ci: add environment gate and Flux rollout verification to cd pipeline
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Successful in 4s

Aligns hyperguild's cd.yml with the cobalt-dingo reference pattern:
- Add environment: staging to the deploy job
- Add Flux reconcile trigger after infra repo push
- Add polling wait for supervisor and ingestion image tags to propagate
- Add rollout status verification for both deployments with failure
  diagnostics (pod status, events, describe)
This commit is contained in:
Mathias Bergqvist
2026-05-07 21:52:52 +02:00
parent c509ae2a5f
commit 7139a3ca74

View File

@@ -11,6 +11,7 @@ jobs:
name: Build and deploy
runs-on: self-hosted
if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.event == 'push' }}
environment: staging
env:
SERVICE: supervisor
IMAGE: gitea.d-ma.be/mathias/supervisor
@@ -119,3 +120,74 @@ jobs:
git push
echo "Infra repo updated: ${SERVICE}+ingestion → ${IMAGE_TAG}"
- name: Trigger Flux reconcile (immediate)
run: |
kubectl -n flux-system annotate gitrepository flux-system \
reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
kubectl -n flux-system annotate kustomization apps \
reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
- name: Wait for Flux to apply new supervisor image
run: |
EXPECTED="gitea.d-ma.be/mathias/supervisor:${{ github.sha }}"
for i in $(seq 1 60); do
CURRENT=$(kubectl get deploy supervisor -n supervisor \
-o jsonpath='{.spec.template.spec.containers[0].image}' 2>/dev/null || echo "")
if [ "$CURRENT" = "$EXPECTED" ]; then
echo "✓ Flux applied supervisor image after ${i}s"
break
fi
sleep 1
done
kubectl get deploy supervisor -n supervisor \
-o jsonpath='{.spec.template.spec.containers[0].image}' \
| grep -qx "$EXPECTED" \
|| { echo "✗ Flux did not apply supervisor image within 60s"; exit 1; }
- name: Wait for Flux to apply new ingestion image
run: |
EXPECTED="gitea.d-ma.be/mathias/ingestion:${{ github.sha }}"
for i in $(seq 1 60); do
CURRENT=$(kubectl get deploy ingestion -n supervisor \
-o jsonpath='{.spec.template.spec.containers[0].image}' 2>/dev/null || echo "")
if [ "$CURRENT" = "$EXPECTED" ]; then
echo "✓ Flux applied ingestion image after ${i}s"
break
fi
sleep 1
done
kubectl get deploy ingestion -n supervisor \
-o jsonpath='{.spec.template.spec.containers[0].image}' \
| grep -qx "$EXPECTED" \
|| { echo "✗ Flux did not apply ingestion image within 60s"; exit 1; }
- name: Verify supervisor rollout
run: |
kubectl rollout status deployment/supervisor \
--namespace supervisor \
--timeout=120s \
|| {
echo "── pod status ──"
kubectl get pods -n supervisor -o wide
echo "── events ──"
kubectl get events -n supervisor --sort-by='.lastTimestamp' | tail -20
echo "── describe ──"
kubectl describe pods -n supervisor -l app=supervisor | tail -40
exit 1
}
- name: Verify ingestion rollout
run: |
kubectl rollout status deployment/ingestion \
--namespace supervisor \
--timeout=120s \
|| {
echo "── pod status ──"
kubectl get pods -n supervisor -o wide
echo "── events ──"
kubectl get events -n supervisor --sort-by='.lastTimestamp' | tail -20
echo "── describe ──"
kubectl describe pods -n supervisor -l app=ingestion | tail -40
exit 1
}