fix: bump seed pod timeout to 5m and add debug diagnostics on pipeline failures

infra/inttest/run_pipeline.sh

@@ -88,6 +88,29 @@ stage_fail() {
   log "✗ Stage: $name FAILED after ${STAGE_DURATION[$name]}s"
 }
 
+debug_pod_failure() {
+  local pod_name="$1"
+  local label="${2:-}"
+  log "─── DEBUG: pod failure diagnostics ───"
+  if [ -n "$label" ]; then
+    # Find pod by label selector
+    local found_pod
+    found_pod=$(kubectl get pods -n "$NAMESPACE" -l "$label" -o jsonpath='{.items[0].metadata.name}' 2>/dev/null || true)
+    if [ -n "$found_pod" ]; then
+      pod_name="$found_pod"
+    fi
+  fi
+  log "Pod describe ($pod_name):"
+  kubectl describe pod "$pod_name" -n "$NAMESPACE" 2>&1 | tail -40 || true
+  log "Pod logs ($pod_name):"
+  kubectl logs "$pod_name" -n "$NAMESPACE" --tail=60 2>&1 || true
+  log "Pod status:"
+  kubectl get pod "$pod_name" -n "$NAMESPACE" -o wide 2>&1 || true
+  log "Recent events in namespace:"
+  kubectl get events -n "$NAMESPACE" --sort-by='.lastTimestamp' 2>&1 | tail -20 || true
+  log "─── END DEBUG ───"
+}
+
 # ── Parse CLI args ───────────────────────────────────────────────────────────
 while [[ $# -gt 0 ]]; do
   case $1 in
@@ -268,6 +291,7 @@ envsubst < "$REPO_ROOT/infra/inttest/minio.yaml" | kubectl apply -n "$NAMESPACE"
 log "Waiting for postgres readiness ..."
 if ! kubectl wait --for=condition=ready pod -l app=postgres -n "$NAMESPACE" --timeout=120s; then
   log "FATAL: PostgreSQL did not become ready"
+  debug_pod_failure "postgres" "app=postgres"
   stage_fail "infra_deploy"
   PIPELINE_EXIT_CODE=2
   exit 2
@@ -276,6 +300,7 @@ fi
 log "Waiting for redis readiness ..."
 if ! kubectl wait --for=condition=ready pod -l app=redis -n "$NAMESPACE" --timeout=60s; then
   log "FATAL: Redis did not become ready"
+  debug_pod_failure "redis" "app=redis"
   stage_fail "infra_deploy"
   PIPELINE_EXIT_CODE=2
   exit 2
@@ -284,13 +309,19 @@ fi
 log "Waiting for minio readiness ..."
 if ! kubectl wait --for=condition=ready pod -l app=minio -n "$NAMESPACE" --timeout=60s; then
   log "FATAL: MinIO did not become ready"
+  debug_pod_failure "minio" "app=minio"
   stage_fail "infra_deploy"
   PIPELINE_EXIT_CODE=2
   exit 2
 fi
 
 log "Waiting for minio-bucket-init job ..."
-kubectl wait --for=condition=complete job/minio-bucket-init -n "$NAMESPACE" --timeout=60s || true
+if ! kubectl wait --for=condition=complete job/minio-bucket-init -n "$NAMESPACE" --timeout=120s; then
+  log "WARNING: minio-bucket-init job did not complete within 120s"
+  log "Bucket-init pod logs:"
+  kubectl logs -l app=minio-bucket-init -n "$NAMESPACE" --tail=30 2>&1 || true
+  kubectl describe job/minio-bucket-init -n "$NAMESPACE" 2>&1 | tail -20 || true
+fi
 
 stage_end "infra_deploy" "ok"
 
@@ -307,6 +338,7 @@ if ! kubectl run seed-sandbox \
     --restart=Never \
     --rm \
     --attach \
+    --pod-running-timeout=5m \
     --namespace="$NAMESPACE" \
     --image-pull-policy=Always \
     --overrides='{
@@ -326,6 +358,7 @@ if ! kubectl run seed-sandbox \
     --env="MINIO_SECRET_KEY=minioadmin" \
     --command -- python -m tests.integration.seed_sandbox; then
   log "FATAL: Database seed failed"
+  debug_pod_failure "seed-sandbox" "run=seed-sandbox"
   stage_fail "seed_data"
   PIPELINE_EXIT_CODE=2
   exit 2
@@ -337,6 +370,7 @@ if ! kubectl run seed-minio \
     --restart=Never \
     --rm \
     --attach \
+    --pod-running-timeout=5m \
     --namespace="$NAMESPACE" \
     --image-pull-policy=Always \
     --overrides='{
@@ -351,6 +385,7 @@ if ! kubectl run seed-minio \
     --env="MINIO_SECRET_KEY=minioadmin" \
     --command -- python -m tests.integration.seed_minio; then
   log "FATAL: MinIO seed failed"
+  debug_pod_failure "seed-minio" "run=seed-minio"
   stage_fail "seed_data"
   PIPELINE_EXIT_CODE=2
   exit 2
@@ -371,6 +406,11 @@ envsubst < "$REPO_ROOT/infra/inttest/services.yaml" \
 log "Waiting for all API services to become ready ..."
 if ! kubectl wait --for=condition=ready pod -l tier=api -n "$NAMESPACE" --timeout=120s; then
   log "FATAL: API services did not become ready"
+  log "Pod statuses:"
+  kubectl get pods -n "$NAMESPACE" -l tier=api -o wide 2>&1 || true
+  for pod in $(kubectl get pods -n "$NAMESPACE" -l tier=api --no-headers -o custom-columns=':metadata.name' 2>/dev/null); do
+    debug_pod_failure "$pod"
+  done
   stage_fail "service_deploy"
   PIPELINE_EXIT_CODE=2
   exit 2
@@ -398,6 +438,7 @@ else
   if kubectl wait --for=condition=failed job/inttest-runner -n "$NAMESPACE" --timeout=5s 2>/dev/null; then
     log "Test runner job reported failure"
   fi
+  debug_pod_failure "inttest-runner" "app=inttest-runner"
   stage_fail "integration_tests"
   PIPELINE_EXIT_CODE=1
 fi