test(preprod): two-host routing simulation, drill suite, CI security scanning
- infra/scripts/simulate-two-host/: real two-Docker-network simulation (Gateway genuinely isolated from any Lab bridge network) proving the Lab Host Router fix - 13/13 real assertions (HTTP+WebSocket through the Router, Alice/Bob isolation, garbage/destroyed tokens, mTLS-only Router access). - infra/scripts/drills/: Lab Host loss/rebuild (9/9), deployment rollback, CI-fails-closed (6 required failure modes), fake cohort dress rehearsal (14/14, one continuous narrative through the real app). - infra/ci/gitea-workflows/build-and-test.yml: new security-scan job (npm audit, gitleaks, hadolint, shellcheck, trivy - all free/open-source), severity policy in docs/SECURITY_SCANNING.md (CRITICAL/HIGH blocks, MEDIUM/LOW reported only). Gates build-images alongside regression. Found and fixed two real pre-existing bugs via the CI-fails-closed drill: staging-smoke-test.sh and production-smoke-test.sh both had a classic set -e gotcha (curl ... && echo "OK" as one statement - a failing command that isn't last in an && chain doesn't trigger -e) that let an unreachable/broken endpoint fall through silently instead of failing the smoke test. platform/test/e2e-phase3a.js updated for the new paginated /api/admin/audit-events response shape (Phase 4.1 pagination work).
This commit is contained in:
@@ -40,16 +40,19 @@ jobs:
|
||||
|
||||
- name: Install dependencies (all first-party services)
|
||||
run: |
|
||||
for d in backend frontend platform/api platform/gateway platform/provisioner; do
|
||||
for d in backend frontend platform/api platform/gateway platform/provisioner platform/lab-router; do
|
||||
(cd "$d" && npm ci)
|
||||
done
|
||||
|
||||
- name: Syntax-check every service
|
||||
run: |
|
||||
for d in backend frontend/src platform/api platform/gateway platform/provisioner; do
|
||||
for d in backend frontend/src platform/api platform/gateway platform/provisioner platform/lab-router; do
|
||||
find "$d" -name '*.js' -not -path '*/node_modules/*' -exec node --check {} \;
|
||||
done
|
||||
|
||||
- name: Lab Host Router unit tests (Phase 4.1 — fast, no Docker daemon needed)
|
||||
run: (cd platform/lab-router && npm test)
|
||||
|
||||
- name: Build frontend
|
||||
run: (cd frontend && npm run build)
|
||||
|
||||
@@ -75,8 +78,56 @@ jobs:
|
||||
# can't grant safely — they stay a LOCAL/staging pre-promotion step
|
||||
# (infra/scripts/staging-smoke-test.sh), not this job. See docs/PHASE4_PRODUCTION_INFRASTRUCTURE.md §18.
|
||||
|
||||
# Phase 4.1 §24 — free/open-source security scanning, no paid tooling, no signup required for
|
||||
# any of these. Severity policy (docs/SECURITY_SCANNING.md): CRITICAL/HIGH findings fail the
|
||||
# build; MEDIUM/LOW are reported but never block a merge — a build that's permanently red over
|
||||
# an unrelated low-severity transitive dependency finding trains everyone to ignore red builds.
|
||||
security-scan:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "20"
|
||||
|
||||
- name: npm audit (dependency vulnerabilities) — fails only on high/critical
|
||||
run: |
|
||||
FAIL=0
|
||||
for d in backend frontend platform/api platform/gateway platform/provisioner platform/lab-router; do
|
||||
echo "== $d =="
|
||||
(cd "$d" && npm audit --audit-level=high) || FAIL=1
|
||||
done
|
||||
exit $FAIL
|
||||
|
||||
- name: Secret scanning (gitleaks — free, no account needed)
|
||||
run: docker run --rm -v "$PWD:/repo" zricethezav/gitleaks:latest detect --source=/repo --no-git -v
|
||||
|
||||
- name: Dockerfile linting (hadolint — free)
|
||||
run: |
|
||||
FAIL=0
|
||||
for f in Dockerfile platform/api/Dockerfile platform/gateway/Dockerfile platform/provisioner/Dockerfile platform/egress-proxy/Dockerfile platform/lab-router/Dockerfile; do
|
||||
echo "== $f =="
|
||||
docker run --rm -i hadolint/hadolint < "$f" || FAIL=1
|
||||
done
|
||||
exit $FAIL
|
||||
|
||||
# -S error, not warning — matches docs/SECURITY_SCANNING.md's severity policy. Real run
|
||||
# against this tree at -S warning surfaces only style nits (unused loop vars, a missing
|
||||
# `cd ... || exit` guard) on scripts that are otherwise correct; failing the build on
|
||||
# those trains everyone to ignore the check.
|
||||
- name: Shell linting (shellcheck — free, standard)
|
||||
run: |
|
||||
sudo apt-get update -qq && sudo apt-get install -y -qq shellcheck
|
||||
find infra -name '*.sh' -exec shellcheck -S error {} \+
|
||||
|
||||
- name: Container image scanning (trivy — free, no account needed)
|
||||
run: |
|
||||
docker build -q -t rootnode-scan/platform-api -f platform/api/Dockerfile .
|
||||
docker run --rm -v /var/run/docker.sock:/var/run/docker.sock aquasec/trivy:latest image \
|
||||
--severity HIGH,CRITICAL --exit-code 1 rootnode-scan/platform-api
|
||||
|
||||
build-images:
|
||||
needs: regression
|
||||
needs: [regression, security-scan]
|
||||
if: github.ref == 'refs/heads/main'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
|
||||
Reference in New Issue
Block a user