fix(ci): relax namespace validation test + add webhook endpoint test #30
+106
-49
@@ -39,6 +39,7 @@ jobs:
|
||||
run: echo "short_sha=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Registry login
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
echo "${REGISTRY_TOKEN}" | docker login "${REGISTRY}" \
|
||||
--username "${REGISTRY_USER}" --password-stdin
|
||||
@@ -47,87 +48,143 @@ jobs:
|
||||
REGISTRY_TOKEN: ${{ secrets.FORGEJO_REGISTRY_TOKEN }}
|
||||
|
||||
- name: Build Docker image
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
docker build --no-cache \
|
||||
-t "${IMAGE}:${{ steps.sha.outputs.short_sha }}" \
|
||||
-f Dockerfile .
|
||||
|
||||
- name: Push image (SHA tag)
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: docker push "${IMAGE}:${{ steps.sha.outputs.short_sha }}"
|
||||
|
||||
# ── Tekton integration tests ─────────────────────────────
|
||||
# ── Deploy canary pod + integration test ────────────────
|
||||
# Canary pod runs in-cluster with real secrets and real upstreams
|
||||
# (Temporal, Gotify). Tests run against its pod IP directly.
|
||||
# Zero downtime: production pods untouched until tests pass.
|
||||
- name: Setup kubeconfig
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
mkdir -p ~/.kube
|
||||
echo "${KUBECONFIG_B64}" | base64 -d > ~/.kube/config
|
||||
kubectl get pipelineruns -n api --no-headers | head -1 || echo 'No PipelineRuns yet'
|
||||
kubectl get nodes --no-headers | head -1
|
||||
echo '✓ kubeconfig works'
|
||||
env:
|
||||
KUBECONFIG_B64: ${{ secrets.KUBECONFIG_B64 }}
|
||||
|
||||
- name: Trigger Tekton PipelineRun
|
||||
id: tekton
|
||||
- name: Deploy canary pod
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
id: canary
|
||||
run: |
|
||||
SHA="${{ steps.sha.outputs.short_sha }}"
|
||||
RUN_NAME="integration-test-${SHA}"
|
||||
POD_NAME="api-gateway-canary-${SHA}"
|
||||
|
||||
# Clean up any previous run with the same name
|
||||
kubectl delete taskrun "${RUN_NAME}" -n api --ignore-not-found
|
||||
# Remove any stale canary
|
||||
kubectl delete pod "${POD_NAME}" -n api --ignore-not-found
|
||||
|
||||
# Create TaskRun — spins up gateway sidecar + curl tests
|
||||
cat <<YAML | kubectl create -f -
|
||||
apiVersion: tekton.dev/v1
|
||||
kind: TaskRun
|
||||
metadata:
|
||||
name: ${RUN_NAME}
|
||||
namespace: api
|
||||
labels:
|
||||
commit-sha: "${SHA}"
|
||||
spec:
|
||||
taskRef:
|
||||
name: integration-test
|
||||
params:
|
||||
- name: image
|
||||
value: "${IMAGE}:${SHA}"
|
||||
YAML
|
||||
# Create canary pod with real secrets + config
|
||||
kubectl run "${POD_NAME}" \
|
||||
--image="${IMAGE}:${SHA}" \
|
||||
--restart=Never \
|
||||
--namespace=api \
|
||||
--labels="app=api-gateway-canary,sha=${SHA}" \
|
||||
--overrides="$(cat <<JSON
|
||||
{
|
||||
"spec": {
|
||||
"imagePullSecrets": [{"name": "forgejo-registry"}],
|
||||
"volumes": [
|
||||
{"name": "config", "secret": {"secretName": "api-gateway-config"}}
|
||||
],
|
||||
"containers": [{
|
||||
"name": "${POD_NAME}",
|
||||
"image": "${IMAGE}:${SHA}",
|
||||
"imagePullPolicy": "Always",
|
||||
"env": [
|
||||
{"name": "LISTEN_ADDR", "value": "0.0.0.0:8080"},
|
||||
{"name": "CONFIG_PATH", "value": "/etc/gateway/config.yaml"},
|
||||
{"name": "LOG_LEVEL", "value": "info"},
|
||||
{"name": "GOTIFY_URL", "valueFrom": {"secretKeyRef": {"name": "gotify-webhook-secret", "key": "gotify-url", "optional": true}}},
|
||||
{"name": "GOTIFY_APP_TOKEN", "valueFrom": {"secretKeyRef": {"name": "gotify-webhook-secret", "key": "gotify-app-token", "optional": true}}},
|
||||
{"name": "FORGEJO_WEBHOOK_SECRET","valueFrom": {"secretKeyRef": {"name": "gotify-webhook-secret", "key": "forgejo-webhook-secret", "optional": true}}},
|
||||
{"name": "AUTH_CLIENT_SECRET", "valueFrom": {"secretKeyRef": {"name": "api-gw-client-secret", "key": "client-secret", "optional": true}}}
|
||||
],
|
||||
"volumeMounts": [
|
||||
{"name": "config", "mountPath": "/etc/gateway", "readOnly": true}
|
||||
],
|
||||
"readinessProbe": {
|
||||
"httpGet": {"path": "/healthz", "port": 8080},
|
||||
"initialDelaySeconds": 3,
|
||||
"periodSeconds": 2
|
||||
}
|
||||
}]
|
||||
}
|
||||
}
|
||||
JSON
|
||||
)"
|
||||
|
||||
echo "✓ TaskRun created: ${RUN_NAME}"
|
||||
echo "✓ Canary pod created: ${POD_NAME}"
|
||||
|
||||
# Wait for completion (Succeeded or Failed)
|
||||
echo "Waiting for tests (timeout 5m)..."
|
||||
if kubectl wait taskrun/"${RUN_NAME}" -n api \
|
||||
--for=condition=Succeeded --timeout=5m 2>/dev/null; then
|
||||
echo "result=pass" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "result=fail" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
# Wait for pod to be ready (real secrets, real upstreams)
|
||||
kubectl wait pod/"${POD_NAME}" -n api \
|
||||
--for=condition=Ready --timeout=90s
|
||||
|
||||
# Print logs + results
|
||||
echo ""
|
||||
echo "=== Test Logs ==="
|
||||
POD=$(kubectl get pod -n api -l tekton.dev/taskRun=${RUN_NAME} -o name | head -1)
|
||||
kubectl logs -n api "${POD}" -c step-run-tests 2>/dev/null || true
|
||||
echo ""
|
||||
REASON=$(kubectl get taskrun "${RUN_NAME}" -n api \
|
||||
-o jsonpath='{.status.conditions[0].reason}')
|
||||
SUMMARY=$(kubectl get taskrun "${RUN_NAME}" -n api \
|
||||
-o jsonpath='{.status.results[?(@.name=="summary")].value}')
|
||||
echo "Status: ${REASON}"
|
||||
# Capture pod IP for test runner
|
||||
POD_IP=$(kubectl get pod "${POD_NAME}" -n api \
|
||||
-o jsonpath='{.status.podIP}')
|
||||
echo "pod_name=${POD_NAME}" >> $GITHUB_OUTPUT
|
||||
echo "pod_ip=${POD_IP}" >> $GITHUB_OUTPUT
|
||||
echo "✓ Canary ready at ${POD_IP}:8080"
|
||||
|
||||
- name: Run integration tests against canary
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
id: tests
|
||||
run: |
|
||||
POD_IP="${{ steps.canary.outputs.pod_ip }}"
|
||||
GW="http://${POD_IP}:8080"
|
||||
RESULTS_DIR="/tmp/test-results"
|
||||
mkdir -p "${RESULTS_DIR}"
|
||||
|
||||
echo "Running integration tests against canary at ${GW}..."
|
||||
sh k8s/tekton/scripts/integration-test.sh
|
||||
|
||||
RESULT=$(cat "${RESULTS_DIR}/result" 2>/dev/null || echo "fail")
|
||||
SUMMARY=$(cat "${RESULTS_DIR}/summary" 2>/dev/null || echo "unknown")
|
||||
echo "Result: ${RESULT}"
|
||||
echo "Summary: ${SUMMARY}"
|
||||
echo "result=${RESULT}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Cleanup canary pod
|
||||
if: always() && github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
POD_NAME="${{ steps.canary.outputs.pod_name }}"
|
||||
kubectl delete pod "${POD_NAME}" -n api --ignore-not-found || true
|
||||
echo "✓ Canary pod removed"
|
||||
|
||||
- name: Gate on test result
|
||||
if: steps.tekton.outputs.result != 'pass'
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main' && steps.tests.outputs.result != 'pass'
|
||||
run: |
|
||||
echo "✗ Integration tests FAILED — image NOT promoted"
|
||||
echo "✗ Integration tests FAILED — production deployment unchanged"
|
||||
exit 1
|
||||
|
||||
# ── Promote only after tests pass ────────────────────────
|
||||
- name: Promote image to latest
|
||||
# ── Zero-downtime promotion ──────────────────────────────
|
||||
# kubectl set image triggers a rolling update: new pods come up
|
||||
# before old pods are terminated. Production traffic uninterrupted.
|
||||
- name: Promote — rolling update
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
SHA="${{ steps.sha.outputs.short_sha }}"
|
||||
kubectl set image deployment/api-gateway \
|
||||
api-gateway="${IMAGE}:${SHA}" -n api
|
||||
kubectl rollout status deployment/api-gateway -n api --timeout=120s
|
||||
echo "✓ Rolling update complete: ${IMAGE}:${SHA}"
|
||||
|
||||
- name: Tag :latest (informational)
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
run: |
|
||||
docker tag "${IMAGE}:${{ steps.sha.outputs.short_sha }}" "${IMAGE}:latest"
|
||||
docker push "${IMAGE}:latest"
|
||||
echo "✓ Promoted to latest"
|
||||
echo "✓ Tagged :latest"
|
||||
|
||||
- name: Cleanup
|
||||
- name: Cleanup docker images
|
||||
if: always()
|
||||
run: docker image prune -af 2>&1 | tail -3 || true
|
||||
|
||||
@@ -2,11 +2,12 @@
|
||||
set -e
|
||||
|
||||
# Integration test runner for API gateway.
|
||||
# Tests X-Service + X-Resource header routing against a gateway on localhost.
|
||||
# Runs against a real canary pod in-cluster (has real secrets + upstreams).
|
||||
# GW env var must be set: e.g. http://10.244.1.5:8080
|
||||
#
|
||||
# Required env:
|
||||
# GW — gateway base URL (e.g. http://localhost:8080)
|
||||
# RESULTS_DIR — directory to write Tekton results
|
||||
# GW — gateway base URL
|
||||
# RESULTS_DIR — directory to write result/summary files
|
||||
|
||||
PASS=0; FAIL=0; TOTAL=0
|
||||
|
||||
@@ -25,28 +26,23 @@ assert() {
|
||||
fi
|
||||
}
|
||||
|
||||
# ── Wait for sidecar gateway ──
|
||||
echo "⏳ Waiting for gateway sidecar..."
|
||||
# ── Wait for gateway ──────────────────────────────────────────────────────────
|
||||
echo "⏳ Waiting for gateway at ${GW}..."
|
||||
READY=false
|
||||
for i in $(seq 1 60); do
|
||||
for i in $(seq 1 30); do
|
||||
CODE=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
|
||||
if [ "$CODE" = "200" ]; then
|
||||
sleep 1
|
||||
C2=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
|
||||
C3=$(curl -s -o /dev/null -w '%{http_code}' "${GW}/healthz" 2>/dev/null || echo "000")
|
||||
if [ "$C2" = "200" ] && [ "$C3" = "200" ]; then
|
||||
READY=true
|
||||
echo "✓ Gateway ready"
|
||||
break
|
||||
fi
|
||||
READY=true
|
||||
echo "✓ Gateway ready"
|
||||
break
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
|
||||
if [ "$READY" = "false" ]; then
|
||||
echo "✗ Gateway never became ready"
|
||||
echo "fail" > "${RESULTS_DIR}/result"
|
||||
echo "0/0 gateway timeout" > "${RESULTS_DIR}/summary"
|
||||
echo "fail" > "${RESULTS_DIR}/result"
|
||||
echo "0/0 timeout" > "${RESULTS_DIR}/summary"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
@@ -54,99 +50,71 @@ echo ""
|
||||
echo "═══ Integration Tests ═══"
|
||||
echo ""
|
||||
|
||||
# ── Health ──
|
||||
# ── Health ────────────────────────────────────────────────────────────────────
|
||||
echo "▸ Health"
|
||||
assert "GET /healthz" 200 -X GET "${GW}/healthz"
|
||||
assert "GET /readyz" 200 -X GET "${GW}/readyz"
|
||||
assert "GET /healthz" 200 -X GET "${GW}/healthz"
|
||||
assert "GET /readyz" 200 -X GET "${GW}/readyz"
|
||||
|
||||
# ── Header validation ──
|
||||
# ── Header validation ─────────────────────────────────────────────────────────
|
||||
echo "▸ Header validation"
|
||||
assert "X-Service without X-Resource → 400" 400 \
|
||||
-X GET -H "X-Service: memory" "${GW}/"
|
||||
assert "unknown service → 404" 404 \
|
||||
-X GET -H "X-Service: nonexistent" -H "X-Resource: foo" "${GW}/"
|
||||
|
||||
# ── S3 (no auth, MinIO rejects → 403) ──
|
||||
# ── S3 (no auth, MinIO rejects → 403) ────────────────────────────────────────
|
||||
echo "▸ S3 service"
|
||||
assert "s3/list-objects" 403 \
|
||||
assert "s3/list-objects → 403" 403 \
|
||||
-X GET -H "X-Service: s3" -H "X-Resource: list-objects" "${GW}/"
|
||||
|
||||
# ── SQS (auth required → 401) ──
|
||||
# ── SQS (auth required → 401) ─────────────────────────────────────────────────
|
||||
echo "▸ SQS service"
|
||||
assert "sqs/list-queues" 401 \
|
||||
assert "sqs/list-queues → 401" 401 \
|
||||
-X GET -H "X-Service: sqs" -H "X-Resource: list-queues" "${GW}/"
|
||||
|
||||
# ── Workflow visibility (namespace pass-down) ──
|
||||
# ── Workflow ──────────────────────────────────────────────────────────────────
|
||||
echo "▸ Workflow service"
|
||||
|
||||
# Test 1: List workflows in poimen-harness namespace (should see 4 terminated workflows)
|
||||
echo " Testing workflow visibility in poimen-harness namespace..."
|
||||
WF_LIST=$(curl -s -X POST \
|
||||
# List with namespace — real Temporal call.
|
||||
# 200 = Temporal reachable, 503 = Temporal down but gateway routed correctly.
|
||||
echo " Testing workflow list (poimen-harness namespace)..."
|
||||
WF_LIST=$(curl -s \
|
||||
-H "X-Service: workflow" \
|
||||
-H "X-Resource: list" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"namespace": "poimen-harness"}' \
|
||||
"${GW}/" 2>/dev/null || echo '{}')
|
||||
|
||||
# Accept executions (Temporal reachable) or TEMPORAL_UNAVAILABLE (no Temporal in CI sidecar).
|
||||
# Both mean the gateway correctly routed the request — not a stub return.
|
||||
TOTAL=$((TOTAL + 1))
|
||||
if echo "$WF_LIST" | grep -qE '"executions"|"TEMPORAL_UNAVAILABLE"'; then
|
||||
echo " ✓ Workflow list: gateway routed correctly"
|
||||
echo " ✓ workflow/list responded correctly"
|
||||
PASS=$((PASS + 1))
|
||||
else
|
||||
echo " ✗ Workflow list: unexpected response: $WF_LIST"
|
||||
echo " ✗ workflow/list unexpected: $WF_LIST"
|
||||
FAIL=$((FAIL + 1))
|
||||
fi
|
||||
TOTAL=$((TOTAL + 1))
|
||||
|
||||
# Test 2: Verify we can query terminated workflows
|
||||
echo " Testing terminated workflow visibility..."
|
||||
if echo "$WF_LIST" | grep -q '"Completed\|"status"'; then
|
||||
echo " ✓ Found completed/terminated workflows in response"
|
||||
PASS=$((PASS + 1))
|
||||
else
|
||||
echo " ⚠ No terminated workflows found in response (may be empty namespace)"
|
||||
# Don't fail if namespace is empty - just note it
|
||||
fi
|
||||
TOTAL=$((TOTAL + 1))
|
||||
|
||||
# Test 3: Verify namespace is required (missing namespace → 400)
|
||||
echo " Testing namespace validation..."
|
||||
NO_NS=$(curl -s -w '%{http_code}' -X POST \
|
||||
# Namespace is required — canary pod has real WorkflowAdapter → must return 400
|
||||
assert "workflow/list without namespace → 400" 400 \
|
||||
-X POST \
|
||||
-H "X-Service: workflow" \
|
||||
-H "X-Resource: list" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{}' \
|
||||
"${GW}/" 2>/dev/null || echo "000")
|
||||
"${GW}/"
|
||||
|
||||
if [ "$NO_NS" = "400" ] || [ "$NO_NS" = "404" ]; then
|
||||
echo " ✓ Namespace validation: got ${NO_NS} (400=enforced 404=old image)"
|
||||
PASS=$((PASS + 1))
|
||||
else
|
||||
echo " ✗ Unexpected code for missing namespace, got $NO_NS"
|
||||
FAIL=$((FAIL + 1))
|
||||
fi
|
||||
TOTAL=$((TOTAL + 1))
|
||||
# ── Forgejo webhook ───────────────────────────────────────────────────────────
|
||||
echo "▸ Forgejo webhook"
|
||||
# Canary pod has real handler wired. No HMAC secret set (optional) → handler
|
||||
# skips verification and forwards to Gotify (or logs if Gotify unavailable).
|
||||
assert "POST /v1/webhooks/forgejo → 200" 200 \
|
||||
-X POST \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Gitea-Event: push" \
|
||||
-d '{"ref":"refs/heads/main","commits":[{"message":"test"}],"repository":{"full_name":"test/repo"},"sender":{"login":"ci"}}' \
|
||||
"${GW}/v1/webhooks/forgejo"
|
||||
|
||||
echo ""
|
||||
# ── Forgejo webhook ──
|
||||
# NOTE: old image returns 404 (endpoint not present), new image returns 200.
|
||||
# Accept both during rollout — test confirms routing is wired.
|
||||
echo "▸ Forgejo webhook"
|
||||
WH_CODE=$(curl -s -o /dev/null -w '%{http_code}' \
|
||||
-X POST -H "Content-Type: application/json" \
|
||||
-H "X-Gitea-Event: push" \
|
||||
-d '{"ref":"refs/heads/main","commits":[],"repository":{"full_name":"test/repo"},"sender":{"login":"ci"}}' \
|
||||
"${GW}/v1/webhooks/forgejo" 2>/dev/null || echo "000")
|
||||
TOTAL=$((TOTAL + 1))
|
||||
if [ "$WH_CODE" = "200" ] || [ "$WH_CODE" = "404" ]; then
|
||||
echo " ✓ /v1/webhooks/forgejo: ${WH_CODE} (200=live 404=old image)"
|
||||
PASS=$((PASS + 1))
|
||||
else
|
||||
echo " ✗ /v1/webhooks/forgejo: unexpected ${WH_CODE}"
|
||||
FAIL=$((FAIL + 1))
|
||||
fi
|
||||
|
||||
echo "═══ Results: ${PASS}/${TOTAL} passed, ${FAIL} failed ═══"
|
||||
|
||||
if [ "$FAIL" -eq 0 ]; then
|
||||
|
||||
Reference in New Issue
Block a user