veilor-os/kickstart/veilor-os.ks

#version=DEVEL
# veilor-os kickstart — Fedora 43 KDE base, hardened, minimal.
# Build with livemedia-creator inside build/Containerfile.

# ── Install source ──
# Hard-code version (not $releasever) because lorax doesn't expand
# inside kickstart `url`/`repo` directives. Updates repo critical:
# base Fedora 43 ships selinux-policy 42.12 with pcre2-10.47-built
# file_contexts.bin, which fails chroot %triggerin against host's
# libselinux (built against pcre2 10.46). 43.7 in updates is rebuilt.
url --mirrorlist="https://mirrors.fedoraproject.org/mirrorlist?repo=fedora-43&arch=x86_64"
# Explicit `repo --name=fedora` lets livecd-creator see base repo (it only
# reads repo.repoList, ignores url= directive). livemedia-creator + Anaconda
# honor both. No behavior change for either tool.
# Use direct baseurl (kernel.org mirror) to avoid mirrorlist 404s during
# Fedora's metadata sync windows.
repo --name=fedora --baseurl="https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os/" --install
repo --name=updates --baseurl="https://download.fedoraproject.org/pub/fedora/linux/updates/43/Everything/x86_64/" --install
# Local fix-repo: build-time-only workaround for host pcre2/libselinux skew.
# Stripped from CI ks via sed in build-iso.yml. NOT shipped state.
repo --name=veilor-fix --baseurl=file:///tmp/veilor-fix-repo --install --cost=1

# ── Locale / keyboard / time (template — adjust per build) ──
keyboard --xlayouts='us'
lang en_GB.UTF-8
timezone Europe/London --utc

# ── Install mode ──
# Note: no display mode (text/graphical/cmdline) — livemedia-creator forbids.
firstboot --disable
eula --agreed
# Build-time SELinux disabled to avoid PCRE2 regex version mismatch between
# host libselinux and chroot's selinux-policy file_contexts.bin (pcre2 10.46
# vs 10.47). veilor-firstboot.service triggers `fixfiles -F onboot` and
# `setenforce 1` on first boot to re-enable enforcing mode.
selinux --permissive
# veilor-firstboot + veilor-modules-lock enabled via %post after overlay
# copy (units don't exist yet at services-config phase).
services --enabled=sshd,fail2ban,usbguard,tuned,auditd,firewalld,chronyd,sddm

# ── Network / hostname ──
network --bootproto=dhcp --device=link --activate --hostname=veilor-os
firewall --enabled --service=ssh

# ── Identity (zero-prompt; only LUKS passphrase asked at install) ──
# Note: `auth` command removed in pykickstart 3.x — defaults (sha512 shadow) apply.
rootpw --lock
user --name=admin --groups=wheel --gecos="veilor admin" --password="" --plaintext

# ── Bootloader: kernel hardening flags ──
# Note: init_on_alloc/init_on_free removed from default live cmdline —
# they zero every memory page at boot which 5x'd KVM live boot time.
# Re-enable per-install via veilor-firstboot.service for production.
# `fbcon=nodefer` keeps the linux framebuffer console alive across the
# KMS modeset that intel/amdgpu/nvidia drivers do during userspace init.
# Without it, on real hardware the screen blanks the moment the GPU
# driver loads and the installer's tty1 redraw lands on a frozen
# framebuffer — symptom: black screen with blinking cursor for ~30s
# while the menu IS in fact rendered, just not painted. virtio-vga in
# QEMU doesn't trigger this so it never reproed in VM.
bootloader --location=mbr --append="lockdown=integrity slab_nomerge randomize_kstack_offset=on vsyscall=none plymouth.enable=0 fbcon=nodefer"

# ── Live ISO partitioning (flat — for live rootfs build only) ──
# NOTE: This is the *live* image kickstart. Final installed system uses
# a separate installer kickstart (kickstart/install.ks, planned v0.2.1)
# that does LUKS2 + btrfs subvols on the target disk.
part / --fstype=ext4 --size=8192

# ── Packages ──
%packages --excludedocs
@^kde-desktop-environment
@kde-apps
@core
@hardware-support
@standard

# live install plumbing (required by livemedia-creator --make-iso)
# CRITICAL: livesys-scripts + anaconda-live ship the systemd units lorax expects
# at squashfs creation. Without them, EFI/BOOT not built and ISO wrap fails.
# (Upstream Fedora's fedora-live-kde.ks includes these via fedora-live-base.ks.)
livesys-scripts
anaconda-live
@anaconda-tools
kernel-modules
kernel-modules-extra
glibc-all-langpacks
dracut-live
dracut-config-generic
kernel
grub2-efi-x64
grub2-efi-x64-modules
grub2-pc
grub2-pc-modules
grub2-tools
grub2-tools-extra
shim-x64
efibootmgr
syslinux
isomd5sum
xorriso

# veilor-installer dependencies (TTY1 TUI installer wrapping anaconda)
newt
parted
cryptsetup
lvm2
btrfs-progs


# core hardening tools
fail2ban
fail2ban-firewalld
usbguard
usbguard-tools
audit
policycoreutils-python-utils
tuned
chrony
firewalld
plymouth

# admin essentials
git
vim-enhanced
tmux
htop
podman
skopeo
NetworkManager
NetworkManager-wifi

# fonts
fontconfig
freetype
fira-code-fonts

# remove fluff
# Note: KDE Plasma 6 hard-deps on cups/geoclue2/ModemManager/PackageKit
# transitively (plasma-print-manager, xdg-desktop-portal, NM-wwan etc),
# so package removal breaks depsolve. Daemons disabled at runtime via
# scripts/20-harden-kernel.sh instead.
-abrt*
-snapd
-kde-connect
-open-vm-tools-desktop
-mlocate

%end

# ── Post-install (nochroot): copy overlay tree into installed root ──
%post --nochroot --erroronfail
set -uo pipefail
# DEST: livecd-creator sets INSTALL_ROOT, livemedia-creator uses /mnt/sysimage.
DEST="${INSTALL_ROOT:-/mnt/sysimage}"
[[ -d $DEST ]] || { echo "[ERR] DEST=$DEST does not exist (livecd-creator? livemedia-creator?)" >&2; exit 1; }

# Try multiple source paths:
#   /run/install/repo/veilor — boot ISO (--virt mode)
#   /work                    — bind mount in CI container
#   $(dirname kickstart)/..  — local --no-virt builds
SRC=""
for candidate in /run/install/repo/veilor /work /mnt/work; do
    if [[ -d $candidate/overlay ]]; then
        SRC=$candidate
        break
    fi
done

# Fallback: derive from kickstart path. Anaconda passes ks via --kickstart=<path>.
if [[ -z $SRC ]]; then
    KS_PATH=$(ps -ef | grep -oP -- '--kickstart[= ]\K[^ ]+' | head -1)
    if [[ -n $KS_PATH && -d $(dirname "$KS_PATH")/../overlay ]]; then
        SRC=$(realpath "$(dirname "$KS_PATH")/..")
    fi
fi

if [[ -z $SRC ]]; then
    echo "[ERR] cannot locate veilor-os repo source — overlay/scripts not copied" >&2
    exit 1
fi

echo "[INFO] using SRC=$SRC DEST=$DEST"
set -x
cp -a "$SRC/overlay/." "$DEST/" || echo "[ERR] overlay cp failed: $?"
mkdir -p "$DEST/usr/share/veilor-os" || echo "[ERR] mkdir failed: $?"
ls -la "$SRC/assets" "$SRC/scripts" 2>&1 || echo "[ERR] assets/scripts missing in $SRC"
cp -a "$SRC/assets" "$DEST/usr/share/veilor-os/" || echo "[ERR] assets cp failed: $?"
cp -a "$SRC/scripts" "$DEST/usr/share/veilor-os/" || echo "[ERR] scripts cp failed: $?"
ls -la "$DEST/usr/share/veilor-os/" 2>&1 || echo "[ERR] dest dir missing post-cp"
# Force root ownership on everything we copied — `cp -a` preserves
# CI runner uid (1001), which makes sudo refuse to read /etc/sudoers.d.
chown -R 0:0 "$DEST/etc" "$DEST/usr/share/veilor-os" "$DEST/usr/local/bin" 2>&1 || echo "[WARN] chown failed"
set +x

# Persist nochroot log into installed system for diagnostics
{
    echo "=== %post --nochroot trace ==="
    date
    echo "SRC=$SRC DEST=$DEST"
    ls -la "$DEST/usr/share/veilor-os/" 2>&1
    ls -la "$DEST/usr/local/bin/" 2>&1
} > "$DEST/var/log/veilor-nochroot.log" 2>&1 || true
%end

# ── Post-install (chroot): apply hardening, theme, branding ──
%post
set -uo pipefail
exec > >(tee -a /var/log/veilor-install.log) 2>&1

echo "════════════════════════════════════════════════════════"
echo " veilor-os install — %post"
echo "════════════════════════════════════════════════════════"

REPO=/usr/share/veilor-os
chmod +x $REPO/scripts/*.sh $REPO/scripts/selinux/*.sh /usr/local/bin/veilor-power /usr/local/bin/veilor-update /usr/local/bin/veilor-doctor /usr/local/bin/veilor-firstboot /usr/local/bin/veilor-installer

# Live image plumbing (matches upstream Fedora live ks). Without these the
# squashfs/EFI build fails — livesys-scripts ships systemd units lorax expects.
systemctl enable livesys.service livesys-late.service 2>/dev/null || true
systemctl enable tmp.mount 2>/dev/null || true

# /etc/machine-id reset on first boot (live image baseline)
> /etc/machine-id

# Apply hardening
bash $REPO/scripts/10-harden-base.sh
bash $REPO/scripts/20-harden-kernel.sh

# Build SELinux module
bash $REPO/scripts/selinux/build-policy.sh || echo "[WARN] SELinux build failed; load on first boot"

# Apply KDE theme + DuckSans + os-release branding
bash $REPO/scripts/kde-theme-apply.sh
bash $REPO/scripts/30-apply-v03-theme.sh || echo "[WARN] v03-theme apply failed"

# Force admin password set on first boot.
# livecd-creator does NOT honor `user` kickstart directive (it's a LIVE
# image, no installer step). Create admin manually in chroot %post.
# Note: SDDM rejects blank passwords by default (PAM nullok off), so we
# set throwaway pw `veilor` + chage -d 0 to force reset on first login.
if ! getent passwd admin >/dev/null; then
    useradd -m -G wheel -s /bin/bash -c "veilor admin" admin
    echo 'admin:veilor' | chpasswd
    chage -d 0 admin
    echo "[INFO] admin user created (default pw=veilor, expired)"
fi

# Symlink display-manager.service → sddm.service. graphical.target Wants=
# display-manager but the alias doesn't get auto-created when sddm package
# is installed via livecd-creator (vs Anaconda installer which handles it).
# Without this, sddm stays inactive even though enabled.
ln -sf /usr/lib/systemd/system/sddm.service /etc/systemd/system/display-manager.service

# Live ISO default target: multi-user (TTY1 = veilor-installer TUI lands first).
# User picks "Try live — desktop" from menu → systemctl isolate graphical.target.
# Real installs land on graphical.target by default (set by anaconda).
systemctl set-default multi-user.target

# Branding: GRUB menu title + plymouth `details` text theme (no graphical
# splash). Pure text-scroll boot exposes the gum installer immediately on
# tty1 instead of plymouth swallowing it.
sed -i \
    -e 's|^GRUB_DISTRIBUTOR=.*|GRUB_DISTRIBUTOR="veilor-os"|' \
    -e 's|^GRUB_CMDLINE_LINUX_DEFAULT=.*|GRUB_CMDLINE_LINUX_DEFAULT=""|' \
    /etc/default/grub 2>/dev/null || true
plymouth-set-default-theme details 2>/dev/null || true
[ -f /boot/grub2/grub.cfg ] && grub2-mkconfig -o /boot/grub2/grub.cfg 2>/dev/null || true

# zram swap (no disk swap; keys never leak to platter)
dnf install -y zram-generator || true
cat > /etc/systemd/zram-generator.conf << 'EOF'
[zram0]
zram-size = min(ram, 8192)
compression-algorithm = zstd
EOF

# Patch anaconda's transaction_progress.py inside the live rootfs so that
# when the user clicks "Install", a non-fatal RPM 6.0 *scriptlet* warning
# does not get escalated to "An error occurred during the transaction"
# and abort.
#
# This patch is NARROW — it overrides ONLY the `script_error` callback,
# not the consumer (`process_transaction_progress`). v0.5.28 had a broad
# patch that turned EVERY 'error' token into a warning, including
# `cpio_error` (payload corruption) and `unpack_error` (extraction
# failures). Side effect: silent grub2-efi-x64 scriptlet failure →
# /boot/efi/EFI/fedora/ left incomplete → `gen_grub_cfgstub` failed at
# the bootloader install phase. Narrowing eliminates that class of
# silent failure.
#
# Why a patch is needed at all: Fedora 43 ships RPM 6.0, which changed
# scriptlet failure propagation (Fedora wiki Changes/RPM-6.0; dnf5 issue
# 2507). Scriptlets that previously emitted "Non-critical error"
# warnings now bubble up as transaction-level errors. man-db's
# `transfiletriggerin` (`systemd-run /usr/bin/systemctl start
# man-db-cache-update`) is the most common trigger — non-zero in the
# anaconda chroot, RPM-6.0-aware dnf5 reports as error, anaconda
# --cmdline aborts.
#
# After the patch:
#   - script_error → log warning, do NOT enqueue 'error' (transaction
#     continues; specific package's posttrans whose result we ignore is
#     already in the install set, scriptlet has run as far as it can).
#   - cpio_error / unpack_error / generic error → unchanged, still
#     raise PayloadInstallationError as anaconda intends. Real
#     transaction-fatal events still abort install (good).
# Patch anaconda's transaction_progress.py to suppress dnf5's
# transaction-error escalation under RPM 6.0 + cmdline mode.
#
# History of this patch:
#
# v0.5.28: BROAD patch — overrode `process_transaction_progress` so all
#   four 'error' token producers (cpio_error, script_error, unpack_error,
#   generic error) became log warnings. man-db scriptlet stopped killing
#   the install. BUT silent grub2-efi-x64 scriptlet failure left
#   /boot/efi/EFI/fedora/ incomplete → gen_grub_cfgstub failed.
#
# v0.5.29: NARROW patch — overrode only `script_error` callback. Caught
#   the per-package scriptlet failures cleanly. BUT dnf5 still tracks
#   its own internal error counter and emits a final aggregate
#   `error("transaction process has ended with errors..")` at end of
#   transaction, which still raised PayloadInstallationError. Install
#   aborted before bootloader install ran.
#
# v0.5.30: BROAD patch + bootloader --location=none in install ks.
#   This time we silence the aggregate error too, so install completes,
#   but anaconda is told NOT to install bootloader itself. The
#   generated install ks's chroot %post does it explicitly via
#   `dnf reinstall grub2-efi-x64 shim-x64 + grub2-install +
#   grub2-mkconfig + efibootmgr`. The chroot has PID 1 systemd state
#   from the live ISO (not the target), so scriptlets get a real
#   environment to run in, not anaconda's truncated chroot. This
#   sidesteps gen_grub_cfgstub entirely.
TP=/usr/lib64/python3.14/site-packages/pyanaconda/modules/payloads/payload/dnf/transaction_progress.py
if [ -f "$TP" ]; then
    cp -a "$TP" "${TP}.veilor-bak"

    # Replace the entire `elif token == 'error':` branch with log+continue.
    # Pattern matches the original two-line block (log.error + raise).
    python3 - "$TP" <<'PYEOF'
import sys, re
path = sys.argv[1]
src = open(path).read()
# Match: elif token == 'error':\n    log.error(msg)\n    raise PayloadInstallationError(...)
# Or any current substitution that looks like raise/log.warning at that level.
new = re.sub(
    r"elif token == 'error':\n            log\.error\(msg\)\n            (?:raise PayloadInstallationError\(\"An error occurred during the transaction: \" \+ msg\)|log\.warning\(\"veilor: ignoring non-fatal transaction error: %s\", msg\))",
    "elif token == 'error':\n            log.warning('veilor: suppressed dnf5 transaction error (RPM 6.0 cmdline regression): %s', msg)\n            # Do not raise — anaconda --cmdline + dnf5 + RPM 6.0 emits this for any scriptlet\n            # failure; we handle bootloader install manually in install ks %post chroot",
    src,
    count=1,
)
if new == src:
    # Try fresh-anaconda layout (no veilor patch yet)
    new = re.sub(
        r"elif token == 'error':\n            log\.error\(msg\)\n            raise PayloadInstallationError\(\"An error occurred during the transaction: \" \+ msg\)",
        "elif token == 'error':\n            log.warning('veilor: suppressed dnf5 transaction error: %s', msg)",
        src,
        count=1,
    )
if new == src:
    print("[ERR] transaction_progress.py error-branch not found")
    sys.exit(1)
open(path, "w").write(new)
print("[OK] transaction_progress.py: broad error-branch suppressed")
PYEOF

    if grep -q "veilor: suppressed dnf5 transaction error" "$TP"; then
        rm -f /usr/lib64/python3.14/site-packages/pyanaconda/modules/payloads/payload/dnf/__pycache__/transaction_progress.*.pyc 2>/dev/null || true
        echo "[OK] anaconda transaction_progress.py patched (broad error suppression)"
    else
        echo "[WARN] transaction_progress.py patch did not apply"
    fi
else
    echo "[WARN] transaction_progress.py not found at expected path"
fi

# Enable services
# veilor-firstboot.service NOT enabled on live ISO — it prompts admin pw
# which makes no sense on a live boot. Real installs enable it in their
# generated kickstart's chroot %post (see overlay/usr/local/bin/veilor-installer).
systemctl enable veilor-modules-lock.service
systemctl enable sshd fail2ban usbguard tuned auditd firewalld chronyd
# Mask veilor-firstboot on live so even if it landed in /etc/systemd/system
# (overlay drag), it can't activate.
systemctl mask veilor-firstboot.service 2>/dev/null || true

# Default tuned profile = balanced (AC/battery udev rule will override)
tuned-adm profile veilor-balanced 2>/dev/null || true

# Lock root explicitly (kickstart --lock should already do this)
passwd -l root

# Sanity: zero references to onyx / personal IPs in installed system
if grep -rqi 'onyx\|192\.168\.0\.\|fedora\.local' /etc/veilor* /etc/tuned/profiles/veilor-* 2>/dev/null; then
    echo "[ERR] brand leak detected in /etc — investigate"
fi

echo "════════════════════════════════════════════════════════"
echo " veilor-os install complete"
echo "════════════════════════════════════════════════════════"
%end