homelab/.gitea/workflows/ci.yaml

name: ci

on:
  push:
    branches:
      - "**"
  pull_request:
  workflow_dispatch:

# Every job here is checkout plus local tools. The token needs to read the tree
# and nothing else, and saying so keeps a future step that reaches for the API
# from quietly holding a token that can write to the repository.
permissions:
  contents: read

concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

env:
  REGISTRY: gcr.forust.xyz

jobs:
  lint-compose:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      # Structure check for every committed Compose file, active or not.
      # Interpolation, env-file and bind-mount resolution are all switched off,
      # because inactive stacks have no .env here and would only fail on their
      # ${VAR:?} guards. Active stacks get the full check with interpolation in
      # the deploy workflow, where the real .env files live.
      - name: Validate Compose files
        shell: bash
        run: |
          set -euo pipefail
          source .gitea/workflows/compose-lint.sh

          mapfile -t safe_flags < <(compose_safe_flags)
          echo "docker compose config ${safe_flags[*]-}"

          mapfile -t files < <(compose_files)
          if [ "${#files[@]}" -eq 0 ]; then
            echo "No Compose files found."
            exit 0
          fi

          failed=0
          for f in "${files[@]}"; do
            if ! out="$(validate_compose_file "$f" ${safe_flags[@]+"${safe_flags[@]}"} 2>&1)"; then
              failed=1
              echo "::error file=${f}::$(printf '%s' "$out" | head -1)"
            fi
          done

          if [ "$failed" -ne 0 ]; then
            echo "Compose validation failed."
            exit 1
          fi
          echo "checked ${#files[@]} Compose file(s)"

  lint-actionlint:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Lint Gitea Actions workflows with actionlint
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh actionlint)"
          export PATH="$tools_dir:$PATH"
          actionlint -config-file .gitea/actionlint.yaml -color .gitea/workflows/*.yaml

  lint-shellcheck:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Lint shell scripts with ShellCheck
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh shellcheck)"
          export PATH="$tools_dir:$PATH"
          mapfile -t scripts < <(
            git ls-files '*.sh' ':(glob)**/*.bash'
          )
          if [ "${#scripts[@]}" -eq 0 ]; then
            echo "No shell scripts found."
            exit 0
          fi
          shellcheck --external-sources --source-path=SCRIPTDIR --severity=style "${scripts[@]}"

  lint-prettier:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Check formatting with Prettier
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh prettier)"
          export PATH="$tools_dir:$PATH"

          mapfile -t prettier_files < <(
            git ls-files \
              | grep -E '\.(md|json|ya?ml|html|css)$' \
              | grep -Ev '^(\.docs/|\.zed/|errorpages/html/|homepages/(forust_files|xdfnx_files)/)'
          )

          if [ "${#prettier_files[@]}" -eq 0 ]; then
            echo "No Prettier-managed files found."
            exit 0
          fi

          prettier --check --ignore-unknown "${prettier_files[@]}"

  lint-ruff:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Lint and format-check Python with Ruff
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh ruff)"
          export PATH="$tools_dir:$PATH"
          ruff check .
          ruff format --check .

  lint-yaml:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Lint YAML syntax
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh yamllint)"
          export PATH="$tools_dir:$PATH"

          mapfile -t yaml_files < <(
            git ls-files '*.yaml' '*.yml' \
              ':!node_modules/**' \
              ':!**/.venv/**'
          )

          if [ "${#yaml_files[@]}" -eq 0 ]; then
            echo "No YAML files found."
            exit 0
          fi

          yamllint -c .yamllint "${yaml_files[@]}"

  lint-dockerfiles:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Lint Dockerfiles
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh hadolint)"
          export PATH="$tools_dir:$PATH"

          mapfile -t dockerfiles < <(
            git ls-files ':(glob)**/Dockerfile' ':(glob)**/Dockerfile.*'
          )

          if [ "${#dockerfiles[@]}" -eq 0 ]; then
            echo "No Dockerfiles found."
            exit 0
          fi

          hadolint -c .hadolint.yaml "${dockerfiles[@]}"

  validate:
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 20
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4

      - name: Validate Kubernetes manifests against JSON schemas
        shell: bash
        run: |
          set -euo pipefail
          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform)"
          export PATH="$tools_dir:$PATH"

          mapfile -t manifests < <(
            git ls-files ':(glob)**/k8s/**/*.yaml' ':(glob)**/k8s/**/*.yml' \
              | grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
          )

          if [ "${#manifests[@]}" -eq 0 ]; then
            echo "No Kubernetes manifests found."
            exit 0
          fi

          kubeconform \
            -strict \
            -ignore-missing-schemas \
            -summary \
            "${manifests[@]}"

      # kubeconform has no schemas for CRDs, so every IngressRoute, Certificate,
      # PrometheusRule, Middleware, ServersTransport and ServiceMonitor is silently
      # skipped above. The live API server knows the real CRD schemas (and runs the
      # cert-manager / Traefik admission webhooks), so validate there too.
      #
      # Only services marked with a k8s/active marker are checked: server-side
      # dry-run needs the target namespace to exist, and inactive services are not
      # deployed. Services being enabled for the first time are still covered by
      # the JSON-schema pass above.
      #
      # Main pushes only. `--dry-run=server` persists nothing, but it does execute
      # the admission webhooks of the production API server, so anyone able to open
      # a pull request would be able to run arbitrary manifest content through
      # cert-manager and Traefik. A pull request has nothing to gain from it either:
      # only main is ever deployed, and this job runs to completion before the
      # deploy workflow is allowed to start, so a bad CRD is still caught before
      # anything reaches the cluster -- just on the push rather than on the PR.
      - name: Note the server-side check is not running here
        if: github.event_name == 'pull_request' || github.ref != 'refs/heads/main'
        shell: bash
        run: |
          echo "::notice::Skipping the server-side dry-run. It executes the cert-manager and" \
            "Traefik admission webhooks against the production API server, so it is limited" \
            "to pushes to main. CRDs are still schema-checked by kubeconform above, and the" \
            "server-side pass still runs on main before the deploy."

      - name: Validate active manifests against the live API server
        if: github.event_name != 'pull_request' && github.ref == 'refs/heads/main'
        shell: bash
        run: |
          set -euo pipefail

          if ! kubectl get --raw='/readyz' --request-timeout=10s >/dev/null 2>&1; then
            echo "::warning::Cluster unreachable — skipped server-side validation of CRDs (IngressRoute, Certificate, PrometheusRule). Review manifest changes manually."
            exit 0
          fi

          mapfile -t k8s_dirs < <(
            git ls-files '*.yaml' '*.yml' \
              | grep -E '(^|/)k8s/' \
              | sed -E 's#((^|.*/)k8s)/.*#\1#' \
              | sort -u
          )

          manifests=()
          kustomize_apps=()
          for dir in "${k8s_dirs[@]}"; do
            if [ ! -f "${dir}/active" ]; then
              echo "skip (no k8s/active): ${dir}"
              continue
            fi
            if [ -f "${dir}/overlays/prod/kustomization.yaml" ]; then
              kustomize_apps+=("${dir}/overlays/prod")
            elif [ -f "${dir}/base/kustomization.yaml" ]; then
              kustomize_apps+=("${dir}/base")
            else
              while IFS= read -r f; do
                [ -n "$f" ] && manifests+=("$f")
              done < <(
                git ls-files "${dir}/*.yaml" "${dir}/*.yml" \
                  | grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
              )
            fi
          done

          echo "server-side dry-run: ${#manifests[@]} manifests, ${#kustomize_apps[@]} kustomize apps"
          failed=0
          for m in ${manifests[@]+"${manifests[@]}"}; do
            if ! out="$(kubectl apply --dry-run=server -f "$m" 2>&1)"; then
              failed=1
              echo "::error file=${m}::$(printf '%s' "$out" | head -1)"
            fi
          done
          for k in ${kustomize_apps[@]+"${kustomize_apps[@]}"}; do
            if ! out="$(kubectl apply -k "$k" --dry-run=server 2>&1)"; then
              failed=1
              echo "::error file=${k}::$(printf '%s' "$out" | head -1)"
            fi
          done

          if [ "$failed" -ne 0 ]; then
            echo "Server-side validation failed. The API server (or an admission webhook) rejected these manifests."
            exit 1
          fi
          echo "server-side dry-run: all active manifests accepted by the API server"

  build:
    needs:
      # The panel's scan-deps/test-backend/test-frontend jobs gated here until
      # userbot moved to its own repo; upstream's code is upstream's gate now.
      # The rule is unchanged: publishing and passing the checks are the same
      # gate, so a commit that fails any of these still cannot move :prod.
      [lint-actionlint, lint-shellcheck, lint-compose, lint-prettier, lint-ruff, lint-yaml, lint-dockerfiles, validate]
    if: github.event_name != 'pull_request' && (github.ref_name == 'main' || github.ref_name == 'dev') && !startsWith(github.ref_name, 'renovate/')
    runs-on: [self-hosted, linux, arch, homelab]
    timeout-minutes: 60
    outputs:
      services: ${{ steps.services.outputs.services }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
        with:
          fetch-depth: 0

      - name: Detect changed docker-built services
        id: services
        shell: bash
        run: |
          set -euo pipefail
          base="${{ github.event.before }}"
          if [ -z "$base" ] || [ "$base" = "0000000000000000000000000000000000000000" ]; then
            base="$(git rev-list --max-parents=0 HEAD)"
          fi

          # A failed diff used to leave changed_files empty, which reads exactly
          # like "nothing to build": the job went green having built nothing and
          # the tag never moved. The status is checked, not assumed.
          if ! changed="$(git diff --name-only "$base" "${GITHUB_SHA}")"; then
            echo "::error::cannot diff ${base}..${GITHUB_SHA}"
            exit 1
          fi
          mapfile -t changed_files <<<"$changed"

          services=()

          add_service() {
            local name="$1"
            local seen=0
            for existing in "${services[@]}"; do
              if [ "$existing" = "$name" ]; then
                seen=1
                break
              fi
            done
            if [ "$seen" -eq 0 ]; then
              services+=("$name")
            fi
          }

          for file in "${changed_files[@]}"; do
            case "$file" in
              errorpages/*)
                add_service errorpages
                ;;
              homepages/*)
                add_service homepages
                ;;
              edu_master/phpsessid-bot/*|edu_master/webinar-checker/*|edu_master/compose.yaml)
                add_service edu_master
                ;;
            esac
          done

          if [ "${#services[@]}" -eq 0 ]; then
            echo "No docker-built services changed."
            echo "services=" >> "$GITHUB_OUTPUT"
            exit 0
          fi

          printf '%s\n' "${services[@]}" | tee /tmp/services.txt
          echo "services=$(paste -sd, /tmp/services.txt)" >> "$GITHUB_OUTPUT"

      - name: Log in to registry
        # The pin step below also writes (manifest PUTs), and it runs on every
        # main push — including manifest-only ones where services is empty. A
        # stale persistent login on the old runner used to mask this; a clean
        # runner pushes anonymously and gets 401.
        if: steps.services.outputs.services != '' || github.ref_name == 'main'
        shell: bash
        # Through env, not by substitution into the script. A secret written
        # into a run: block is pasted into the shell source before bash parses
        # it, so a password containing a quote, a backtick or $(...) becomes
        # code that runs. Masking the value in the log does not prevent that.
        env:
          REGISTRY_USERNAME: ${{ secrets.REGISTRY_USERNAME }}
          REGISTRY_PASSWORD: ${{ secrets.REGISTRY_PASSWORD }}
        run: |
          set -euo pipefail
          printf '%s' "$REGISTRY_PASSWORD" | docker login "${REGISTRY}" \
            -u "$REGISTRY_USERNAME" \
            --password-stdin

      - name: Build and push changed images
        if: steps.services.outputs.services != ''
        shell: bash
        run: |
          # This step was the one run: block in the workflow without it, and it
          # is the one that cannot afford it: a docker push that failed partway
          # through the loop used to be followed by more pushes, the loop's exit
          # status came from the last one, and the job went green with half the
          # images missing from the registry.
          set -euo pipefail
          IFS=, read -r -a services <<< "${{ steps.services.outputs.services }}"

          # Tags for this push. The commit-pinned name is the point of this
          # step: the deploy resolves it in preference to :prod, so a deploy
          # that sat in the queue behind a later push still gets the build of
          # the commit CI validated, instead of whatever :prod points at by the
          # time it runs. See render_pinned in deploy-lib.sh.
          commit_tag=""
          if [ "${GITHUB_REF_NAME}" = "main" ]; then
            commit_tag="sha-${GITHUB_SHA:0:12}"
          fi

          set_tags() {
            tags=()
            case "${GITHUB_REF_NAME}" in
              main) tags+=("main" "prod") ;;
              dev) tags+=("dev") ;;
            esac
            if [ -n "$commit_tag" ]; then
              tags+=("$commit_tag")
            fi
          }

          for service in "${services[@]}"; do
            case "$service" in
              errorpages)
                image="${REGISTRY}/forust/error-pages"
                set_tags
                build_args=()
                for tag in "${tags[@]}"; do
                  build_args+=(-t "${image}:${tag}")
                done
                docker build \
                  --cache-from "type=registry,ref=${image}:buildcache" \
                  --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
                  "${build_args[@]}" errorpages
                for tag in "${tags[@]}"; do
                  docker push "${image}:${tag}"
                done
                ;;
              homepages)
                for variant in forust xdfnx; do
                  case "$variant" in
                    forust)
                      image="${REGISTRY}/forust/forust-homepage"
                      ;;
                    xdfnx)
                      image="${REGISTRY}/forust/xdfnx-homepage"
                      ;;
                  esac
                  set_tags
                  build_args=()
                  for tag in "${tags[@]}"; do
                    build_args+=(-t "${image}:${tag}")
                  done
                  docker build \
                    --cache-from "type=registry,ref=${image}:buildcache" \
                    --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
                    "${build_args[@]}" -f "homepages/Dockerfile.${variant}" homepages
                  for tag in "${tags[@]}"; do
                    docker push "${image}:${tag}"
                  done
                done
                ;;
              edu_master)
                for variant in session-keeper webinar-checker; do
                  case "$variant" in
                    session-keeper)
                      context="edu_master/phpsessid-bot"
                      image="${REGISTRY}/forust/session-keeper"
                      ;;
                    webinar-checker)
                      context="edu_master/webinar-checker"
                      image="${REGISTRY}/forust/webinar-checker"
                      ;;
                  esac
                  set_tags
                  build_args=()
                  for tag in "${tags[@]}"; do
                    build_args+=(-t "${image}:${tag}")
                  done
                  docker build \
                    --cache-from "type=registry,ref=${image}:buildcache" \
                    --cache-to "type=registry,ref=${image}:buildcache,mode=max" \
                    "${build_args[@]}" "$context"
                  for tag in "${tags[@]}"; do
                    docker push "${image}:${tag}"
                  done
                done
                ;;
            esac
          done

      # Every image the tree names has to carry the commit-pinned name, not only
      # the ones this push rebuilt. A push that touches nothing but manifests
      # builds nothing, and its deploy would then find no commit-pinned tag to
      # resolve and quietly fall back to the moving :prod - which is the whole
      # failure the commit-pinned name exists to remove.
      #
      # Re-tagging copies the manifest list and transfers no layers, so pinning
      # six images that already exist costs six registry writes.
      #
      # The list is derived from the tree rather than written out here, so an
      # image added to a manifest is covered without a second place to update.
      - name: Pin the commit name on the images this push did not rebuild
        if: github.ref_name == 'main'
        shell: bash
        run: |
          set -euo pipefail
          commit_tag="sha-${GITHUB_SHA:0:12}"
          mapfile -t repos < <(
            git grep -hoE 'gcr\.forust\.xyz/forust/[A-Za-z0-9._-]+' -- '*.yaml' '*.yml' \
              | sort -u
          )
          if [ "${#repos[@]}" -eq 0 ]; then
            echo "No own images referenced by the tree."
            exit 0
          fi
          echo "pinning ${#repos[@]} image(s) to $commit_tag"
          for repo in "${repos[@]}"; do
            if docker buildx imagetools inspect "$repo:$commit_tag" >/dev/null 2>&1; then
              echo "  already built by this push: ${repo##*/}"
              continue
            fi
            if ! docker buildx imagetools inspect "$repo:prod" >/dev/null 2>&1; then
              echo "  WARNING: ${repo##*/} has no :prod to pin and no build produced it"
              continue
            fi
            docker buildx imagetools create --tag "$repo:$commit_tag" "$repo:prod"
            echo "  pinned ${repo##*/}"
          done