thoughtsync/.forgejo/workflows/ci.yml

# CI runs first; build only proceeds if lint + typecheck pass.
#
# Push to dev:       typecheck + lint + test + build :dev + :<sha>
# Push to main:      typecheck + lint + test + build :latest + :<sha>
# Tag v* (release):  typecheck + lint + test + build :latest + :<version> + :<sha>
#
# main is the production line, so a merge to main rebuilds and moves :latest to its
# tip (family rule 46) — no version release required. The :<sha> image is the
# immutable rollback unit for every build.
#
# Required secret (repo -> Settings -> Secrets -> Actions):
#   REGISTRY_TOKEN  -- Forgejo PAT with write:packages scope
# The registry username is derived from github.repository_owner (public — it's in
# the image path), so no REGISTRY_USER secret is needed.
name: CI & Build

on:
  push:
    branches: [dev, main]
    tags: ["v*"]
    paths:
      - "src/**"
      - "frontend/**"
      - "tests/**"
      - "pyproject.toml"
      - "alembic/**"
      - "alembic.ini"
      - "Dockerfile"
      - ".forgejo/workflows/ci.yml"
  # Dispatched by the Android lane once it has published a client, so the image
  # that bakes it in is built AFTER the APK exists rather than racing it. See the
  # `gate` job below for the other half.
  workflow_dispatch:

# Cancel older runs on the same branch when a newer push lands. Tag runs get their
# own group implicitly and are never cancelled.
concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: ${{ !startsWith(github.ref, 'refs/tags/') }}

permissions:
  contents: read

env:
  REGISTRY: git.fabledsword.com
  IMAGE: git.fabledsword.com/bvandeusen/thoughtsync

jobs:
  # Should this push build an image now, or is the Android lane about to publish a
  # client that the image ought to contain?
  #
  # A push touching the Android app runs BOTH workflows at once. Building here
  # would bake in the PREVIOUS client and then, when the new one landed, there
  # would be no second build — `:<sha>` is the immutable rollback unit (rule 46)
  # and rebuilding it with different content would make it neither.
  #
  # So on such a push this workflow stands down, and the Android lane dispatches it
  # when it is finished. Exactly one image per commit, containing the client from
  # that commit.
  #
  # The path list below MUST match android.yml's trigger. Two places holding one
  # decision is the recurring failure in this repo (issues 2181-2183); it is here
  # because a workflow cannot read another's filters, and it is a `git diff` rather
  # than a config so at least it is inspectable in the log.
  gate:
    name: Build now, or wait for Android?
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    outputs:
      build: ${{ steps.decide.outputs.build }}
    steps:
      - uses: actions/checkout@v6
        with:
          # Full history: the diff below spans the whole PUSHED RANGE, not just the
          # tip. A push of three commits whose Android change sits in the first
          # would otherwise look Android-free, and the race this job exists to
          # prevent would happen anyway — silently, which is the worst version.
          fetch-depth: 0

      - name: Decide
        id: decide
        run: |
          # A dispatched run IS the Android lane calling back. Always build.
          if [ "${{ github.event_name }}" != "push" ]; then
            echo "Dispatched by the Android lane — building."
            echo "build=true" >> $GITHUB_OUTPUT
            exit 0
          fi

          # A tag. The Android lane does not run on tags, so nothing would ever
          # call back — standing down here would mean a release tag that never
          # produces an image at all.
          case "${{ github.ref }}" in
            refs/tags/*)
              echo "Tag build — the Android lane does not run on tags. Building."
              echo "build=true" >> $GITHUB_OUTPUT
              exit 0
              ;;
          esac

          # No parent (first commit, or a force-push that orphaned it) — nothing to
          # compare, so build rather than stall.
          if ! git rev-parse --verify -q HEAD^ >/dev/null; then
            echo "No parent commit to diff against — building."
            echo "build=true" >> $GITHUB_OUTPUT
            exit 0
          fi

          # The whole push, not just its tip. `before` is what the ref pointed at
          # beforehand; it is absent or all-zeros for a brand-new branch, and may
          # be unreachable after a force-push — fall back to the tip commit then.
          before="${{ github.event.before }}"
          if [ -n "$before" ] \
            && [ "$before" != "0000000000000000000000000000000000000000" ] \
            && git cat-file -e "$before^{commit}" 2>/dev/null; then
            range="$before..HEAD"
          else
            range="HEAD^..HEAD"
          fi
          echo "Comparing $range"

          changed="$(git diff --name-only $range)"
          echo "Changed in this push:"
          echo "$changed" | sed 's/^/    /'

          if echo "$changed" | grep -qE '^(android/|core/|Cargo\.toml$|Cargo\.lock$|\.forgejo/workflows/android\.yml$)'; then
            echo ""
            echo "This push also changes the Android client. Standing down: the"
            echo "Android lane will publish a new APK and dispatch this workflow,"
            echo "so the image is built once, with the client from this commit."
            echo "build=false" >> $GITHUB_OUTPUT
          else
            echo ""
            echo "No Android change — the newest published client is already the"
            echo "right one to bake in. Building."
            echo "build=true" >> $GITHUB_OUTPUT
          fi

  typecheck:
    name: TypeScript typecheck
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      - name: Install dependencies
        run: npm ci
        working-directory: frontend

      - name: Type check
        run: npx vue-tsc --noEmit
        working-directory: frontend

  lint:
    name: Python lint
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      # ruff is pre-installed in the ci-runner base image.
      - name: Lint
        run: ruff check src/

  test:
    name: Python tests
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      - name: Create virtual environment
        run: uv venv /opt/venv

      - name: Install package with dev deps
        run: uv pip install --python /opt/venv/bin/python -e ".[dev]"

      - name: Run tests
        # DB-free by design. Anything needing a real Postgres is marked `integration`
        # and runs in the job below.
        run: /opt/venv/bin/python -m pytest tests/ -q -m "not integration"

  # Real-Postgres lane (family rule 6). Until this existed, `alembic upgrade head` ran
  # for the first time when the operator's container started — 26 revisions, none of
  # them ever executed by CI — and the schema the migrations build had never been
  # checked against the models that read it.
  #
  # Gates the build, along with every other lane — see the `build` job's `needs`.
  #
  # Job key stays separator-free ("integration") with no `name:` — rule 80. act_runner
  # derives the service-container name from the truncated job display name, and the
  # discovery step below filters `docker ps` by it. Service hostnames are not routable
  # on this runner (rule 79), so the step resolves the container's bridge IP.
  integration:
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    services:
      postgres:
        # Same image the production compose runs, so the schema is proven against the
        # Postgres it will actually meet.
        image: postgres:16-alpine
        env:
          POSTGRES_USER: thoughtsync
          POSTGRES_PASSWORD: ci_integration
          POSTGRES_DB: thoughtsync_test
        options: >-
          --health-cmd "pg_isready -U thoughtsync"
          --health-interval 10s
          --health-timeout 5s
          --health-retries 10
    steps:
      - uses: actions/checkout@v6

      - name: Create virtual environment
        run: uv venv /opt/venv

      # Same install as the unit lane — the two must agree on versions, or
      # "unit green, integration red" stops being a signal about the code.
      - name: Install package with dev deps
        run: uv pip install --python /opt/venv/bin/python -e ".[dev]"

      - name: Integration suite (resolve service IP, migrate, test)
        run: |
          set -eux
          echo "=== container landscape (diagnostic for the name filter) ==="
          docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
          PG=$(docker ps --filter "name=integration" --filter "ancestor=postgres:16-alpine" -q | head -n1)
          test -n "$PG"
          PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
          test -n "$PG_IP"
          export THOUGHTSYNC_DATABASE_URL="postgresql+asyncpg://thoughtsync:ci_integration@${PG_IP}:5432/thoughtsync_test"
          # Wait for Postgres to accept connections. `run:` is busybox sh (rule 81) —
          # no bash /dev/tcp — so use the Python that is always present here.
          /opt/venv/bin/python - "$PG_IP" <<'PY'
          import socket, sys, time
          for _ in range(30):
              try:
                  socket.create_connection((sys.argv[1], 5432), timeout=2).close()
                  break
              except OSError:
                  time.sleep(1)
          else:
              sys.exit("postgres did not become reachable")
          PY
          # Real migrations build the schema, never metadata.create_all (rule 82) —
          # testing a schema no deployment has ever seen would prove nothing. This
          # step IS the migration test: a broken revision fails the job here.
          /opt/venv/bin/alembic upgrade head
          /opt/venv/bin/python -m pytest tests/ -v -m integration

  build:
    name: Build & push image
    # Every lane gates the build. This once stopped at lint + typecheck, on the
    # reasoning that DB-backed testing happened manually against the dev image
    # rather than on every push — true until 6f21db8 added the integration lane,
    # and false since.
    #
    # What that gap cost: run 4293 failed `test` and published :dev and :<sha>
    # anyway, so the deployed server ran a build whose test lane was red. An image
    # tag is the rollback substrate (family rule 46); one that can be published
    # from a failing run is not a substrate you can roll back TO.
    needs: [gate, typecheck, lint, test, integration]
    if: needs.gate.outputs.build == 'true'
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    permissions:
      contents: read
      packages: write
    steps:
      - uses: actions/checkout@v6

      - name: Generate image tags and version
        id: tags
        # run: steps execute under busybox sh (family rule 81), so use POSIX `case`,
        # NOT bash `[[ ]]`.
        run: |
          TAGS="${{ env.IMAGE }}:${{ github.sha }}"
          BUILD_VERSION="dev"
          case "${{ github.ref }}" in
            refs/heads/dev)
              TAGS="$TAGS,${{ env.IMAGE }}:dev"
              ;;
            refs/heads/main)
              # Production line: :latest tracks main's tip (rule 46). No :main tag;
              # the :<sha> above is the rollback unit. Version label = short sha.
              TAGS="$TAGS,${{ env.IMAGE }}:latest"
              BUILD_VERSION="$(echo ${{ github.sha }} | cut -c1-7)"
              ;;
            refs/tags/*)
              TAGS="$TAGS,${{ env.IMAGE }}:latest,${{ env.IMAGE }}:${{ github.ref_name }}"
              BUILD_VERSION="${{ github.ref_name }}"
              ;;
          esac
          echo "value=$TAGS" >> $GITHUB_OUTPUT
          echo "build_version=$BUILD_VERSION" >> $GITHUB_OUTPUT

      - name: Free disk space
        run: |
          docker system prune -af || true
          docker builder prune --keep-storage 5g -f || true

      # Bake the Android client in, on EVERY image build, so :dev, :latest and
      # :<version> all carry one and a `docker compose pull` delivers a new client
      # along with the new server.
      #
      # Always the rolling `dev` release — the newest build there is. A versioned
      # image therefore carries the newest client rather than one pinned to that
      # version; the two negotiate a sync protocol version before linking, so
      # "newest" is safe in a way "matching" would not buy anything over.
      #
      # Fetched by the JOB, not by the Dockerfile: the release is private, and a
      # token used inside a build lands in the context or a layer.
      #
      # NEVER fails the build. An image with no Android client advertises none and
      # hides the download — a supported state, and the only one available before
      # the first Android build has ever published.
      - name: Fetch the Android client to bake in
        env:
          GITHUB_TOKEN: ${{ github.token }}
        run: |
          mkdir -p client
          # THE CHANNEL IS A PROPERTY OF THE IMAGE. A :dev image serves the dev
          # client; :latest serves the stable one. This read `download/dev`
          # unconditionally until M314 step 3, on every branch — so every stable
          # server shipped a dev-channel APK to anyone who downloaded the client
          # from it. Not a versioning gap; a plain defect, fixed here because this
          # is the step that gave `stable` an APK to point at.
          case "${{ github.ref_name }}" in
            main|v*) channel=stable ;;
            *)       channel=dev ;;
          esac
          echo "Baking in the $channel client."
          base="${{ github.server_url }}/${{ github.repository }}/releases/download/$channel"
          ok=1
          for f in thoughtsync.apk thoughtsync-android.json; do
            curl -fsSL -H "Authorization: token $GITHUB_TOKEN" -o "client/$f" "$base/$f" || ok=0
          done
          if [ "$ok" = 1 ]; then
            echo "Baking in:"
            cat client/thoughtsync-android.json
            ls -l client/thoughtsync.apk
          else
            # Both or neither. Half a pair is worse than none: the server would
            # read a sidecar describing an APK that isn't there, or an APK it
            # cannot state a version for.
            echo "::warning::No Android client on the dev release — this image ships without one."
            rm -f client/thoughtsync.apk client/thoughtsync-android.json
          fi

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

      - name: Log in to Forgejo registry
        uses: docker/login-action@v4
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ github.repository_owner }}
          password: ${{ secrets.REGISTRY_TOKEN }}

      - name: Build and push
        uses: docker/build-push-action@v7
        with:
          context: .
          push: true
          provenance: false
          tags: ${{ steps.tags.outputs.value }}
          build-args: BUILD_VERSION=${{ steps.tags.outputs.build_version }}
          cache-from: type=registry,ref=${{ env.IMAGE }}:cache
          cache-to: type=registry,ref=${{ env.IMAGE }}:cache,mode=max,ignore-error=true