home-network-k3s-impl/ci/l0.sh

#!/usr/bin/env bash
# ci/l0.sh — Stage 2+3: ServiceDefinition schema validation + Kyverno L0 policy gate.
# Both run in CI WITHOUT a cluster (docs/14 §"Where each layer runs") — live now.
#
#   Stage 2  schema : catalog/*.yaml validated against the ServiceDefinition
#                     schema (owner: T-0.3, schemas/).
#   Stage 3  L0     : `kyverno test` over platform/kyverno/ — default-deny baseline
#                     present, no plaintext secrets, required labels/egress-class,
#                     ServiceDefinition schema conformance (owner: T-0.5, ADR-0011).
#   Stage 3b L0     : conformance/run.sh --layer l0 — the WHOLE-REPO L0 invariants that
#                     a per-resource policy cannot express (secret hygiene across every
#                     tracked file, least-privilege RBAC, spec-immutability enforcement).
#
# Integration seams are env-overridable (see ci/lib.sh + README). When an owning
# subtree is still a placeholder, this reports SKIPPED (exit 3) for that sub-stage
# rather than a false pass — the gate then knows the seam is unwired, not green.
set -euo pipefail
CI_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck disable=SC1091
source "${CI_DIR}/lib.sh"

rc=0

# ---- Stage 2: ServiceDefinition schema validation ---------------------------
log "Stage: ServiceDefinition schema validation (catalog/ against schemas/)"
if ! entrypoint_ready "$SCHEMA_VALIDATE_CMD"; then
  skip "schema validator not present at '${SCHEMA_VALIDATE_CMD}' (T-0.3 / schemas/ not delivered yet) — UNWIRED, not green"
  summary "- schema: **SKIPPED** (validator entrypoint \`${SCHEMA_VALIDATE_CMD}\` missing — T-0.3)"
else
  if [ -d "$CATALOG_DIR" ] && compgen -G "${CATALOG_DIR}/*.y*ml" >/dev/null 2>&1; then
    if "$SCHEMA_VALIDATE_CMD" "${CATALOG_DIR}"/*.y*ml; then
      ok "schema validation passed"
      summary "- schema: **passed**"
    else
      err "schema validation failed"; summary "- schema: **FAILED**"; rc=1
    fi
  else
    log "no ServiceDefinitions in ${CATALOG_DIR} yet — validating validator is callable only"
    "$SCHEMA_VALIDATE_CMD" --version >/dev/null 2>&1 || true
    ok "schema validator present; no catalog entries to validate"
    summary "- schema: **passed** (no catalog entries yet)"
  fi
fi

# ---- Stage 3: Kyverno L0 policy gate ----------------------------------------
log "Stage: Kyverno L0 policy gate (kyverno test ${KYVERNO_POLICY_DIR})"
# `kyverno test <dir>` discovers kyverno-test.yaml files recursively.
if ! have kyverno; then
  skip "kyverno CLI not installed (pin v${KYVERNO_VERSION}) — cannot run L0 gate"
  summary "- kyverno-l0: **SKIPPED** (kyverno CLI not installed)"
  # Missing tool is an environment gap, not a code pass -> exit 3 unless already failing.
  [ "$rc" -eq 0 ] && rc=3
elif [ ! -d "$KYVERNO_POLICY_DIR" ] || ! compgen -G "${KYVERNO_POLICY_DIR}/**/kyverno-test.yaml" >/dev/null 2>&1 \
     && ! find "$KYVERNO_POLICY_DIR" -name 'kyverno-test.yaml' 2>/dev/null | grep -q .; then
  skip "no kyverno-test.yaml under '${KYVERNO_POLICY_DIR}' (T-0.5 / platform/kyverno not delivered yet) — UNWIRED, not green"
  summary "- kyverno-l0: **SKIPPED** (no policy tests yet — T-0.5)"
else
  # The ClusterPolicies carry a Flux postBuild token in validationFailureAction
  # (${KYVERNO_VALIDATION_ACTION}, substituted in-cluster from
  # clusters/base/cluster-vars.yaml). The offline `kyverno test` CLI does NOT run
  # Flux substitution, so the literal token is an invalid enum value and those
  # policies fail to load (no result rows -> "Not found"). Render a throwaway copy
  # with the base/prod value (Enforce — the strict posture the gate must prove)
  # before testing. This does not change what the policies enforce in-cluster.
  : "${KYVERNO_VALIDATION_ACTION:=Enforce}"
  l0_render="$(mktemp -d)"
  cp -a "${KYVERNO_POLICY_DIR}/." "$l0_render/"
  find "$l0_render" -type f -name '*.yaml' -print0 \
    | xargs -0 sed -i "s/\${KYVERNO_VALIDATION_ACTION}/${KYVERNO_VALIDATION_ACTION}/g"
  if kyverno test "$l0_render"; then
    ok "Kyverno L0 policy tests passed"
    summary "- kyverno-l0: **passed**"
  else
    err "Kyverno L0 policy tests failed"; summary "- kyverno-l0: **FAILED**"; rc=1
  fi
  rm -rf "$l0_render"
fi

# ---- Stage 3b: L0 STATIC conformance checks ---------------------------------
# docs/14's L0 row is "manifests/ServiceDefinitions obey invariants", which is wider
# than what Kyverno alone can express over single resources: whole-repo invariants
# (no plaintext secrets anywhere in git, least-privilege RBAC across every tracked
# binding, the spec-immutability gate's own behaviour) live in the conformance
# harness's tests/l0-static subtree and run with no cluster. This stage executes them
# through the same single-command runner CI and a laptop both use (R-TEST-02).
log "Stage: L0 static conformance checks (${CONFORMANCE_CMD} --layer l0)"
if ! entrypoint_ready "$CONFORMANCE_CMD"; then
  skip "conformance runner not present at '${CONFORMANCE_CMD}' — UNWIRED, not green"
  summary "- l0-static: **SKIPPED** (conformance runner missing)"
  if [ "$rc" -eq 0 ]; then rc=3; fi
else
  load_touched_requirements
  if "$CONFORMANCE_CMD" --layer l0 ${REQ_ARGS[@]+"${REQ_ARGS[@]}"}; then
    ok "L0 static conformance checks passed"
    summary "- l0-static: **passed**"
  else
    err "L0 static conformance checks failed"
    summary "- l0-static: **FAILED**"
    rc=1
  fi
fi

# ---- Stage 3c: Flux post-build substitution safety (UNCONDITIONAL) ----------
# R-ENV-02's promote-once mechanism is `postBuild.substituteFrom cluster-vars`, and it
# FAILS OPEN: an undefined ${TOKEN} becomes the empty string and the Kustomization still
# reports Ready. That emptied Cilium's k8sServiceHost and broke the CNI on 2/3 dev nodes
# (DECISIONS-LOG 2026-09-01, "substitution race that fails OPEN"). The check asserts every
# ${...} in every substituted path is DEFINED in cluster-vars or deliberately ESCAPED
# `$${...}` — i.e. that enabling the StrictPostBuildSubstitutions feature gate cannot fail
# a legitimate manifest, and that no expansion silently empties today.
#
# WHY THIS IS ITS OWN STAGE and not left to Stage 3b: 3b scopes the conformance run to the
# TOUCHED requirements (R-TEST-03), and ci/touched-requirements.sh's coarse path map keys
# only clusters/* to R-ENV-02 — an edit to a SUBSTITUTED manifest under apps/ or platform/
# attributes no requirement, so the requirement-scoped selection would filter this check
# out of exactly the change that introduces the bug. The invariant is whole-repo (same
# reasoning as spec-immutability's own gate stage), so it runs on EVERY gate invocation.
# When 3b's touched set does include R-ENV-02/R-GITOPS-01 the check runs twice; it is a
# sub-second offline scan with no side effects, so the duplication is not worth avoiding.
SUBST_CHECK="${SUBST_CHECK:-${REPO_ROOT}/conformance/tests/l0-static/flux-postbuild-substitution/check.sh}"
log "Stage: Flux postBuild substitution safety (${SUBST_CHECK})"
if [ ! -f "$SUBST_CHECK" ]; then
  skip "substitution check not present at '${SUBST_CHECK}' — UNWIRED, not green"
  summary "- subst-safety: **SKIPPED** (check missing)"
  if [ "$rc" -eq 0 ]; then rc=3; fi
else
  subst_rc=0
  bash "$SUBST_CHECK" || subst_rc=$?
  case "$subst_rc" in
    0) ok "Flux postBuild substitution safety passed"
       summary "- subst-safety: **passed**" ;;
    3) skip "substitution check SKIPPED (clusters/ absent) — not a pass"
       summary "- subst-safety: **SKIPPED** (nothing to audit)"
       if [ "$rc" -eq 0 ]; then rc=3; fi ;;
    *) err "Flux postBuild substitution safety FAILED"
       summary "- subst-safety: **FAILED**"; rc=1 ;;
  esac
fi

case "$rc" in
  0) ok "L0 stage complete" ;;
  3) skip "L0 stage incomplete (unwired seam / missing tool) — not a pass" ;;
  *) err "L0 stage failed" ;;
esac
exit "$rc"