2026-03-07 14:30:36 +00:00
|
|
|
variable "tls_secret_name" {
|
2026-03-14 08:51:45 +00:00
|
|
|
type = string
|
2026-03-07 14:30:36 +00:00
|
|
|
sensitive = true
|
|
|
|
|
}
|
|
|
|
|
variable "client_certificate_secret_name" {
|
|
|
|
|
type = string
|
|
|
|
|
}
|
2026-02-22 13:56:34 +00:00
|
|
|
|
|
|
|
|
|
2026-02-22 15:13:55 +00:00
|
|
|
resource "random_password" "csrf_token" {
|
|
|
|
|
length = 16
|
|
|
|
|
special = true
|
|
|
|
|
override_special = "_%@"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# instructions on deploying:
|
|
|
|
|
# https://kubernetes.io/docs/tasks/access-application-cluster/web-ui-dashboard/#accessing-the-dashboard-ui
|
|
|
|
|
|
|
|
|
|
# module "dashboard" {
|
|
|
|
|
# # source = "cookielab/dashboard/kubernetes"
|
|
|
|
|
# source = "ViktorBarzin/dashboard/kubernetes"
|
|
|
|
|
# version = "0.13.2"
|
|
|
|
|
# kubernetes_dashboard_csrf = random_password.csrf_token.result
|
|
|
|
|
# kubernetes_dashboard_deployment_args = tolist([
|
|
|
|
|
# "--auto-generate-certificates",
|
|
|
|
|
# "--token-ttl=0"
|
|
|
|
|
# ])
|
|
|
|
|
# }
|
|
|
|
|
resource "kubernetes_namespace" "k8s-dashboard" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard"
|
|
|
|
|
labels = {
|
|
|
|
|
"istio-injection" : "disabled"
|
|
|
|
|
tier = local.tiers.cluster
|
2026-05-16 12:41:05 +00:00
|
|
|
"keel.sh/enrolled" = "true"
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
[infra] Suppress Goldilocks vpa-update-mode label drift on all namespaces [ci skip]
## Context
Wave 3B-continued: the Goldilocks VPA dashboard (stacks/vpa) runs a Kyverno
ClusterPolicy `goldilocks-vpa-auto-mode` that mutates every namespace with
`metadata.labels["goldilocks.fairwinds.com/vpa-update-mode"] = "off"`. This
is intentional — Terraform owns container resource limits, and Goldilocks
should only provide recommendations, never auto-update. The label is how
Goldilocks decides per-namespace whether to run its VPA in `off` mode.
Effect on Terraform: every `kubernetes_namespace` resource shows the label
as pending-removal (`-> null`) on every `scripts/tg plan`. Dawarich survey
2026-04-18 confirmed the drift. Cluster-side count: 88 namespaces carry the
label (`kubectl get ns -o json | jq ... | wc -l`). Every TF-managed namespace
is affected.
This commit brings the intentional admission drift under the same
`# KYVERNO_LIFECYCLE_V1` discoverability marker introduced in c9d221d5 for
the ndots dns_config pattern. The marker now stands generically for any
Kyverno admission-webhook drift suppression; the inline comment records
which specific policy stamps which specific field so future grep audits
show why each suppression exists.
## This change
107 `.tf` files touched — every stack's `resource "kubernetes_namespace"`
resource gets:
```hcl
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"]]
}
```
Injection was done with a brace-depth-tracking Python pass (`/tmp/add_goldilocks_ignore.py`):
match `^resource "kubernetes_namespace" ` → track `{` / `}` until the
outermost closing brace → insert the lifecycle block before the closing
brace. The script is idempotent (skips any file that already mentions
`goldilocks.fairwinds.com/vpa-update-mode`) so re-running is safe.
Vault stack picked up 2 namespaces in the same file (k8s-users produces
one, plus a second explicit ns) — confirmed via file diff (+8 lines).
## What is NOT in this change
- `stacks/trading-bot/main.tf` — entire file is `/* … */` commented out
(paused 2026-04-06 per user decision). Reverted after the script ran.
- `stacks/_template/main.tf.example` — per-stack skeleton, intentionally
minimal. User keeps it that way. Not touched by the script (file
has no real `resource "kubernetes_namespace"` — only a placeholder
comment).
- `.terraform/` copies (e.g. `stacks/metallb/.terraform/modules/...`) —
gitignored, won't commit; the live path was edited.
- `terraform fmt` cleanup of adjacent pre-existing alignment issues in
authentik, freedify, hermes-agent, nvidia, vault, meshcentral. Reverted
to keep the commit scoped to the Goldilocks sweep. Those files will
need a separate fmt-only commit or will be cleaned up on next real
apply to that stack.
## Verification
Dawarich (one of the hundred-plus touched stacks) showed the pattern
before and after:
```
$ cd stacks/dawarich && ../../scripts/tg plan
Before:
Plan: 0 to add, 2 to change, 0 to destroy.
# kubernetes_namespace.dawarich will be updated in-place
(goldilocks.fairwinds.com/vpa-update-mode -> null)
# module.tls_secret.kubernetes_secret.tls_secret will be updated in-place
(Kyverno generate.* labels — fixed in 8d94688d)
After:
No changes. Your infrastructure matches the configuration.
```
Injection count check:
```
$ rg -c 'KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode' stacks/ | awk -F: '{s+=$2} END {print s}'
108
```
## Reproduce locally
1. `git pull`
2. Pick any stack: `cd stacks/<name> && ../../scripts/tg plan`
3. Expect: no drift on the namespace's goldilocks.fairwinds.com/vpa-update-mode label.
Closes: code-dwx
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 21:15:27 +00:00
|
|
|
lifecycle {
|
|
|
|
|
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
|
|
|
|
|
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
|
|
|
|
|
}
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
# }
|
|
|
|
|
|
|
|
|
|
module "tls_secret" {
|
|
|
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "helm_release" "kubernetes-dashboard" {
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
name = "kubernetes-dashboard"
|
|
|
|
|
|
2026-03-22 02:50:32 +02:00
|
|
|
repository = "https://kubernetes-retired.github.io/dashboard/"
|
2026-02-22 15:13:55 +00:00
|
|
|
chart = "kubernetes-dashboard"
|
|
|
|
|
atomic = true
|
|
|
|
|
version = "7.12.0"
|
|
|
|
|
|
|
|
|
|
# values = [templatefile("${path.module}/chart_values.tpl", { postgresql_password = var.postgresql_password })]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# # locals {
|
|
|
|
|
# # resources = split("---\n", file("${path.module}/recommended.yaml"))
|
|
|
|
|
# # }
|
|
|
|
|
# # resource "k8s_manifest" "kubernetes-dashboard-manifests" {
|
|
|
|
|
# # count = length(local.resources) - 1
|
|
|
|
|
# # # count = 2
|
|
|
|
|
# # # content = local.resources[1 + count.index]
|
|
|
|
|
# # # content = file("${path.module}/recommended.yaml")
|
|
|
|
|
# # content = local.resources[1]
|
|
|
|
|
# # depends_on = [kubernetes_namespace.kubernetes-dashboard]
|
|
|
|
|
# # }
|
|
|
|
|
# resource "kubectl_manifest" "kubernetes-dashboard-manifests" {
|
|
|
|
|
# yaml_body = file("${path.module}/recommended.yaml")
|
|
|
|
|
# force_new = true
|
|
|
|
|
# depends_on = [kubernetes_namespace.kubernetes-dashboard]
|
|
|
|
|
# }
|
|
|
|
|
|
|
|
|
|
# resource "kubernetes_secret" "dashboard-token" {
|
|
|
|
|
# metadata {
|
|
|
|
|
# name = "dashboard-secret"
|
|
|
|
|
# namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
# annotations = {
|
|
|
|
|
# "kubernetes.io/service-account.name" : "kubernetes-dashboard"
|
|
|
|
|
# }
|
|
|
|
|
# }
|
|
|
|
|
# type = "kubernetes.io/service-account-token"
|
|
|
|
|
# }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
module "ingress" {
|
|
|
|
|
source = "../../modules/kubernetes/ingress_factory"
|
2026-06-04 08:04:23 +00:00
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
name = "kubernetes-dashboard"
|
|
|
|
|
# Route through the token-injector: Authentik forward-auth (auth=required) gates
|
|
|
|
|
# access AND injects X-authentik-username; the injector maps that to the user's
|
|
|
|
|
# ServiceAccount token and sets Authorization: Bearer so the dashboard skips its
|
|
|
|
|
# token-paste login. See dashboard_injector.tf.
|
|
|
|
|
service_name = "dashboard-token-injector"
|
2026-06-04 03:59:43 +00:00
|
|
|
host = "k8s"
|
|
|
|
|
dns_type = "proxied"
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
auth = "required"
|
2026-06-04 08:04:23 +00:00
|
|
|
backend_protocol = "HTTP"
|
|
|
|
|
port = 80
|
2026-03-07 16:41:36 +00:00
|
|
|
extra_annotations = {
|
|
|
|
|
"gethomepage.dev/enabled" = "true"
|
|
|
|
|
"gethomepage.dev/name" = "Kubernetes Dashboard"
|
|
|
|
|
"gethomepage.dev/description" = "Cluster dashboard"
|
|
|
|
|
"gethomepage.dev/icon" = "kubernetes-dashboard.png"
|
|
|
|
|
"gethomepage.dev/group" = "Core Platform"
|
|
|
|
|
"gethomepage.dev/pod-selector" = ""
|
|
|
|
|
}
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# create token with
|
|
|
|
|
# kb create token --duration=0s kubernetes-dashboard
|
|
|
|
|
resource "kubernetes_service_account" "kubernetes-dashboard" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Give cluster-admin permissions to dashboard
|
|
|
|
|
resource "kubernetes_cluster_role_binding" "kubernetes-dashboard" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "admin-user"
|
|
|
|
|
}
|
|
|
|
|
role_ref {
|
|
|
|
|
api_group = "rbac.authorization.k8s.io"
|
|
|
|
|
kind = "ClusterRole"
|
|
|
|
|
name = "cluster-admin"
|
|
|
|
|
}
|
|
|
|
|
subject {
|
|
|
|
|
kind = "ServiceAccount"
|
|
|
|
|
name = "kubernetes-dashboard"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
# depends_on = [module.dashboard]
|
|
|
|
|
}
|
|
|
|
|
|
migrate consuming stacks to ESO + remove k8s-dashboard static token
Phase 9: ExternalSecret migration across 26 stacks:
Fully migrated (vault data source removed, ESO delivers secrets):
- speedtest, shadowsocks, wealthfolio, plotting-book, f1-stream, tandoor
- n8n, dawarich, diun, netbox, onlyoffice, tuya-bridge
- hackmd (ESO template for DB URL), health (ESO template for DB URL)
- trading-bot (ESO template for DATABASE_URL + 7 secret env vars)
- forgejo (removed unused vault data source)
Partially migrated (vault kept for plan-time, ESO added for runtime):
- immich, linkwarden, nextcloud, paperless-ngx (jsondecode for homepage)
- claude-memory, rybbit, url, webhook_handler (plan-time in locals/jobs)
- woodpecker, openclaw, resume (plan-time in helm values/jobs/modules)
17 stacks unchanged (all plan-time: homepage annotations, configmaps,
module inputs) — vault data source works with OIDC auth.
Phase 17a: Remove k8s-dashboard static admin token secret.
Users now get tokens via: vault write kubernetes/creds/dashboard-admin
2026-03-15 19:05:04 +00:00
|
|
|
# Admin token: use `vault write kubernetes/creds/dashboard-admin kubernetes_namespace=kubernetes-dashboard`
|
|
|
|
|
# instead of a static never-expiring token.
|
2026-02-22 15:13:55 +00:00
|
|
|
|
|
|
|
|
## Readonly RBAC
|
|
|
|
|
resource "kubernetes_cluster_role" "kubernetes-dashboard-viewonly" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = [""]
|
|
|
|
|
resources = ["configmaps", "endpoints", "persistentvolumeclaims", "pods", "replicationcontrollers", "replicationcontrollers/scale", "serviceaccounts", "services", "nodes", "persistentvolumeclaims", "persistentvolumes"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = [""]
|
|
|
|
|
resources = ["bindings", "events", "limitranges", "namespaces/status", "pods/log", "pods/status", "replicationcontrollers/status", "resourcequotas", "resourcequotas/status"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = [""]
|
|
|
|
|
resources = ["namespaces"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["apps"]
|
|
|
|
|
resources = ["daemonsets", "deployments", "deployments/scale", "replicasets", "replicasets/scale", "statefulsets"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["autoscaling"]
|
|
|
|
|
resources = ["horizontalpodautoscalers"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["batch"]
|
|
|
|
|
resources = ["cronjobs", "jobs"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["extensions"]
|
|
|
|
|
resources = ["daemonsets", "deployments", "deployments/scale", "ingresses", "networkpolicies", "replicasets", "replicasets/scale", "replicationcontrollers/scale"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["policy"]
|
|
|
|
|
resources = ["poddisruptionbudgets"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["networking.k8s.io"]
|
|
|
|
|
resources = ["networkpolicies"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["storage.k8s.io"]
|
|
|
|
|
resources = ["storageclasses", "volumeattachments"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
rule {
|
|
|
|
|
api_groups = ["rbac.authorization.k8s.io"]
|
|
|
|
|
resources = ["clusterrolebindings", "clusterroles", "roles", "rolebindings"]
|
|
|
|
|
verbs = ["get", "list", "watch"]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_cluster_role_binding" "kubernetes-dashboard-viewonly" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
role_ref {
|
|
|
|
|
api_group = "rbac.authorization.k8s.io"
|
|
|
|
|
kind = "ClusterRole"
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
}
|
|
|
|
|
subject {
|
|
|
|
|
kind = "ServiceAccount"
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service_account" "kubernetes-dashboard-viewonly" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_secret" "kubernetes-dashboard-viewonly-token" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "kubernetes-dashboard-viewonly"
|
|
|
|
|
namespace = kubernetes_namespace.k8s-dashboard.metadata[0].name
|
|
|
|
|
annotations = {
|
|
|
|
|
"kubernetes.io/service-account.name" : "kubernetes-dashboard-viewonly"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
type = "kubernetes.io/service-account-token"
|
2026-02-22 13:56:34 +00:00
|
|
|
}
|
2026-05-16 13:42:57 +00:00
|
|
|
|
|
|
|
|
# CI retrigger 2026-05-16T13:42:57+00:00 — bulk enrollment apply (pipeline #689 killed)
|
2026-05-16 13:46:35 +00:00
|
|
|
# CI retrigger v2 2026-05-16T13:46:35+00:00
|
2026-05-16 14:06:39 +00:00
|
|
|
|
|
|
|
|
# CI retrigger v3 2026-05-16T14:06:39Z
|
2026-05-16 14:13:59 +00:00
|
|
|
|
|
|
|
|
# CI retrigger v4 2026-05-16T14:13:59Z
|
2026-05-16 23:10:38 +00:00
|
|
|
|
|
|
|
|
# CI retrigger v5 2026-05-16T23:10:38Z
|
2026-05-16 23:18:59 +00:00
|
|
|
|
|
|
|
|
# CI retrigger v6 2026-05-16T23:18:58Z
|