home-network-k3s-impl/bootstrap/flux/bootstrap.sh

#!/usr/bin/env bash
#
# bootstrap.sh — the SINGLE Flux + SOPS bootstrap entrypoint for the dev cluster.
#
# Phase 1, T-1.4 · ADR-0004 (Flux) · ADR-0007 (SOPS+age) · R-GITOPS-01 · R-SEC-01.
# =============================================================================
#   *** AUTHORED, NOT RUN. The Infra worker's FINAL Ansible play invokes this   ***
#   *** (interface contract, see ../README.md). Agents must not execute it.     ***
# =============================================================================
#
# WHAT THIS DOES (Phase 1, bootstrap-source method — reconciles from the LOCAL repo, no remote
# git host exists yet per spec docs/05 + CONTRIBUTING.md):
#
#   1. `flux install`   — deploy the Flux controllers. Besides the default set (source, kustomize,
#                         helm, notification) we ALSO install the two IMAGE controllers via
#                         `--components-extra` (see FLUX_COMPONENTS_EXTRA below): image-reflector-
#                         controller + image-automation-controller. These register the
#                         image.toolkit.fluxcd.io CRDs (ImageRepository/ImagePolicy/ImageUpdateAutomation)
#                         that Phase-4 hands-off updates need (ADR-0009, R-UPD-02). They are part of the
#                         flux-system install exactly like the other 4 controllers — NOT a reconciled
#                         HelmRelease — so their CRDs pre-exist before the first reconcile (this is why
#                         platform/image-automation can carry the ImageUpdateAutomation CR without the
#                         F-MON1 controllers/configs split: the CRD is present at bootstrap, like
#                         GitRepository/Kustomization are). WS-UPDATE (T-4.5).
#                         We do NOT use `flux bootstrap git` in Phase 1 because that command commits
#                         and OWNS its own gotk-sync GitRepository+Kustomization named `flux-system`.
#                         Our entrypoints are ALREADY authored in clusters/base (flux-system.yaml =
#                         the GitRepository; platform.yaml + platform-config.yaml + the app-wave
#                         Kustomizations apps-wave-0/1/2.yaml + apps-vms.yaml = the Kustomizations;
#                         the single apps.yaml was retired). Letting
#                         bootstrap regenerate them would DUPLICATE/conflict. `flux install` +
#                         applying the authored clusters/dev overlay is the reconciling path.
#   2. sops-age Secret  — the operator installs the age PRIVATE key out-of-band BEFORE reconcile so
#                         decryption works on first pass (../sops/age-key-secret.md). This script
#                         only VERIFIES it exists; it never handles key material.
#   3. `kubectl apply -k clusters/dev` — materialises the authored reconciliation graph:
#                         GitRepository `flux-system` (source) -> Kustomization `platform` ->
#                         `platform-config` -> the app-wave Kustomizations `apps-wave-0/1/2`
#                         (chained dependsOn) + `apps-vms`, with cluster-vars overlay
#                         (R-ENV-02) and per-Kustomization SOPS decryption enabled via ./patches/.
#
# PREREQUISITES the operator/PM resolves before this runs (see ../README.md "Handoff"):
#   - clusters/base/flux-system.yaml url placeholder is overridden — wire ./patches/flux-system-
#     source-url.yaml into clusters/dev/kustomization.yaml (or set the URL) so the source is real.
#   - ./patches/platform-sops-decryption.yaml + apps-sops-decryption.yaml are wired into
#     clusters/dev/kustomization.yaml `patches:` so decryption is enabled at reconcile.
#   - the repo-root .sops.yaml carries the real age recipient (single canonical file; no copy under ../sops).
#
# PHASE 6 (WS-GITOPS, later — NOT Phase 1): once Gitea is up, cut the source over with
# `flux bootstrap git` against gitea.home.keithjackson.dev — see ../README.md "Phase-6 cutover".
#
set -euo pipefail

# --- config (env-overridable) ------------------------------------------------
FLUX_ENV_PATH="${FLUX_ENV_PATH:-clusters/dev}"     # dev is the ONLY Phase-1 build target
FLUX_NAMESPACE="${FLUX_NAMESPACE:-flux-system}"
SOPS_SECRET_NAME="${SOPS_SECRET_NAME:-sops-age}"
# The two Phase-4 image-automation controllers are installed alongside the default set so their CRDs
# exist before reconcile (ADR-0009, R-UPD-02). Override to "" to build a cluster without them.
FLUX_COMPONENTS_EXTRA="${FLUX_COMPONENTS_EXTRA:-image-reflector-controller,image-automation-controller}"

script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
repo_root="$(git -C "${script_dir}" rev-parse --show-toplevel 2>/dev/null || (cd "${script_dir}/../.." && pwd))"

echo "==> Flux + SOPS bootstrap (dev) — path=${FLUX_ENV_PATH}"

# --- 0. tooling present (from infra/devcontainer; versions pinned there) ------
for bin in flux kubectl; do
  command -v "$bin" >/dev/null 2>&1 || { echo "ERROR: '$bin' not found (use infra/devcontainer)." >&2; exit 1; }
done

# --- 1. install Flux controllers (rendered through ./components) --------------
# Default controllers + the image-reflector/image-automation pair (Phase-4 hands-off updates,
# ADR-0009). `--components-extra` regenerates flux-system with all controllers and registers the
# image.toolkit.fluxcd.io CRDs before any reconcile — so platform/image-automation's CR applies cleanly.
#
# We do NOT run `flux install` directly any more. The controllers need CUSTOMIZING (currently:
# --feature-gates=StrictPostBuildSubstitutions=true on kustomize-controller, so an undefined
# postBuild variable FAILS the Kustomization instead of silently rendering an empty string — see
# ./components/kustomization.yaml and the 2026-09-01 INCIDENT entry in DECISIONS-LOG.md).
#
# `flux install` has no flag for that, and because this repo does not use `flux bootstrap` the
# controllers are not in git for a Flux Kustomization to patch. So we use the mechanism Flux
# documents for hand-installed clusters ("Customize Flux manifests"):
#
#     flux install --export  >  gotk-components.yaml     # exact manifests `flux install` would apply
#     kustomize overlay      =  ./components/kustomization.yaml (checked in — the ONLY hand-authored part)
#     kubectl apply -k
#
# The export is regenerated from the PINNED flux CLI on every run (FLUX_VERSION,
# infra/devcontainer/versions.env), so nothing is vendored and nothing can drift. The render dir is
# a temp dir — the repo tree is never written to.
#
# ESCAPE HATCH: FLUX_INSTALL_PLAIN=1 falls back to a bare `flux install` (no customization, so NO
# strict substitution). Use only to unblock a bring-up if the render path misbehaves, and say so.
echo "==> [1/3] installing Flux controllers${FLUX_COMPONENTS_EXTRA:+ (+ extra: ${FLUX_COMPONENTS_EXTRA})}"
flux_install_args=(--namespace="${FLUX_NAMESPACE}")
[ -n "${FLUX_COMPONENTS_EXTRA}" ] && flux_install_args+=(--components-extra="${FLUX_COMPONENTS_EXTRA}")

if [ "${FLUX_INSTALL_PLAIN:-0}" = "1" ]; then
  echo "    WARNING: FLUX_INSTALL_PLAIN=1 — controller customization SKIPPED."
  echo "             StrictPostBuildSubstitutions will NOT be enabled; substitution fails OPEN."
  flux install "${flux_install_args[@]}"
else
  components_dir="${script_dir}/components"
  [ -f "${components_dir}/kustomization.yaml" ] || {
    echo "ERROR: ${components_dir}/kustomization.yaml missing — refusing to install uncustomized." >&2
    echo "       (Override with FLUX_INSTALL_PLAIN=1 only if you accept fail-OPEN substitution.)" >&2
    exit 1
  }
  render_dir="$(mktemp -d)"
  trap 'rm -rf "${render_dir}"' EXIT
  echo "    rendering flux install --export through ${components_dir}"
  flux install --export "${flux_install_args[@]}" > "${render_dir}/gotk-components.yaml"
  cp "${components_dir}/kustomization.yaml" "${render_dir}/kustomization.yaml"
  # Fail fast if the overlay cannot build (e.g. a patch target that no longer exists after a Flux
  # version bump) — better a hard stop than silently installing without the feature gate.
  kubectl kustomize "${render_dir}" > "${render_dir}/rendered.yaml"
  grep -q -- '--feature-gates=StrictPostBuildSubstitutions=true' "${render_dir}/rendered.yaml" || {
    echo "ERROR: the StrictPostBuildSubstitutions patch did not apply to the rendered manifests." >&2
    echo "       Check ./components/kustomization.yaml against this flux CLI version." >&2
    exit 1
  }
  kubectl apply -f "${render_dir}/rendered.yaml"
fi

# --- 2. verify the out-of-band age key Secret exists -------------------------
# We DO NOT create it here (it holds the private key). The operator installs it per
# ../sops/age-key-secret.md. Fail fast if missing so decryption can't silently no-op.
echo "==> [2/3] verifying ${SOPS_SECRET_NAME} Secret exists in ${FLUX_NAMESPACE}"
if ! kubectl -n "${FLUX_NAMESPACE}" get secret "${SOPS_SECRET_NAME}" >/dev/null 2>&1; then
  echo "ERROR: Secret ${FLUX_NAMESPACE}/${SOPS_SECRET_NAME} not found." >&2
  echo "       Install the age private key first: bootstrap/sops/age-key-secret.md" >&2
  exit 1
fi

# --- 3. apply the authored dev entrypoint ------------------------------------
echo "==> [3/3] kubectl apply -k ${FLUX_ENV_PATH}"
kubectl apply -k "${repo_root}/${FLUX_ENV_PATH}"

echo
echo "==> Bootstrap applied. Watch reconciliation with (read-only):"
echo "      flux get kustomizations --watch"
echo "      flux get sources git -n ${FLUX_NAMESPACE}"
echo "    'platform' should go Ready, then 'apps' (dependsOn platform)."