stem95su: scheduled Drive->site sync CronJob (every 10m)
CronJob stem95su-gdrive-sync (*/10) mounts the content PVC RW and rclone-syncs the read-only Drive folder "claude" (stem claude/files) onto it (rclone/rclone:1.74.3, scope=drive.readonly, empty-source guard + --max-delete 25). ESO ExternalSecret stem95su-rclone <- Vault secret/stem95su. Requires the GCP OAuth app published to Production or the refresh token expires ~weekly. Lands the gdrive-sync stack on master (it had landed on a feature branch by accident on the shared devvm checkout). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Viktor Barzin
parent
05b50d2b96
commit
6d224861c4
1168 changed files with 120 additions and 358547 deletions
|
|
@ -1,302 +0,0 @@
|
|||
variable "tls_secret_name" {
|
||||
type = string
|
||||
sensitive = true
|
||||
}
|
||||
variable "nfs_server" { type = string }
|
||||
|
||||
|
||||
resource "kubernetes_namespace" "whisper" {
|
||||
metadata {
|
||||
name = "whisper"
|
||||
labels = {
|
||||
tier = local.tiers.gpu
|
||||
"keel.sh/enrolled" = "true"
|
||||
}
|
||||
}
|
||||
lifecycle {
|
||||
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
|
||||
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
|
||||
}
|
||||
}
|
||||
|
||||
module "tls_secret" {
|
||||
source = "../../modules/kubernetes/setup_tls_secret"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
tls_secret_name = var.tls_secret_name
|
||||
}
|
||||
|
||||
module "nfs_data_host" {
|
||||
source = "../../modules/kubernetes/nfs_volume"
|
||||
name = "whisper-data-host"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
nfs_server = var.nfs_server
|
||||
nfs_path = "/srv/nfs/whisper"
|
||||
storage = "1Gi"
|
||||
access_modes = ["ReadWriteMany"]
|
||||
}
|
||||
|
||||
resource "kubernetes_deployment" "whisper" {
|
||||
metadata {
|
||||
name = "whisper"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
labels = {
|
||||
app = "whisper"
|
||||
tier = local.tiers.gpu
|
||||
}
|
||||
}
|
||||
spec {
|
||||
replicas = 0 # Scaled down - GPU node memory pressure
|
||||
strategy {
|
||||
type = "Recreate"
|
||||
}
|
||||
selector {
|
||||
match_labels = {
|
||||
app = "whisper"
|
||||
}
|
||||
}
|
||||
template {
|
||||
metadata {
|
||||
labels = {
|
||||
app = "whisper"
|
||||
}
|
||||
}
|
||||
spec {
|
||||
node_selector = {
|
||||
"nvidia.com/gpu.present" : "true"
|
||||
}
|
||||
toleration {
|
||||
key = "nvidia.com/gpu"
|
||||
operator = "Equal"
|
||||
value = "true"
|
||||
effect = "NoSchedule"
|
||||
}
|
||||
|
||||
container {
|
||||
name = "whisper"
|
||||
image = "rhasspy/wyoming-whisper:latest"
|
||||
args = ["--model", "small-int8", "--language", "en", "--beam-size", "1"]
|
||||
|
||||
port {
|
||||
container_port = 10300
|
||||
protocol = "TCP"
|
||||
}
|
||||
|
||||
volume_mount {
|
||||
name = "data"
|
||||
mount_path = "/data"
|
||||
}
|
||||
resources {
|
||||
requests = {
|
||||
cpu = "25m"
|
||||
memory = "1Gi"
|
||||
}
|
||||
limits = {
|
||||
memory = "1Gi"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
volume {
|
||||
name = "data"
|
||||
persistent_volume_claim {
|
||||
claim_name = module.nfs_data_host.claim_name
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
lifecycle {
|
||||
ignore_changes = [
|
||||
spec[0].template[0].spec[0].dns_config, # KYVERNO_LIFECYCLE_V1
|
||||
metadata[0].annotations["keel.sh/policy"],
|
||||
metadata[0].annotations["keel.sh/trigger"],
|
||||
metadata[0].annotations["keel.sh/pollSchedule"], # KYVERNO_LIFECYCLE_V2
|
||||
metadata[0].annotations["keel.sh/match-tag"],
|
||||
spec[0].template[0].spec[0].container[0].image, # KEEL_IGNORE_IMAGE — Keel manages tag updates
|
||||
metadata[0].annotations["kubernetes.io/change-cause"],
|
||||
metadata[0].annotations["deployment.kubernetes.io/revision"],
|
||||
spec[0].template[0].metadata[0].annotations["keel.sh/update-time"], # KEEL_LIFECYCLE_V1
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
resource "kubernetes_service" "whisper" {
|
||||
metadata {
|
||||
name = "whisper"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
labels = {
|
||||
app = "whisper"
|
||||
}
|
||||
}
|
||||
|
||||
spec {
|
||||
selector = {
|
||||
app = "whisper"
|
||||
}
|
||||
port {
|
||||
name = "wyoming"
|
||||
port = 10300
|
||||
target_port = 10300
|
||||
protocol = "TCP"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# TCP passthrough from Traefik to whisper service
|
||||
resource "kubernetes_manifest" "whisper_tcp_ingressroute" {
|
||||
manifest = {
|
||||
apiVersion = "traefik.io/v1alpha1"
|
||||
kind = "IngressRouteTCP"
|
||||
metadata = {
|
||||
name = "whisper-tcp"
|
||||
namespace = "traefik"
|
||||
}
|
||||
spec = {
|
||||
entryPoints = ["whisper-tcp"]
|
||||
routes = [{
|
||||
match = "HostSNI(`*`)"
|
||||
services = [{
|
||||
name = "whisper"
|
||||
namespace = "whisper"
|
||||
port = 10300
|
||||
}]
|
||||
}]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Piper TTS
|
||||
resource "kubernetes_deployment" "piper" {
|
||||
metadata {
|
||||
name = "piper"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
labels = {
|
||||
app = "piper"
|
||||
tier = local.tiers.gpu
|
||||
}
|
||||
}
|
||||
spec {
|
||||
replicas = 0 # Scaled down - GPU node memory pressure
|
||||
strategy {
|
||||
type = "Recreate"
|
||||
}
|
||||
selector {
|
||||
match_labels = {
|
||||
app = "piper"
|
||||
}
|
||||
}
|
||||
template {
|
||||
metadata {
|
||||
labels = {
|
||||
app = "piper"
|
||||
}
|
||||
}
|
||||
spec {
|
||||
node_selector = {
|
||||
"nvidia.com/gpu.present" : "true"
|
||||
}
|
||||
toleration {
|
||||
key = "nvidia.com/gpu"
|
||||
operator = "Equal"
|
||||
value = "true"
|
||||
effect = "NoSchedule"
|
||||
}
|
||||
|
||||
container {
|
||||
name = "piper"
|
||||
image = "rhasspy/wyoming-piper:latest"
|
||||
args = ["--voice", "en_US-lessac-medium"]
|
||||
|
||||
port {
|
||||
container_port = 10200
|
||||
protocol = "TCP"
|
||||
}
|
||||
|
||||
volume_mount {
|
||||
name = "data"
|
||||
mount_path = "/data"
|
||||
}
|
||||
resources {
|
||||
requests = {
|
||||
cpu = "25m"
|
||||
memory = "64Mi"
|
||||
}
|
||||
limits = {
|
||||
memory = "64Mi"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
volume {
|
||||
name = "data"
|
||||
persistent_volume_claim {
|
||||
claim_name = module.nfs_data_host.claim_name
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
lifecycle {
|
||||
ignore_changes = [
|
||||
spec[0].template[0].spec[0].dns_config, # KYVERNO_LIFECYCLE_V1
|
||||
metadata[0].annotations["keel.sh/policy"],
|
||||
metadata[0].annotations["keel.sh/trigger"],
|
||||
metadata[0].annotations["keel.sh/pollSchedule"], # KYVERNO_LIFECYCLE_V2
|
||||
metadata[0].annotations["keel.sh/match-tag"],
|
||||
spec[0].template[0].spec[0].container[0].image, # KEEL_IGNORE_IMAGE — Keel manages tag updates
|
||||
metadata[0].annotations["kubernetes.io/change-cause"],
|
||||
metadata[0].annotations["deployment.kubernetes.io/revision"],
|
||||
spec[0].template[0].metadata[0].annotations["keel.sh/update-time"], # KEEL_LIFECYCLE_V1
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
resource "kubernetes_service" "piper" {
|
||||
metadata {
|
||||
name = "piper"
|
||||
namespace = kubernetes_namespace.whisper.metadata[0].name
|
||||
labels = {
|
||||
app = "piper"
|
||||
}
|
||||
}
|
||||
|
||||
spec {
|
||||
selector = {
|
||||
app = "piper"
|
||||
}
|
||||
port {
|
||||
name = "wyoming"
|
||||
port = 10200
|
||||
target_port = 10200
|
||||
protocol = "TCP"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# TCP passthrough from Traefik to piper service
|
||||
resource "kubernetes_manifest" "piper_tcp_ingressroute" {
|
||||
manifest = {
|
||||
apiVersion = "traefik.io/v1alpha1"
|
||||
kind = "IngressRouteTCP"
|
||||
metadata = {
|
||||
name = "piper-tcp"
|
||||
namespace = "traefik"
|
||||
}
|
||||
spec = {
|
||||
entryPoints = ["piper-tcp"]
|
||||
routes = [{
|
||||
match = "HostSNI(`*`)"
|
||||
services = [{
|
||||
name = "piper"
|
||||
namespace = "whisper"
|
||||
port = 10200
|
||||
}]
|
||||
}]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# CI retrigger 2026-05-16T13:42:57+00:00 — bulk enrollment apply (pipeline #689 killed)
|
||||
# CI retrigger v2 2026-05-16T13:46:35+00:00
|
||||
|
||||
# CI retrigger v3 2026-05-16T14:06:39Z
|
||||
Loading…
Add table
Add a link
Reference in a new issue