name: Build veilor-os ISO

on:
  push:
    branches: [main]
    paths:
      - 'kickstart/**'
      - 'overlay/**'
      - 'scripts/**'
      - 'assets/**'
      - 'build/**'
      - '.github/workflows/build-iso.yml'
  workflow_dispatch:
    inputs:
      releasever:
        description: 'Fedora release version'
        required: false
        default: '43'
  release:
    types: [published]

permissions:
  contents: write       # needed for action-gh-release to create+update ci-latest
  id-token: write       # cosign keyless OIDC + attest-build-provenance
  attestations: write   # attest-build-provenance writes the attestation

jobs:
  build:
    name: Build live ISO
    runs-on: ubuntu-24.04
    timeout-minutes: 90

    steps:
      - name: Checkout
        # Pinned to last v4 tag confirmed to ship on node20. v4.2+ ships
        # node24 which forgejo-runner v6.4.0 (node20) cannot exec.
        uses: actions/checkout@v4.1.7

      - name: Free up disk
        run: |
          sudo rm -rf /opt/hostedtoolcache /usr/share/dotnet /usr/local/lib/android /usr/local/share/boost
          sudo apt-get clean
          df -h

      - name: Run build inside Fedora 43 container
        # v3 is composite/docker-based — no node runtime in the action
        # itself. Safe under node20 forgejo-runner. TODO(infra): consider
        # SHA pinning in a follow-up sweep.
        uses: addnab/docker-run-action@v3
        with:
          image: registry.fedoraproject.org/fedora:43
          options: |
            --privileged
            -v ${{ github.workspace }}:/work
            -v /dev:/dev
            --tmpfs /tmp:rw,nosuid,nodev,exec,size=16G
          run: |
            set -euxo pipefail

            # Update Fedora image to latest packages — guarantees pcre2 +
            # libselinux + selinux-policy are matched (the local build's
            # core problem). CI runners always start fresh, no version skew.
            dnf -y upgrade --refresh

            # Install build tooling
            dnf -y install \
              lorax \
              livecd-tools \
              pykickstart \
              python3-imgcreate \
              anaconda-tui \
              squashfs-tools \
              xorriso \
              createrepo_c \
              git \
              which \
              shadow-utils \
              syslinux \
              tar \
              curl

            # Vendor gum binary onto the ISO so the TTY1 installer can use
            # Charm.sh TUI primitives. gum is not packaged in Fedora repos,
            # so pull the upstream release tarball pinned by sha256.
            GUM_VERSION="0.17.0"
            GUM_URL="https://github.com/charmbracelet/gum/releases/download/v${GUM_VERSION}/gum_${GUM_VERSION}_Linux_x86_64.tar.gz"
            GUM_SHA256="69ee169bd6387331928864e94d47ed01ef649fbfe875baed1bbf27b5377a6fdb"
            mkdir -p /work/overlay/usr/local/bin
            curl -fsSL "$GUM_URL" -o /tmp/gum.tgz
            echo "$GUM_SHA256  /tmp/gum.tgz" | sha256sum -c -
            tar -xzf /tmp/gum.tgz -C /tmp/
            install -m 0755 "/tmp/gum_${GUM_VERSION}_Linux_x86_64/gum" /work/overlay/usr/local/bin/gum
            /work/overlay/usr/local/bin/gum --version
            echo "[OK] gum ${GUM_VERSION} vendored into overlay/usr/local/bin/"

            cd /work

            # PATCH: livecd-creator bug — __get_efi_image_stanza writes
            # `root=live:LABEL=...` instead of `live:CDLABEL=...` for dracut.
            # Result: dracut hangs on parse-livenet looking for non-CD label.
            # Fix in-place before running build.
            LIVE_PY=$(python3 -c 'import imgcreate, os; print(os.path.dirname(imgcreate.__file__))')/live.py
            sed -i 's|"live:LABEL=%(fslabel)s"|"live:CDLABEL=%(fslabel)s"|g' "$LIVE_PY"
            grep -n 'CDLABEL=%(fslabel)s' "$LIVE_PY" || { echo "[ERR] patch failed"; exit 1; }
            echo "[OK] livecd-creator patched: LABEL= → CDLABEL= for EFI dracut stanza"

            # CI uses ks-ci.ks (no local fix-repo line). Generated from main ks.
            # Also strip flags livecd-creator doesn't recognize.
            # Drop `updates` repo: 3 consecutive builds 404'd on its
            # repodata zchunk file across all mirrors — Fedora infra issue
            # mid-push window. Original reason for `updates` (selinux-policy
            # 43.7 pcre2 fix) is no longer needed; base 43 ships fixed.
            sed -e '/veilor-fix/d' \
                -e '/^shutdown$/d' \
                -e '/repo --name=updates/d' \
                kickstart/veilor-os.ks > kickstart/veilor-os-ci.ks

            ksvalidator kickstart/veilor-os-ci.ks
            mkdir -p build/out

            # livecd-creator (livecd-tools) — purpose-built for live ISOs.
            # Handles EFI/BOOT + isohybrid + grafting that livemedia-creator
            # --make-iso --no-virt does not. Produces UEFI+BIOS bootable ISO.
            # --tmpdir /var/lmc to avoid GitHub Actions /tmp tmpfs constraints.
            # /var on the runner is the host's ext4 (~80GB free post-disk-cleanup).
            mkdir -p /var/lmc /var/lmc-cache
            livecd-creator \
              --verbose \
              --config kickstart/veilor-os-ci.ks \
              --fslabel "veilor-os-43" \
              --title "veilor-os" \
              --product "veilor-os" \
              --releasever "${{ github.event.inputs.releasever || '43' }}" \
              --tmpdir /var/lmc \
              --cache /var/lmc-cache 2>&1 | tee build/out/build.log

            # Graft veilor source tree onto the ISO so the installer-generated
            # kickstart's `%post --nochroot` can find SRC at
            # /run/install/repo/veilor/{overlay,scripts,assets}/ when the user
            # promotes the live ISO into a real install.
            ISO_FILE=$(ls /work/*.iso 2>/dev/null | head -1)
            [ -n "$ISO_FILE" ] || { echo "[ERR] no ISO produced by livecd-creator"; exit 1; }
            echo "[INFO] grafting /veilor/ onto $ISO_FILE"

            # Extract original ISO's exact boot stanza so the rebuild matches
            # livecd-creator's layout byte-for-byte. This is immune to upstream
            # Fedora layout changes (e.g. images/ vs isolinux/ for efiboot.img,
            # partition geometry flags, hybrid MBR/GPT options).
            xorriso -indev "$ISO_FILE" -report_el_torito as_mkisofs 2>&1 | tee /tmp/iso-boot.txt || true
            ORIG_FLAGS=$(xorriso -indev "$ISO_FILE" -report_el_torito as_mkisofs 2>/dev/null | \
                grep -v '^xorriso :' | grep -E '^-' | tr '\n' ' ')
            [ -n "$ORIG_FLAGS" ] || { echo "[ERR] could not extract boot stanza from $ISO_FILE"; exit 1; }
            echo "[INFO] re-pack flags from original ISO: $ORIG_FLAGS"

            mkdir -p /tmp/iso-mod
            xorriso -osirrox on -indev "$ISO_FILE" -extract / /tmp/iso-mod
            chmod -R u+w /tmp/iso-mod
            mkdir -p /tmp/iso-mod/veilor
            cp -a /work/overlay /work/scripts /work/assets /tmp/iso-mod/veilor/

            # Replay the exact stanza captured above. eval is needed because
            # ORIG_FLAGS contains multiple flag/value pairs that must word-split.
            eval xorriso -as mkisofs \
              -volid "veilor-os-43" \
              $ORIG_FLAGS \
              -o "${ISO_FILE}.tmp" /tmp/iso-mod
            mv "${ISO_FILE}.tmp" "$ISO_FILE"
            rm -rf /tmp/iso-mod
            echo "[OK] /veilor/ grafted onto $ISO_FILE"

            # Move output ISO to expected dir
            mv ./veilor-os-43.iso build/out/ 2>/dev/null || mv ./*.iso build/out/ 2>/dev/null || true

            # Rename + checksum
            ISO_NAME="veilor-os-${{ github.event.inputs.releasever || '43' }}-$(date +%Y%m%d-%H%M%S).iso"
            cd build/out
            for f in *.iso; do
              [[ -f $f && $f != $ISO_NAME ]] && mv "$f" "$ISO_NAME"
            done
            sha256sum "$ISO_NAME" > "$ISO_NAME.sha256"
            ls -lh "$ISO_NAME"

      # ── ISO publish ────────────────────────────────────────────────────
      # GH Release asset size limit = 2 GiB. Our ISO ~2.8 GiB. Split into
      # chunks before upload. Reassemble client-side via `cat *.part-* > x.iso`.
      # Squashfs is already near-incompressible (zstd -19 → 96%) so split,
      # not compress.
      - name: Split ISO into 2GiB chunks
        if: success() && github.ref == 'refs/heads/main'
        run: |
          # ISO + sidecars created by Fedora container as root. Reclaim
          # ownership so this step (running as runner user) can write.
          sudo chown -R "$(id -u):$(id -g)" build/out
          cd build/out
          ISO=$(ls *.iso | head -1)
          [ -n "$ISO" ] || { echo "[ERR] no ISO"; exit 1; }
          # Split with 1900M chunks (under 2 GiB safe). Suffix .part-aa, .part-ab, ...
          split -b 1900M -d --suffix-length=2 "$ISO" "${ISO}.part-"
          ls -lh
          # Drop the original ISO so it doesn't try to upload (over limit)
          rm -f "$ISO"
          # Generate sha256 of all parts so reassembly is verifiable
          sha256sum *.part-* > "${ISO}.parts.sha256"
          echo "[OK] split into:"
          ls "${ISO}".part-*

      - name: Install cosign
        if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
        uses: sigstore/cosign-installer@v3

      - name: Sign ISO parts (keyless)
        if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
        run: |
          cd build/out
          for f in *.part-*; do
            cosign sign-blob --yes "$f" \
              --output-signature "$f.sig" \
              --output-certificate "$f.pem"
          done

      - name: Generate SBOM (SPDX)
        if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
        uses: anchore/sbom-action@v0
        with:
          path: build/out
          format: spdx-json
          output-file: build/out/veilor-os.spdx.json

      - name: Build provenance attestation
        if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
        uses: actions/attest-build-provenance@v2
        with:
          subject-path: 'build/out/*.iso.part-*'

      - name: Publish to ci-latest rolling prerelease
        if: success() && github.ref == 'refs/heads/main'
        # Pinned to last v2 tag confirmed to ship on node20.
        uses: softprops/action-gh-release@v2.0.4
        with:
          tag_name: ci-latest
          name: "ci-latest (auto)"
          body: |
            Rolling auto-build from `main`. Latest commit: ${{ github.sha }}.

            **ISO is split into chunks (GH release 2 GiB asset limit).**
            Reassemble:
            ```
            cat veilor-os-*.iso.part-* > veilor-os.iso
            sha256sum -c veilor-os-*.iso.parts.sha256
            ```
            Or use `test/auto-install.sh` which handles reassembly automatically.

            Not a stable release — for testing only.
          prerelease: true
          make_latest: false
          files: |
            build/out/*.iso.part-*
            build/out/*.sha256
            build/out/*.sig
            build/out/*.pem
            build/out/*.spdx.json

      # Build log on failure: print inline + skip artifact upload to avoid
      # quota wall. Job log retains everything anyway.
      - name: Print build log on failure
        if: failure()
        run: |
          echo "─── build/out/build.log ───"
          tail -200 build/out/build.log 2>/dev/null || echo "(no build.log)"
          echo "─── anaconda program.log ───"
          find build/out/build/anaconda -name 'program.log' -exec tail -100 {} \; 2>/dev/null || echo "(no anaconda log)"

      - name: Attach to release on tag
        if: github.event_name == 'release'
        # Pinned to last v2 tag confirmed to ship on node20.
        uses: softprops/action-gh-release@v2.0.4
        with:
          files: |
            build/out/*.iso
            build/out/*.sha256