>/dev/null; then
            fail "Caddy's IPv6 network is reachable"
          fi
          # Nor is Jellyfin at home through the host's tunnel, where it is up (ADR 0032, D6).
          if timeout 5 bash -c 'exec 3<>/dev/tcp/10.61.96.2/8096' 2>/dev/null; then
            fail "the tunnel to Jellyfin at home is reachable"
          fi
          echo "This job can neither see nor reach production."

      # A job cancelled, or stopped at timeout-minutes, is killed with its step's process
      # group (forgejo-runner v13.1.0 starts every host step as a group and sends it
      # SIGKILL), and no later step runs, `if: always()` ones neither. Yet on 22 Oct a
      # cancelled job left its analysis server running, 4 GB, until someone noticed. The
      # runner takes one job at a time (capacity: 1), so a process here in a job's working
      # folder that is neither the runner nor this step is such a leftover: it is stopped
      # before anything else starts, and the log names it.
      - name: Leftovers
        run: |
          own_group=$(ps -o pgid= -p $$ | tr -d ' ')
          # This step and the runner above it.
          keep=' '
          pid=$$
          while [ -n "$pid" ] && [ "$pid" -gt 1 ]; do
            keep="$keep$pid "
            pid=$(ps -o ppid= -p "$pid" | tr -d ' ')
          done
          left=$(ps -e -o pid=,pgid= | while read -r pid pgid; do
            case "$keep" in *" $pid "*) continue ;; esac
            [ "$pgid" != "$own_group" ] || continue
            # Only what a job started: its working folder, or one since removed.
            case "$(readlink "/proc/$pid/cwd" 2>/dev/null)" in
              "$HOME/work/"*) echo "$pid" ;;
            esac
          done)
          if [ -z "$left" ]; then
            echo 'Nothing left behind by earlier jobs.'
            exit 0
          fi
          echo 'Left behind by earlier jobs, stopped now:'
          # shellcheck disable=SC2086 # one process ID a word
          ps -o pid=,etime=,rss=,args= -p "$(echo $left | tr ' ' ,)" | cut -c1-200
          # shellcheck disable=SC2086
          kill -TERM $left 2>/dev/null || true
          sleep 5
          # shellcheck disable=SC2086
          kill -KILL $left 2>/dev/null || true

      # A commit that passed this job before isn't checked again: a fast-forward merge
      # brings the commit a branch's push checked to main unchanged, and only its deploy
      # is new. The marks live in the runner's home; only pushes run this workflow, so
      # only those who may push can leave one. Every later step of this job asks.
      - name: Checked before?
        run: |
          if [ -e "$HOME/checked/${{ github.sha }}" ]; then
            echo "${{ github.sha }} passed these checks before; they aren't run again."
            echo 'CHECKED_BEFORE=true' >> "$FORGEJO_ENV"
          fi

      - name: Check out
        if: env.CHECKED_BEFORE != 'true'
        env:
          TOKEN: ${{ github.token }}
        run: |
          git init -q .
          # The job's token as a header from the environment, so it never shows in a
          # command line; plain git, so the host needs no Node.js for actions/checkout.
          export GIT_CONFIG_COUNT=1 GIT_CONFIG_KEY_0=http.extraHeader \
            GIT_CONFIG_VALUE_0="Authorization: Basic $(printf 'ci:%s' "$TOKEN" | base64 -w0)"
          git fetch -q --depth 1 "${{ github.server_url }}/${{ github.repository }}.git" "${{ github.sha }}"
          git checkout -q -f FETCH_HEAD
          git clean -q -ffdx

      - name: Flutter
        if: env.CHECKED_BEFORE != 'true'
        run: |
          sdk="$HOME/sdk/flutter-$FLUTTER_VERSION"
          if [ ! -x "$sdk/bin/flutter" ]; then
            rm -rf "$sdk"
            git clone -q --depth 1 --branch "$FLUTTER_VERSION" https://github.com/flutter/flutter.git "$sdk"
          fi
          # No usage reports to Google, every time: a cancelled job may have left an SDK
          # behind before switching them off.
          "$sdk/bin/flutter" config --no-analytics >/dev/null
          "$sdk/bin/dart" --disable-analytics >/dev/null
          echo "$sdk/bin" >> "$FORGEJO_PATH"
          "$sdk/bin/flutter" --version

      # Exactly the committed pubspec.lock, or a failure here with pub's own message:
      # CI never resolves something else on its own.
      #
      # The second try works around pub's https://github.com/dart-lang/pub/issues/4912
      # (Dart v3.13): when the runner's cached copy of a git dependency's repository (the
      # editor fork, pure_zstd) lacks the locked commit, the first run resolves that
      # package without its dependencies and fails, but fetches the commit, so the
      # second goes through. Drop it once the Dart of FLUTTER_VERSION has pub's fix
      # (ebba0dc, pull request 4914).
      - name: Dependencies
        if: env.CHECKED_BEFORE != 'true'
        run: flutter pub get --enforce-lockfile || flutter pub get --enforce-lockfile

      # The Serverpod CLI at SERVERPOD_VERSION, for the checks' generated-code step
      # (tool/check.dart): the generated code is committed, so it has to be exactly what
      # the generator makes of the models and endpoints, and the step refuses a CLI at
      # another version than the lock holds Serverpod at.
      - name: Serverpod CLI
        if: env.CHECKED_BEFORE != 'true'
        run: |
          bin="${XDG_STATE_HOME:-$HOME/.local/state}/Dart/install/bin"
          if ! "$bin/serverpod" --no-analytics version 2>/dev/null | grep -qx "Serverpod version: $SERVERPOD_VERSION"; then
            dart install "serverpod_cli@$SERVERPOD_VERSION"
          fi
          echo "$bin" >> "$FORGEJO_PATH"

      # The test run mode's passwords, which passwords.yaml holds on a developer's machine
      # and which is never committed. Without them the server tests stop without a word.
      # Throwaway and new for every job: they only guard the test database the job creates
      # in its own checkout.
      - name: Test passwords
        if: env.CHECKED_BEFORE != 'true'
        run: |
          for name in SERVERPOD_DATABASE_PASSWORD \
            SERVERPOD_PASSWORD_serverSideSessionKeyHashPepper \
            SERVERPOD_PASSWORD_emailSignInPepper \
            SERVERPOD_PASSWORD_totpKey \
            SERVERPOD_PASSWORD_recoveryCodeKey \
            SERVERPOD_PASSWORD_signInDecoyKey \
            SERVERPOD_PASSWORD_serviceSecret; do
            echo "$name=$(openssl rand -hex 32)" >> "$FORGEJO_ENV"
          done

      - name: Checks
        if: env.CHECKED_BEFORE != 'true'
        run: dart run tool/check.dart

      # Reached only when every step above passed. Marks older than 90 days go.
      - name: Remember the commit
        if: env.CHECKED_BEFORE != 'true'
        run: |
          mkdir -p "$HOME/checked"
          touch "$HOME/checked/${{ github.sha }}"
          find "$HOME/checked" -type f -mtime +90 -delete

  deploy:
    needs: check
    if: github.ref == 'refs/heads/main'
    runs-on: sahaquiel
    timeout-minutes: 30
    steps:
      # The key can run nothing but deploy/redeploy.sh, and only from that server itself.
      - name: Deploy to learn.halkyon.eu
        run: >-
          ssh -i "$HOME/.ssh/deploy_trigger" -o IdentitiesOnly=yes -o BatchMode=yes
          -o StrictHostKeyChecking=yes -o UserKnownHostsFile="$HOME/.ssh/known_hosts"
          deploy@127.0.0.1 "${{ github.sha }}"