The committed apps/ goldens were a MIX of two render flag sets: 8 services were rendered with `--no-image-automation` (no image CRs) while gitea and nextcloud carried stale ImageRepository/ImagePolicy CRs from a render WITHOUT the flag. Neither single command reproduced all goldens, and the gate did not catch it. Part A — canonical render: python3 catalog/render.py --all catalog -o apps --wave-layout --no-image-automation `--no-image-automation` is canonical: image automation is authored-but-DISABLED (DECISIONS-LOG; image-reflector/-automation controllers not installed), and every app was onboarded via this flag. Re-render drops the ImageRepository + ImagePolicy objects from gitea + nextcloud only (52 line deletions, purely the trailing image-automation blocks). No functional content changed — the nextcloud postStart hardening and gitea OIDC hook are untouched. Part B — enforcement: ci/render-golden.sh renders every onboarded catalog service with the canonical command into a temp dir and FAILS on ANY diff vs committed apps/ (missing golden or content drift), across all 10 services (not just the 3 L1 spot-checks). Not-onboarded catalog entries (keycloak, vm-demo) are excluded per DESIGN-waves. Wired as a required no-cluster stage in ci/gate.sh, ci/Makefile, and both the live (.gitea/workflows/gate.yml) and dormant (merge-gate.yaml) pipelines. Proof: tampering a golden makes the stage exit 1 (blocks merge); reverting restores exit 0. `make -C ci gate` green in the devcontainer. Co-Authored-By: Claude Opus 4.8 <[email protected]>
108 lines
4.1 KiB
Bash
Executable File
108 lines
4.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# ci/gate.sh — the merge-gate decision. Runs every stage in order and applies the
|
|
# R-TEST-03 rule: a merge is allowed only when the touched-requirement subset is
|
|
# GREEN. Honestly distinguishes three outcomes per stage:
|
|
# pass (0) green
|
|
# fail (1) BLOCKS the merge
|
|
# skip (3) not run (cluster-gated stage w/ no cluster, or unwired seam) —
|
|
# NOT counted as green (HARD RULE 4: don't fake green)
|
|
#
|
|
# Phase 0 policy (no cluster): L0/L1 stages (lint, schema, kyverno, L1 render)
|
|
# MUST be green. L2/L3 SKIP. If the touched subset needs L2/L3 and no cluster is
|
|
# available, the gate reports those requirements UNVERIFIED and — unless
|
|
# REQUIRE_CLUSTER_TESTS=true — does not hard-block Phase-0 bootstrap work, while
|
|
# making the gap loud. Set REQUIRE_CLUSTER_TESTS=true (Phase 1+) to make any
|
|
# skipped, cluster-needing touched requirement a hard block.
|
|
set -uo pipefail # NOTE: no -e; we want to run all stages and aggregate.
|
|
CI_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
# shellcheck disable=SC1091
|
|
source "${CI_DIR}/lib.sh"
|
|
set +e # lib.sh enables -e; the gate must run ALL stages and aggregate, not abort.
|
|
|
|
: "${REQUIRE_CLUSTER_TESTS:=false}"
|
|
|
|
declare -A OUTCOME
|
|
run_stage() {
|
|
local name="$1"; shift
|
|
log "==== stage: ${name} ===="
|
|
"$@"
|
|
local rc=$?
|
|
case "$rc" in
|
|
0) OUTCOME[$name]="pass"; ok "stage ${name}: pass" ;;
|
|
3) OUTCOME[$name]="skip"; skip "stage ${name}: SKIPPED (not run)" ;;
|
|
*) OUTCOME[$name]="fail"; err "stage ${name}: FAIL" ;;
|
|
esac
|
|
}
|
|
|
|
summary "## Merge gate (R-TEST-03)"
|
|
summary ""
|
|
|
|
run_stage spec-immutability "${CI_DIR}/spec-immutability.sh"
|
|
run_stage lint "${CI_DIR}/lint.sh"
|
|
run_stage l0 "${CI_DIR}/l0.sh"
|
|
run_stage render-golden "${CI_DIR}/render-golden.sh"
|
|
run_stage l1 "${CI_DIR}/l1.sh"
|
|
run_stage conformance "${CI_DIR}/conformance.sh"
|
|
|
|
echo >&2
|
|
log "==== gate decision ===="
|
|
BLOCK=0
|
|
|
|
# spec-immutability (R-TEST-06): a FAIL always blocks (the spec was modified/drifted).
|
|
# A skip means the spec repo wasn't available to verify — surfaced, not green.
|
|
case "${OUTCOME[spec-immutability]}" in
|
|
fail) err "spec-immutability: FAILED -> blocks merge (R-TEST-06)"; BLOCK=1 ;;
|
|
skip) warn "spec-immutability: skipped (spec repo unavailable) — not verified" ;;
|
|
pass) ok "spec-immutability: green" ;;
|
|
esac
|
|
|
|
# L0/L1 stages: any failure blocks. A SKIP here means a seam is unwired — in
|
|
# Phase 0 that is tolerated (placeholders), but surfaced. render-golden is a
|
|
# no-cluster reproducibility gate (canonical render == committed apps/ goldens):
|
|
# a FAIL means a golden drifted from its ServiceDefinition source — always blocks.
|
|
for s in lint l0 render-golden l1; do
|
|
case "${OUTCOME[$s]}" in
|
|
fail) err "${s}: FAILED -> blocks merge"; BLOCK=1 ;;
|
|
skip) warn "${s}: skipped (unwired seam / missing tool) — not green" ;;
|
|
pass) ok "${s}: green" ;;
|
|
esac
|
|
done
|
|
|
|
# L2/L3 conformance: cluster-gated.
|
|
case "${OUTCOME[conformance]}" in
|
|
fail)
|
|
err "conformance (L2/L3): FAILED -> blocks merge"; BLOCK=1 ;;
|
|
pass)
|
|
ok "conformance (L2/L3): green" ;;
|
|
skip)
|
|
if cluster_available; then
|
|
err "conformance: skipped despite CLUSTER_AVAILABLE=true -> blocks merge"; BLOCK=1
|
|
else
|
|
mapfile -t reqs < <("${CI_DIR}/touched-requirements.sh" || true)
|
|
if [ "${#reqs[@]}" -gt 0 ]; then
|
|
warn "conformance L2/L3 UNVERIFIED for touched requirements: ${reqs[*]}"
|
|
warn " (no cluster — Phase 0). These are NOT certified green."
|
|
summary "- **UNVERIFIED (no cluster):** ${reqs[*]}"
|
|
if [ "$REQUIRE_CLUSTER_TESTS" = "true" ]; then
|
|
err "REQUIRE_CLUSTER_TESTS=true and cluster-needing requirements are unverified -> blocks merge"
|
|
BLOCK=1
|
|
fi
|
|
else
|
|
skip "conformance L2/L3 skipped; no cluster-needing requirements touched"
|
|
fi
|
|
fi ;;
|
|
esac
|
|
|
|
echo >&2
|
|
if [ "$BLOCK" -eq 0 ]; then
|
|
ok "MERGE GATE: PASS (touched-requirement subset green for the layers that can run)"
|
|
summary ""
|
|
summary "**Result: PASS** — L0/L1 green. L2/L3 status per cluster availability above."
|
|
exit 0
|
|
else
|
|
err "MERGE GATE: BLOCKED"
|
|
summary ""
|
|
summary "**Result: BLOCKED** — see failures above."
|
|
exit 1
|
|
fi
|