9ad52dfd61
Give the OpenClaw pod two new capabilities:
1. Host-tools bundle. New init container `install-host-tools` extracts
openssh-client + dnsutils + tmux + jq + ripgrep + fd + vault + yq +
friends into /tools/host-tools/, with the bookworm-slim libs the
binaries need. PATH + LD_LIBRARY_PATH on the main container point
ld.so at the bundle. Idempotent via /tools/host-tools/.installed-v1
marker; smoke test (ldd-based) fails the init at deploy time if any
binary has unresolved deps. Bundle is ~558 MB on the existing
/srv/nfs/openclaw/tools NFS.
2. devvm SSH + async task pattern. New init `setup-ssh-config` writes
id_rsa/config/known_hosts under /home/node/.openclaw/.ssh; main
container startup symlinks /home/node/.ssh → there. New
/usr/local/bin/openclaw-task wrapper on devvm manages long-running
work as tmux sessions on devvm (sessions and logs survive pod
restarts — they live on devvm, not in the pod). New init container
`seed-devvm-memory-note` drops a markdown note teaching the pattern;
main container startup now runs `openclaw memory index --force` so
the note is searchable on first boot.
Design + verified E2E flow in
docs/plans/2026-05-22-openclaw-devvm-access-design.md. Persistence test
green: spawned a 50s task from pod A, deleted pod A, new pod B saw the
task finish and read its full log.
Pre-existing keel.sh annotation drift on openclaw/{openlobster,
task_webhook} cleaned up in the same apply.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
1752 lines
59 KiB
HCL
1752 lines
59 KiB
HCL
variable "tls_secret_name" {
|
||
type = string
|
||
sensitive = true
|
||
}
|
||
variable "nfs_server" { type = string }
|
||
|
||
data "vault_kv_secret_v2" "secrets" {
|
||
mount = "secret"
|
||
name = "openclaw"
|
||
}
|
||
|
||
locals {
|
||
skill_secrets = jsondecode(data.vault_kv_secret_v2.secrets.data["skill_secrets"])
|
||
}
|
||
|
||
|
||
resource "kubernetes_namespace" "openclaw" {
|
||
metadata {
|
||
name = "openclaw"
|
||
labels = {
|
||
tier = local.tiers.aux
|
||
"resource-governance/custom-limitrange" = "true"
|
||
"resource-governance/custom-quota" = "true"
|
||
"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.openclaw.metadata[0].name
|
||
tls_secret_name = var.tls_secret_name
|
||
}
|
||
|
||
resource "kubernetes_manifest" "external_secret" {
|
||
manifest = {
|
||
apiVersion = "external-secrets.io/v1beta1"
|
||
kind = "ExternalSecret"
|
||
metadata = {
|
||
name = "openclaw-secrets"
|
||
namespace = "openclaw"
|
||
}
|
||
spec = {
|
||
refreshInterval = "15m"
|
||
secretStoreRef = {
|
||
name = "vault-kv"
|
||
kind = "ClusterSecretStore"
|
||
}
|
||
target = {
|
||
name = "openclaw-secrets"
|
||
}
|
||
dataFrom = [{
|
||
extract = {
|
||
key = "openclaw"
|
||
}
|
||
}]
|
||
}
|
||
}
|
||
depends_on = [kubernetes_namespace.openclaw]
|
||
}
|
||
|
||
resource "kubernetes_service_account" "openclaw" {
|
||
metadata {
|
||
name = "openclaw"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_cluster_role_binding" "openclaw" {
|
||
metadata {
|
||
name = "openclaw-cluster-admin"
|
||
}
|
||
subject {
|
||
kind = "ServiceAccount"
|
||
name = kubernetes_service_account.openclaw.metadata[0].name
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
role_ref {
|
||
api_group = "rbac.authorization.k8s.io"
|
||
kind = "ClusterRole"
|
||
name = "cluster-admin"
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_secret" "ssh_key" {
|
||
metadata {
|
||
name = "ssh-key"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"id_rsa" = data.vault_kv_secret_v2.secrets.data["ssh_key"]
|
||
}
|
||
type = "generic"
|
||
}
|
||
|
||
resource "kubernetes_config_map" "git_crypt_key" {
|
||
metadata {
|
||
name = "git-crypt-key"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"key" = filebase64("${path.root}/../../.git/git-crypt/keys/default")
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_config_map" "openclaw_config" {
|
||
metadata {
|
||
name = "openclaw-config"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"openclaw.json" = jsonencode({
|
||
gateway = {
|
||
mode = "local"
|
||
bind = "lan"
|
||
trustedProxies = ["10.0.0.0/8"]
|
||
controlUi = {
|
||
dangerouslyDisableDeviceAuth = true
|
||
dangerouslyAllowHostHeaderOriginFallback = true
|
||
}
|
||
}
|
||
agents = {
|
||
defaults = {
|
||
contextTokens = 1000000
|
||
bootstrapMaxChars = 30000
|
||
workspace = "/workspace"
|
||
sandbox = {
|
||
mode = "off"
|
||
}
|
||
model = {
|
||
# ChatGPT Plus OAuth via openai-codex plugin (account: ancaelena98@gmail.com).
|
||
# gpt-5.4-mini is the only mini variant the Codex backend accepts for Plus tier;
|
||
# gpt-5-mini / gpt-5.1-codex-mini return model_not_found / "not supported with
|
||
# ChatGPT account". Plus rate-card: 1,200–7,000 local msgs / 5h on gpt-5.4-mini.
|
||
primary = "openai-codex/gpt-5.4-mini"
|
||
fallbacks = ["openai-codex/gpt-5.5", "nim/qwen/qwen3-coder-480b-a35b-instruct", "modelrelay/auto-fastest"]
|
||
}
|
||
models = {
|
||
"modelrelay/auto-fastest" = {}
|
||
"nim/deepseek-ai/deepseek-v3.2" = {}
|
||
"nim/qwen/qwen3.5-397b-a17b" = {}
|
||
"nim/mistralai/mistral-large-3-675b-instruct-2512" = {}
|
||
"nim/qwen/qwen3-coder-480b-a35b-instruct" = {}
|
||
"nim/nvidia/llama-3.1-nemotron-ultra-253b-v1" = {}
|
||
"nim/z-ai/glm5" = {}
|
||
"llama-as-openai/Llama-4-Maverick-17B-128E-Instruct-FP8" = {}
|
||
"llama-as-openai/Llama-4-Scout-17B-16E-Instruct-FP8" = {}
|
||
"openrouter/stepfun/step-3.5-flash:free" = {}
|
||
"openrouter/arcee-ai/trinity-large-preview:free" = {}
|
||
"openai-codex/gpt-5.4-mini" = {}
|
||
"openai-codex/gpt-5.5" = {}
|
||
}
|
||
}
|
||
}
|
||
tools = {
|
||
profile = "full"
|
||
deny = []
|
||
elevated = {
|
||
enabled = true
|
||
}
|
||
exec = {
|
||
host = "gateway"
|
||
security = "full"
|
||
ask = "off"
|
||
pathPrepend = ["/tools", "/workspace"]
|
||
}
|
||
web = {
|
||
search = {
|
||
enabled = true
|
||
provider = "brave"
|
||
apiKey = data.vault_kv_secret_v2.secrets.data["brave_api_key"]
|
||
maxResults = 5
|
||
}
|
||
fetch = {
|
||
enabled = true
|
||
maxChars = 50000
|
||
timeoutSeconds = 30
|
||
}
|
||
}
|
||
}
|
||
plugins = {
|
||
allow = ["memory-core", "recruiter-api"]
|
||
slots = { memory = "memory-core" }
|
||
load = {
|
||
# /app/extensions is the legacy bundled-plugins path; OpenClaw
|
||
# already loads bundled plugins natively (doctor warning).
|
||
paths = ["/home/node/.openclaw/extensions"]
|
||
}
|
||
}
|
||
# Note: mcp.servers is configured via `openclaw mcp set` in the main
|
||
# container startup command (see below) rather than in this ConfigMap.
|
||
# OpenClaw's `doctor --fix` (which runs on every pod start) strips
|
||
# bulk-loaded mcp blocks from openclaw.json, but preserves CLI-set
|
||
# entries. The CLI is the canonical writer.
|
||
commands = {
|
||
native = true
|
||
nativeSkills = true
|
||
}
|
||
channels = {
|
||
telegram = {
|
||
enabled = true
|
||
botToken = data.vault_kv_secret_v2.secrets.data["telegram_bot_token"]
|
||
dmPolicy = "allowlist"
|
||
allowFrom = ["tg:8281953845"]
|
||
groupPolicy = "allowlist"
|
||
streamMode = "partial"
|
||
}
|
||
}
|
||
models = {
|
||
mode = "merge"
|
||
providers = {
|
||
modelrelay = {
|
||
baseUrl = "http://127.0.0.1:7352/v1"
|
||
api = "openai-completions"
|
||
apiKey = "modelrelay"
|
||
models = [
|
||
{ id = "auto-fastest", name = "Auto (Fastest)", reasoning = false, input = ["text"], contextWindow = 200000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
]
|
||
}
|
||
nim = {
|
||
baseUrl = "https://integrate.api.nvidia.com/v1"
|
||
api = "openai-completions"
|
||
apiKey = data.vault_kv_secret_v2.secrets.data["nvidia_api_key"]
|
||
models = [
|
||
{ id = "deepseek-ai/deepseek-v3.2", name = "DeepSeek V3.2", reasoning = false, input = ["text"], contextWindow = 164000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "qwen/qwen3.5-397b-a17b", name = "Qwen 3.5", reasoning = true, input = ["text"], contextWindow = 262000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "mistralai/mistral-large-3-675b-instruct-2512", name = "Mistral Large 3", reasoning = false, input = ["text"], contextWindow = 262000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "qwen/qwen3-coder-480b-a35b-instruct", name = "Qwen 3 Coder", reasoning = false, input = ["text"], contextWindow = 262000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "nvidia/llama-3.1-nemotron-ultra-253b-v1", name = "Nemotron Ultra 253B", reasoning = true, input = ["text"], contextWindow = 128000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "z-ai/glm5", name = "GLM-5", reasoning = false, input = ["text"], contextWindow = 128000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
]
|
||
}
|
||
openrouter = {
|
||
baseUrl = "https://openrouter.ai/api/v1"
|
||
api = "openai-completions"
|
||
apiKey = data.vault_kv_secret_v2.secrets.data["openrouter_api_key"]
|
||
models = [
|
||
{ id = "stepfun/step-3.5-flash:free", name = "Step 3.5 Flash", reasoning = true, input = ["text"], contextWindow = 256000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "arcee-ai/trinity-large-preview:free", name = "Trinity Large", reasoning = false, input = ["text"], contextWindow = 131000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
]
|
||
}
|
||
llama-as-openai = {
|
||
baseUrl = "https://api.llama.com/compat/v1"
|
||
apiKey = data.vault_kv_secret_v2.secrets.data["llama_api_key"]
|
||
api = "openai-completions"
|
||
models = [
|
||
{ id = "Llama-4-Maverick-17B-128E-Instruct-FP8", name = "Llama 4 Maverick", reasoning = false, input = ["text"], contextWindow = 200000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
{ id = "Llama-4-Scout-17B-16E-Instruct-FP8", name = "Llama 4 Scout", reasoning = false, input = ["text"], contextWindow = 200000, maxTokens = 16384, cost = { input = 0, output = 0, cacheRead = 0, cacheWrite = 0 } },
|
||
]
|
||
}
|
||
}
|
||
}
|
||
wizard = {
|
||
lastRunAt = "2026-03-01T15:11:54.176Z"
|
||
lastRunVersion = "2026.2.9"
|
||
lastRunCommand = "configure"
|
||
lastRunMode = "local"
|
||
}
|
||
})
|
||
}
|
||
}
|
||
|
||
resource "random_password" "gateway_token" {
|
||
length = 32
|
||
special = false
|
||
}
|
||
|
||
# Prometheus exporter script — read by the openclaw-exporter sidecar.
|
||
# Stdlib-only Python so no pip install at startup. Reads sessions JSONL +
|
||
# auth-profiles.json from the NFS-backed openclaw home volume (mounted ro).
|
||
resource "kubernetes_config_map" "openclaw_exporter" {
|
||
metadata {
|
||
name = "openclaw-exporter"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"exporter.py" = file("${path.module}/files/exporter.py")
|
||
}
|
||
}
|
||
|
||
module "nfs_tools_host" {
|
||
source = "../../modules/kubernetes/nfs_volume"
|
||
name = "openclaw-tools-host"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
nfs_server = "192.168.1.127"
|
||
nfs_path = "/srv/nfs/openclaw/tools"
|
||
}
|
||
|
||
resource "kubernetes_persistent_volume_claim" "home_proxmox" {
|
||
wait_until_bound = false
|
||
metadata {
|
||
name = "openclaw-home-proxmox"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
annotations = {
|
||
"resize.topolvm.io/threshold" = "10%"
|
||
"resize.topolvm.io/increase" = "100%"
|
||
"resize.topolvm.io/storage_limit" = "5Gi"
|
||
}
|
||
}
|
||
spec {
|
||
access_modes = ["ReadWriteOnce"]
|
||
storage_class_name = "proxmox-lvm"
|
||
resources {
|
||
requests = {
|
||
storage = "1Gi"
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# The autoresizer expands requests.storage up to storage_limit and
|
||
# PVCs can't shrink. Without this, every TF apply tries to revert
|
||
# to the spec value, K8s rejects the shrink, and the PVC ends up
|
||
# in Terminating-but-in-use limbo.
|
||
ignore_changes = [spec[0].resources[0].requests]
|
||
}
|
||
}
|
||
|
||
module "nfs_workspace_host" {
|
||
source = "../../modules/kubernetes/nfs_volume"
|
||
name = "openclaw-workspace-host"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
nfs_server = "192.168.1.127"
|
||
nfs_path = "/srv/nfs/openclaw/workspace"
|
||
}
|
||
|
||
resource "kubernetes_persistent_volume_claim" "data_proxmox" {
|
||
wait_until_bound = false
|
||
metadata {
|
||
name = "openclaw-data-proxmox"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
annotations = {
|
||
"resize.topolvm.io/threshold" = "10%"
|
||
"resize.topolvm.io/increase" = "100%"
|
||
"resize.topolvm.io/storage_limit" = "5Gi"
|
||
}
|
||
}
|
||
spec {
|
||
access_modes = ["ReadWriteOnce"]
|
||
storage_class_name = "proxmox-lvm"
|
||
resources {
|
||
requests = {
|
||
storage = "1Gi"
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# The autoresizer expands requests.storage up to storage_limit and
|
||
# PVCs can't shrink. Without this, every TF apply tries to revert
|
||
# to the spec value, K8s rejects the shrink, and the PVC ends up
|
||
# in Terminating-but-in-use limbo.
|
||
ignore_changes = [spec[0].resources[0].requests]
|
||
}
|
||
}
|
||
|
||
## cc-config NFS volume removed — replaced by dotfiles repo clone in init container
|
||
## See init_container "install-dotfiles" in the deployment
|
||
|
||
resource "kubernetes_deployment" "openclaw" {
|
||
metadata {
|
||
name = "openclaw"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "openclaw"
|
||
tier = local.tiers.aux
|
||
}
|
||
}
|
||
spec {
|
||
strategy {
|
||
type = "Recreate"
|
||
}
|
||
replicas = 1
|
||
selector {
|
||
match_labels = {
|
||
app = "openclaw"
|
||
}
|
||
}
|
||
template {
|
||
metadata {
|
||
labels = {
|
||
app = "openclaw"
|
||
}
|
||
annotations = {
|
||
"reloader.stakater.com/search" = "true"
|
||
# Prometheus auto-discovers pods with these annotations.
|
||
# Scraped by the openclaw-exporter sidecar — exposes /metrics on :9099.
|
||
"prometheus.io/scrape" = "true"
|
||
"prometheus.io/port" = "9099"
|
||
"prometheus.io/path" = "/metrics"
|
||
}
|
||
}
|
||
spec {
|
||
service_account_name = kubernetes_service_account.openclaw.metadata[0].name
|
||
|
||
# Init 0: fix /workspace ownership so node user can write
|
||
init_container {
|
||
name = "fix-workspace-perms"
|
||
image = "busybox:1.37"
|
||
command = ["sh", "-c", "chown 1000:1000 /workspace"]
|
||
volume_mount {
|
||
name = "workspace"
|
||
mount_path = "/workspace"
|
||
}
|
||
}
|
||
|
||
# Init 1: copy openclaw.json from ConfigMap into writable NFS home
|
||
init_container {
|
||
name = "copy-config"
|
||
image = "busybox:1.37"
|
||
command = ["sh", "-c", "cp /config/openclaw.json /home/node/.openclaw/openclaw.json && chown 1000:1000 /home/node/.openclaw/openclaw.json"]
|
||
volume_mount {
|
||
name = "openclaw-config"
|
||
mount_path = "/config"
|
||
}
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
}
|
||
}
|
||
|
||
# Init 1b: regenerate kubeconfig pointing at the projected SA tokenFile
|
||
# so kubectl always reads the fresh, kubelet-rotated token. Without
|
||
# this the previously-baked kubeconfig retains a SA token bound to a
|
||
# long-dead pod and kubectl returns "must be logged in to the server".
|
||
init_container {
|
||
name = "setup-kubeconfig"
|
||
image = "busybox:1.37"
|
||
command = ["sh", "-c", <<-EOT
|
||
cat > /home/node/.openclaw/kubeconfig <<'KUBECONFIG_EOF'
|
||
apiVersion: v1
|
||
kind: Config
|
||
clusters:
|
||
- cluster:
|
||
certificate-authority: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||
server: https://kubernetes.default.svc
|
||
name: in-cluster
|
||
contexts:
|
||
- context:
|
||
cluster: in-cluster
|
||
user: openclaw
|
||
namespace: openclaw
|
||
name: in-cluster
|
||
current-context: in-cluster
|
||
users:
|
||
- name: openclaw
|
||
user:
|
||
tokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||
KUBECONFIG_EOF
|
||
chown 1000:1000 /home/node/.openclaw/kubeconfig
|
||
chmod 0644 /home/node/.openclaw/kubeconfig
|
||
EOT
|
||
]
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
}
|
||
}
|
||
|
||
# Init 2 removed: install-dotfiles init container was cloning dotfiles
|
||
# repo via git on every pod start, causing 200+ small NFS writes.
|
||
# Dotfiles already exist on NFS at /home/node/.openclaw/dotfiles from
|
||
# a previous clone. To update, run git pull manually or via CronJob.
|
||
|
||
# Init 3: install the recruiter-api OpenClaw plugin from the
|
||
# recruiter-responder image into NFS extensions/. Plugin lifecycle
|
||
# is coupled to the recruiter-responder image tag — bumping that
|
||
# tag re-installs the plugin on next openclaw pod restart.
|
||
init_container {
|
||
name = "install-recruiter-plugin"
|
||
image = "forgejo.viktorbarzin.me/viktor/recruiter-responder:latest"
|
||
command = ["sh", "-c", <<-EOT
|
||
set -eu
|
||
mkdir -p /home/node/.openclaw/extensions/recruiter-api
|
||
cp -r /app/openclaw-plugin/. /home/node/.openclaw/extensions/recruiter-api/
|
||
chown -R 1000:1000 /home/node/.openclaw/extensions/recruiter-api
|
||
echo "recruiter-api plugin installed at /home/node/.openclaw/extensions/recruiter-api"
|
||
ls -la /home/node/.openclaw/extensions/recruiter-api
|
||
EOT
|
||
]
|
||
# /home/node/.openclaw is uid 1000 on NFS; recruiter-responder image
|
||
# otherwise drops to uid 10001 which can't write or chown. Run as
|
||
# root so mkdir + chown succeed.
|
||
security_context {
|
||
run_as_user = 0
|
||
}
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
}
|
||
resources {
|
||
requests = { cpu = "50m", memory = "64Mi" }
|
||
limits = { memory = "128Mi" }
|
||
}
|
||
}
|
||
|
||
# Init 4: install host-tools bundle (ssh, vault, jq, ripgrep, tmux, …)
|
||
# into /tools/host-tools/ so the in-pod agent reaches CLI parity
|
||
# with the dev VM. Upstream OpenClaw image is minimal Debian
|
||
# bookworm running as uid 1000 — can't apt-install at runtime.
|
||
# Idempotent via marker file; bump suffix to force reinstall.
|
||
# See docs/plans/2026-05-22-openclaw-devvm-access-design.md.
|
||
init_container {
|
||
name = "install-host-tools"
|
||
image = "debian:bookworm-slim"
|
||
command = ["bash", "-c", <<-EOT
|
||
set -euo pipefail
|
||
DEST=/tools/host-tools
|
||
MARKER="$DEST/.installed-v1"
|
||
if [ -f "$MARKER" ]; then
|
||
echo "host-tools v1 already installed (skipping)"
|
||
exit 0
|
||
fi
|
||
echo "installing host-tools v1 ..."
|
||
rm -rf "$DEST"
|
||
mkdir -p "$DEST/root" "$DEST/bin"
|
||
|
||
export DEBIAN_FRONTEND=noninteractive
|
||
apt-get update -qq
|
||
# debian:bookworm-slim doesn't ship wget/unzip; install
|
||
# transiently into this init container's filesystem so we
|
||
# can download the static binaries below.
|
||
apt-get install -y --no-install-recommends wget unzip ca-certificates
|
||
|
||
# NOTE: we deliberately do NOT pass --no-install-recommends to
|
||
# the download step. ssh links against libgssapi-krb5-2 which
|
||
# is a hard Depends but its transitive deps (libkrb5-3 etc.)
|
||
# need to come along too. The bundle is a self-contained
|
||
# /usr-like tree that the openclaw container can use via
|
||
# LD_LIBRARY_PATH, so missing deps = broken binaries.
|
||
APT_PKGS="openssh-client dnsutils iputils-ping wget gnupg jq ripgrep fd-find ncdu htop strace tcpdump tmux unzip ca-certificates"
|
||
apt-get install -y --download-only $APT_PKGS
|
||
|
||
for d in /var/cache/apt/archives/*.deb; do
|
||
dpkg-deb -x "$d" "$DEST/root/"
|
||
done
|
||
|
||
VAULT_VER=1.18.3
|
||
YQ_VER=v4.44.3
|
||
wget -qO /tmp/vault.zip \
|
||
"https://releases.hashicorp.com/vault/$${VAULT_VER}/vault_$${VAULT_VER}_linux_amd64.zip"
|
||
unzip -o /tmp/vault.zip vault -d "$DEST/bin/"
|
||
chmod +x "$DEST/bin/vault"
|
||
wget -qO "$DEST/bin/yq" \
|
||
"https://github.com/mikefarah/yq/releases/download/$${YQ_VER}/yq_linux_amd64"
|
||
chmod +x "$DEST/bin/yq"
|
||
|
||
# Smoke test — fail init if any bundled binary has unresolved
|
||
# shared-lib deps, so glibc / shared-lib drift surfaces at
|
||
# deploy time. We don't run --version because flag support
|
||
# varies (older scp returns non-zero, ping/nslookup use weird
|
||
# conventions). ldd is the reliable signal: if any "not
|
||
# found" appears, the binary won't load when called.
|
||
# LD_LIBRARY_PATH points ld.so at the bundled libs (the
|
||
# openclaw main container sets the same env).
|
||
export PATH="$DEST/root/usr/bin:$DEST/root/usr/sbin:$DEST/root/bin:$DEST/root/sbin:$DEST/bin:$PATH"
|
||
export LD_LIBRARY_PATH="$DEST/root/usr/lib/x86_64-linux-gnu:$DEST/root/lib/x86_64-linux-gnu"
|
||
for t in ssh scp ssh-keyscan dig host nslookup ping wget gpg jq rg fdfind tmux vault yq; do
|
||
bin=$(command -v "$t" 2>/dev/null) || { echo "FAIL: $t not on PATH"; exit 1; }
|
||
if ldd "$bin" 2>&1 | grep -q "not found"; then
|
||
echo "FAIL: $t has unresolved shared libs:"
|
||
ldd "$bin"
|
||
exit 1
|
||
fi
|
||
echo "OK: $t"
|
||
done
|
||
|
||
chown -R 1000:1000 "$DEST"
|
||
touch "$MARKER"
|
||
echo "host-tools v1 install complete ($(du -sh "$DEST" | cut -f1))"
|
||
EOT
|
||
]
|
||
volume_mount {
|
||
name = "tools"
|
||
mount_path = "/tools"
|
||
}
|
||
resources {
|
||
requests = { cpu = "100m", memory = "256Mi" }
|
||
limits = { memory = "512Mi" }
|
||
}
|
||
}
|
||
|
||
# Init 5: write /home/node/.openclaw/.ssh/{id_rsa,config,known_hosts}
|
||
# so the agent can `ssh devvm` without device-trust prompts. The
|
||
# main container symlinks /home/node/.ssh → here at startup so
|
||
# the ssh client picks it up via $HOME/.ssh. Installs
|
||
# openssh-client transiently into this init container so
|
||
# ssh-keyscan works without LD_LIBRARY_PATH gymnastics.
|
||
init_container {
|
||
name = "setup-ssh-config"
|
||
image = "debian:bookworm-slim"
|
||
command = ["bash", "-c", <<-EOT
|
||
set -euo pipefail
|
||
SSH=/home/node/.openclaw/.ssh
|
||
MARKER="$SSH/.configured-v1"
|
||
if [ -f "$MARKER" ]; then
|
||
echo "ssh-config v1 already set up (skipping)"
|
||
exit 0
|
||
fi
|
||
echo "installing openssh-client for ssh-keyscan ..."
|
||
export DEBIAN_FRONTEND=noninteractive
|
||
apt-get update -qq
|
||
apt-get install -y --no-install-recommends openssh-client >/dev/null
|
||
|
||
echo "configuring ssh ..."
|
||
mkdir -p "$SSH"
|
||
|
||
# Copy the secret-mounted private key into ~/.ssh with 0600 —
|
||
# the secret's tmpfs mount has wider perms (1777 + symlinks)
|
||
# that openssh refuses.
|
||
cp /ssh/id_rsa "$SSH/id_rsa"
|
||
chmod 0600 "$SSH/id_rsa"
|
||
|
||
cat > "$SSH/config" <<'SSH_EOF'
|
||
Host devvm
|
||
HostName 10.0.10.10
|
||
User wizard
|
||
IdentityFile ~/.ssh/id_rsa
|
||
UserKnownHostsFile ~/.ssh/known_hosts
|
||
StrictHostKeyChecking yes
|
||
SSH_EOF
|
||
chmod 0600 "$SSH/config"
|
||
|
||
ssh-keyscan -H 10.0.10.10 > "$SSH/known_hosts" 2>/tmp/keyscan.err
|
||
if [ ! -s "$SSH/known_hosts" ]; then
|
||
echo "ssh-keyscan produced empty known_hosts; stderr:"
|
||
cat /tmp/keyscan.err
|
||
exit 1
|
||
fi
|
||
chmod 0644 "$SSH/known_hosts"
|
||
|
||
chown -R 1000:1000 "$SSH"
|
||
touch "$MARKER"
|
||
echo "ssh-config v1 set up"
|
||
EOT
|
||
]
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
}
|
||
volume_mount {
|
||
name = "ssh-key"
|
||
mount_path = "/ssh"
|
||
}
|
||
resources {
|
||
requests = { cpu = "50m", memory = "64Mi" }
|
||
limits = { memory = "256Mi" }
|
||
}
|
||
}
|
||
|
||
# Init 6: seed the devvm-fallback memory note into
|
||
# /workspace/memory/projects/openclaw-runtime/. The note teaches
|
||
# openclaw the SSH+tmux pattern. The main container's startup
|
||
# runs `memory index --force` so it's searchable immediately;
|
||
# the daily memory-sync CronJob also keeps it indexed afterward.
|
||
# Always rewrites — the configmap-baked note is canonical.
|
||
init_container {
|
||
name = "seed-devvm-memory-note"
|
||
image = "busybox:1.37"
|
||
command = ["sh", "-c", <<-EOT
|
||
set -eu
|
||
DIR=/workspace/memory/projects/openclaw-runtime
|
||
mkdir -p "$DIR"
|
||
cat > "$DIR/devvm-fallback.md" <<'NOTE_EOF'
|
||
# Using devvm as a fallback
|
||
|
||
When in-pod tools/permissions block you, SSH to devvm and use it.
|
||
Devvm runs as wizard with full home-lab access (Vault, kubectl,
|
||
git repos, Cloudflare, etc.) and Claude Code v2+ is installed.
|
||
|
||
## One-shot lookup
|
||
|
||
ssh devvm 'vault kv get -field=brave_api_key secret/openclaw'
|
||
ssh devvm 'claude -p "investigate why frigate is restarting"'
|
||
|
||
## Long-running async work — USE THIS for anything > ~2 min
|
||
|
||
Spawn in a tmux session on devvm. Sessions and logs survive
|
||
OpenClaw pod restarts (they live on devvm, not in this pod).
|
||
|
||
# spawn
|
||
ssh devvm openclaw-task new my-task "claude -p --dangerously-skip-permissions 'do the thing'"
|
||
|
||
# poll progress (last 1000 lines of pane)
|
||
ssh devvm openclaw-task capture my-task
|
||
|
||
# interactive claude (send follow-up prompts)
|
||
ssh devvm openclaw-task claude my-task "initial prompt"
|
||
ssh devvm openclaw-task send my-task "follow-up prompt" Enter
|
||
|
||
# housekeeping
|
||
ssh devvm openclaw-task list
|
||
ssh devvm openclaw-task status my-task
|
||
ssh devvm openclaw-task kill my-task
|
||
|
||
Logs persist at ~/openclaw-tasks/<id>.log on devvm even after a
|
||
session is killed. Use `ssh devvm openclaw-task log <id>` to
|
||
retrieve them.
|
||
NOTE_EOF
|
||
chown -R 1000:1000 "$DIR"
|
||
echo "memory note seeded at $DIR/devvm-fallback.md"
|
||
EOT
|
||
]
|
||
volume_mount {
|
||
name = "workspace"
|
||
mount_path = "/workspace"
|
||
}
|
||
resources {
|
||
requests = { cpu = "10m", memory = "32Mi" }
|
||
limits = { memory = "32Mi" }
|
||
}
|
||
}
|
||
|
||
# Main container: OpenClaw
|
||
container {
|
||
name = "openclaw"
|
||
image = "ghcr.io/openclaw/openclaw:2026.5.4"
|
||
# Startup sequence:
|
||
# 1. doctor --fix — repair sessions/state (also resets some config)
|
||
# 2. models set — pin gpt-5.4-mini (doctor auto-promotes to gpt-5-pro otherwise)
|
||
# 3. mcp set <name> — register MCP servers via the CLI (the
|
||
# ConfigMap-baked mcp.servers block gets
|
||
# stripped by doctor --fix, but CLI-written
|
||
# entries persist). Values: ha URL from
|
||
# $HA_SOFIA_MCP_URL env (Vault-sourced),
|
||
# others hard-coded.
|
||
# 4. gateway — exec into the gateway process
|
||
command = ["sh", "-c", <<-EOC
|
||
# Symlink /home/node/.ssh → persistent .ssh so the ssh client
|
||
# finds id_rsa/config/known_hosts via $HOME/.ssh. HOME is
|
||
# /home/node (image overlay), .ssh files live on the PVC
|
||
# at /home/node/.openclaw/.ssh (set up by init 5).
|
||
ln -sfn /home/node/.openclaw/.ssh /home/node/.ssh
|
||
node openclaw.mjs doctor --fix 2>/dev/null
|
||
node openclaw.mjs models set openai-codex/gpt-5.4-mini 2>/dev/null
|
||
node openclaw.mjs mcp set ha "{\"url\":\"$HA_SOFIA_MCP_URL\",\"transport\":\"streamable-http\"}" 2>/dev/null
|
||
node openclaw.mjs mcp set context7 '{"command":"npx","args":["-y","@upstash/context7-mcp"]}' 2>/dev/null
|
||
node openclaw.mjs mcp set playwright '{"url":"http://localhost:3000/mcp","transport":"streamable-http"}' 2>/dev/null
|
||
# doctor --fix overwrites plugins.allow with its bundled-plugins
|
||
# list. Re-add our third-party plugin to the allow list via
|
||
# `config patch`, then enable it. (Same pattern as mcp set above.)
|
||
echo '{"plugins":{"allow":["memory-core","recruiter-api","telegram","openrouter","brave","openai","codex"]}}' \
|
||
| node openclaw.mjs config patch --stdin 2>/dev/null || true
|
||
node openclaw.mjs plugins enable recruiter-api 2>/dev/null || true
|
||
# Reindex memory-core so the seeded devvm-fallback note (and
|
||
# anything else dropped under /workspace/memory/) is searchable
|
||
# on first boot; daily memory-sync CronJob also keeps it indexed.
|
||
node openclaw.mjs memory index --force 2>/dev/null || true
|
||
exec node openclaw.mjs gateway --allow-unconfigured --bind lan
|
||
EOC
|
||
]
|
||
port {
|
||
container_port = 18789
|
||
}
|
||
readiness_probe {
|
||
tcp_socket {
|
||
port = 18789
|
||
}
|
||
initial_delay_seconds = 30
|
||
period_seconds = 10
|
||
}
|
||
env {
|
||
name = "NODE_OPTIONS"
|
||
value = "--max-old-space-size=1536"
|
||
}
|
||
env {
|
||
name = "OPENCLAW_GATEWAY_TOKEN"
|
||
value = random_password.gateway_token.result
|
||
}
|
||
env {
|
||
name = "PATH"
|
||
# Host-tools bundle (installed by init 4: install-host-tools)
|
||
# comes first so ssh/scp/dig/vault/jq/etc. resolve to the
|
||
# extracted Debian binaries + the static-binary downloads.
|
||
# /bin + /sbin are needed because iputils-ping installs ping
|
||
# under /bin (not /usr/bin) on Debian.
|
||
value = "/tools/host-tools/root/usr/bin:/tools/host-tools/root/usr/sbin:/tools/host-tools/root/bin:/tools/host-tools/root/sbin:/tools/host-tools/bin:/tools:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
|
||
}
|
||
env {
|
||
# Point ld.so at the bundled libs so the host-tools binaries
|
||
# find their shared-lib deps (libgssapi_krb5, libkrb5, etc.).
|
||
# Both base images are bookworm so the libs match the
|
||
# openclaw image's libc/libssl — no ABI conflicts expected.
|
||
name = "LD_LIBRARY_PATH"
|
||
value = "/tools/host-tools/root/usr/lib/x86_64-linux-gnu:/tools/host-tools/root/lib/x86_64-linux-gnu"
|
||
}
|
||
env {
|
||
name = "TF_VAR_prod"
|
||
value = "true"
|
||
}
|
||
env {
|
||
name = "KUBECONFIG"
|
||
value = "/home/node/.openclaw/kubeconfig"
|
||
}
|
||
env {
|
||
name = "GIT_CONFIG_GLOBAL"
|
||
value = "/home/node/.openclaw/.gitconfig"
|
||
}
|
||
# Skill secrets - Home Assistant
|
||
env {
|
||
name = "HOME_ASSISTANT_URL"
|
||
value = "https://ha-london.viktorbarzin.me"
|
||
}
|
||
env {
|
||
name = "HOME_ASSISTANT_TOKEN"
|
||
value = local.skill_secrets["home_assistant_token"]
|
||
}
|
||
env {
|
||
name = "HOME_ASSISTANT_SOFIA_URL"
|
||
value = "https://ha-sofia.viktorbarzin.me"
|
||
}
|
||
env {
|
||
name = "HOME_ASSISTANT_SOFIA_TOKEN"
|
||
value = local.skill_secrets["home_assistant_sofia_token"]
|
||
}
|
||
# MCP URL for ha-mcp add-on on ha-sofia (secret-path auth).
|
||
# Consumed in the startup command by `openclaw mcp set ha ...`.
|
||
env {
|
||
name = "HA_SOFIA_MCP_URL"
|
||
value = data.vault_kv_secret_v2.secrets.data["ha_sofia_mcp_url"]
|
||
}
|
||
# Skill secrets - Uptime Kuma
|
||
env {
|
||
name = "UPTIME_KUMA_PASSWORD"
|
||
value = local.skill_secrets["uptime_kuma_password"]
|
||
}
|
||
# Memory API
|
||
env {
|
||
name = "MEMORY_API_URL"
|
||
value = "http://claude-memory.claude-memory.svc.cluster.local"
|
||
}
|
||
env {
|
||
name = "MEMORY_API_KEY"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "claude_memory_api_key"
|
||
}
|
||
}
|
||
}
|
||
# Recruiter Responder API — consumed by the recruiter-api plugin
|
||
# (mounted into /home/node/.openclaw/extensions/recruiter-api/ via
|
||
# the install-recruiter-plugin init container below).
|
||
env {
|
||
name = "RECRUITER_RESPONDER_URL"
|
||
value = "http://recruiter-responder.recruiter-responder.svc.cluster.local:8080"
|
||
}
|
||
env {
|
||
name = "RECRUITER_RESPONDER_TOKEN"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "recruiter_responder_bearer_token"
|
||
optional = true
|
||
}
|
||
}
|
||
}
|
||
# Telegram chat ID for the recruiter-api plugin's announcement loop.
|
||
env {
|
||
name = "VIKTOR_CHAT_ID"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "viktor_chat_id"
|
||
optional = true
|
||
}
|
||
}
|
||
}
|
||
# Python packages path for skills
|
||
env {
|
||
name = "PYTHONPATH"
|
||
value = "/tools/python-libs"
|
||
}
|
||
volume_mount {
|
||
name = "tools"
|
||
mount_path = "/tools"
|
||
}
|
||
volume_mount {
|
||
name = "workspace"
|
||
mount_path = "/workspace"
|
||
}
|
||
volume_mount {
|
||
name = "data"
|
||
mount_path = "/data"
|
||
}
|
||
volume_mount {
|
||
name = "ssh-key"
|
||
mount_path = "/ssh"
|
||
}
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
}
|
||
resources {
|
||
limits = {
|
||
memory = "2Gi"
|
||
}
|
||
requests = {
|
||
cpu = "100m"
|
||
memory = "2Gi"
|
||
}
|
||
}
|
||
}
|
||
|
||
# Sidecar: playwright-mcp — headless browser for agents
|
||
container {
|
||
name = "playwright-mcp"
|
||
image = "docker.io/viktorbarzin/playwright-mcp:v1"
|
||
args = ["--headless", "--browser", "chromium", "--no-sandbox", "--port", "3000", "--host", "0.0.0.0"]
|
||
port {
|
||
container_port = 3000
|
||
}
|
||
resources {
|
||
requests = {
|
||
cpu = "50m"
|
||
memory = "256Mi"
|
||
}
|
||
limits = {
|
||
memory = "512Mi"
|
||
}
|
||
}
|
||
}
|
||
|
||
# Sidecar: openclaw-exporter — Prometheus exporter for Codex/OAuth usage.
|
||
# Reads sessions JSONL files + auth-profiles.json, exposes /metrics on :9099.
|
||
# Stdlib-only Python; no pip install at startup.
|
||
container {
|
||
name = "openclaw-exporter"
|
||
image = "docker.io/library/python:3.12-slim"
|
||
command = ["python3", "/scripts/exporter.py"]
|
||
port {
|
||
container_port = 9099
|
||
name = "metrics"
|
||
}
|
||
env {
|
||
name = "OPENCLAW_HOME"
|
||
value = "/home/node/.openclaw"
|
||
}
|
||
env {
|
||
name = "METRICS_PORT"
|
||
value = "9099"
|
||
}
|
||
volume_mount {
|
||
name = "openclaw-exporter-script"
|
||
mount_path = "/scripts"
|
||
read_only = true
|
||
}
|
||
volume_mount {
|
||
name = "openclaw-home"
|
||
mount_path = "/home/node/.openclaw"
|
||
read_only = true
|
||
}
|
||
readiness_probe {
|
||
http_get {
|
||
path = "/healthz"
|
||
port = 9099
|
||
}
|
||
initial_delay_seconds = 5
|
||
period_seconds = 30
|
||
}
|
||
resources {
|
||
requests = {
|
||
cpu = "10m"
|
||
memory = "64Mi"
|
||
}
|
||
limits = {
|
||
memory = "128Mi"
|
||
}
|
||
}
|
||
}
|
||
|
||
# Sidecar: modelrelay — auto-routes to fastest healthy free model
|
||
container {
|
||
name = "modelrelay"
|
||
image = "docker.io/library/node:22-alpine"
|
||
command = ["sh", "-c", <<-EOF
|
||
if [ ! -f /tools/modelrelay/node_modules/.package-lock.json ]; then
|
||
mkdir -p /tools/modelrelay
|
||
cd /tools/modelrelay
|
||
npm init -y > /dev/null 2>&1
|
||
npm install modelrelay > /dev/null 2>&1
|
||
fi
|
||
cd /tools/modelrelay
|
||
exec npx modelrelay --port 7352
|
||
EOF
|
||
]
|
||
port {
|
||
container_port = 7352
|
||
}
|
||
env {
|
||
name = "NVIDIA_API_KEY"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "nvidia_api_key"
|
||
}
|
||
}
|
||
}
|
||
env {
|
||
name = "OPENROUTER_API_KEY"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "openrouter_api_key"
|
||
}
|
||
}
|
||
}
|
||
volume_mount {
|
||
name = "tools"
|
||
mount_path = "/tools"
|
||
}
|
||
resources {
|
||
limits = {
|
||
memory = "256Mi"
|
||
}
|
||
requests = {
|
||
cpu = "25m"
|
||
memory = "128Mi"
|
||
}
|
||
}
|
||
}
|
||
|
||
volume {
|
||
name = "tools"
|
||
persistent_volume_claim {
|
||
claim_name = module.nfs_tools_host.claim_name
|
||
}
|
||
}
|
||
volume {
|
||
name = "openclaw-home"
|
||
persistent_volume_claim {
|
||
claim_name = kubernetes_persistent_volume_claim.home_proxmox.metadata[0].name
|
||
}
|
||
}
|
||
volume {
|
||
name = "workspace"
|
||
persistent_volume_claim {
|
||
claim_name = module.nfs_workspace_host.claim_name
|
||
}
|
||
}
|
||
volume {
|
||
name = "data"
|
||
persistent_volume_claim {
|
||
claim_name = kubernetes_persistent_volume_claim.data_proxmox.metadata[0].name
|
||
}
|
||
}
|
||
volume {
|
||
name = "ssh-key"
|
||
secret {
|
||
secret_name = kubernetes_secret.ssh_key.metadata[0].name
|
||
default_mode = "0600"
|
||
}
|
||
}
|
||
volume {
|
||
name = "openclaw-config"
|
||
config_map {
|
||
name = kubernetes_config_map.openclaw_config.metadata[0].name
|
||
}
|
||
}
|
||
volume {
|
||
name = "openclaw-exporter-script"
|
||
config_map {
|
||
name = kubernetes_config_map.openclaw_exporter.metadata[0].name
|
||
default_mode = "0555"
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
||
ignore_changes = [spec[0].template[0].spec[0].dns_config]
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_service" "openclaw" {
|
||
metadata {
|
||
name = "openclaw"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "openclaw"
|
||
}
|
||
}
|
||
spec {
|
||
selector = {
|
||
app = "openclaw"
|
||
}
|
||
port {
|
||
port = 80
|
||
target_port = 18789
|
||
}
|
||
}
|
||
}
|
||
|
||
module "ingress" {
|
||
source = "../../modules/kubernetes/ingress_factory"
|
||
dns_type = "non-proxied"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
name = "openclaw"
|
||
tls_secret_name = var.tls_secret_name
|
||
port = 80
|
||
auth = "required"
|
||
extra_annotations = {
|
||
"gethomepage.dev/enabled" = "true"
|
||
"gethomepage.dev/name" = "OpenClaw"
|
||
"gethomepage.dev/description" = "AI assistant"
|
||
"gethomepage.dev/icon" = "openai.png"
|
||
"gethomepage.dev/group" = "AI & Data"
|
||
"gethomepage.dev/pod-selector" = ""
|
||
}
|
||
}
|
||
|
||
# --- Webhook receiver: triggers task-processor Job on Forgejo issue events ---
|
||
|
||
resource "kubernetes_config_map" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"server.py" = <<-PYEOF
|
||
from http.server import HTTPServer, BaseHTTPRequestHandler
|
||
import subprocess, time, json, os
|
||
|
||
BOT_USER = os.environ.get('FORGEJO_BOT_USER', 'viktor')
|
||
|
||
class Handler(BaseHTTPRequestHandler):
|
||
def do_POST(self):
|
||
try:
|
||
body = self.rfile.read(int(self.headers.get('Content-Length', 0)))
|
||
data = json.loads(body)
|
||
action = data.get('action', '')
|
||
|
||
# Trigger on: new issue, reopened issue, or new comment
|
||
trigger = False
|
||
if action in ('opened', 'reopened'):
|
||
issue = data.get('issue', {})
|
||
print(f"Issue #{issue.get('number','?')} {action}: {issue.get('title','?')}")
|
||
trigger = True
|
||
elif action == 'created' and 'comment' in data:
|
||
comment = data.get('comment', {})
|
||
commenter = comment.get('user', {}).get('login', '')
|
||
# Skip comments from the bot itself to avoid loops
|
||
if commenter != BOT_USER:
|
||
issue = data.get('issue', {})
|
||
print(f"Comment on #{issue.get('number','?')} by {commenter}")
|
||
trigger = True
|
||
else:
|
||
print(f"Skipping own comment on #{data.get('issue',{}).get('number','?')}")
|
||
|
||
if trigger:
|
||
job_name = f"task-processor-{int(time.time())}"
|
||
subprocess.run([
|
||
'kubectl', 'create', 'job', job_name,
|
||
'--from=cronjob/task-processor',
|
||
'-n', 'openclaw'
|
||
], check=True)
|
||
self.send_response(200)
|
||
self.end_headers()
|
||
self.wfile.write(b'{"ok":true}')
|
||
else:
|
||
self.send_response(200)
|
||
self.end_headers()
|
||
self.wfile.write(b'{"ok":true,"skipped":true}')
|
||
except Exception as e:
|
||
print(f"Error: {e}")
|
||
self.send_response(500)
|
||
self.end_headers()
|
||
self.wfile.write(f'{{"error":"{e}"}}'.encode())
|
||
|
||
def do_GET(self):
|
||
self.send_response(200)
|
||
self.end_headers()
|
||
self.wfile.write(b'{"status":"ok"}')
|
||
|
||
def log_message(self, fmt, *args):
|
||
print(f"[webhook] {args[0]} {args[1]} {args[2]}")
|
||
|
||
print("Task webhook receiver listening on :8080")
|
||
HTTPServer(('', 8080), Handler).serve_forever()
|
||
PYEOF
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_service_account" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_role" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook-job-creator"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
rule {
|
||
api_groups = ["batch"]
|
||
resources = ["jobs", "cronjobs"]
|
||
verbs = ["get", "list", "create"]
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_role_binding" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook-job-creator"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
subject {
|
||
kind = "ServiceAccount"
|
||
name = kubernetes_service_account.task_webhook.metadata[0].name
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
role_ref {
|
||
api_group = "rbac.authorization.k8s.io"
|
||
kind = "Role"
|
||
name = kubernetes_role.task_webhook.metadata[0].name
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_deployment" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "task-webhook"
|
||
tier = local.tiers.aux
|
||
}
|
||
}
|
||
spec {
|
||
replicas = 1
|
||
selector {
|
||
match_labels = {
|
||
app = "task-webhook"
|
||
}
|
||
}
|
||
template {
|
||
metadata {
|
||
labels = {
|
||
app = "task-webhook"
|
||
}
|
||
}
|
||
spec {
|
||
service_account_name = kubernetes_service_account.task_webhook.metadata[0].name
|
||
container {
|
||
name = "webhook"
|
||
image = "python:3-alpine"
|
||
command = ["sh", "-c", "apk add --no-cache curl > /dev/null 2>&1 && curl -sfL https://dl.k8s.io/release/v1.34.2/bin/linux/amd64/kubectl -o /usr/local/bin/kubectl && chmod +x /usr/local/bin/kubectl && exec python3 -u /app/server.py"]
|
||
port {
|
||
container_port = 8080
|
||
}
|
||
volume_mount {
|
||
name = "app"
|
||
mount_path = "/app"
|
||
}
|
||
resources {
|
||
requests = {
|
||
cpu = "5m"
|
||
memory = "64Mi"
|
||
}
|
||
limits = {
|
||
memory = "64Mi"
|
||
}
|
||
}
|
||
}
|
||
volume {
|
||
name = "app"
|
||
config_map {
|
||
name = kubernetes_config_map.task_webhook.metadata[0].name
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
||
ignore_changes = [spec[0].template[0].spec[0].dns_config]
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_service" "task_webhook" {
|
||
metadata {
|
||
name = "task-webhook"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "task-webhook"
|
||
}
|
||
}
|
||
spec {
|
||
selector = {
|
||
app = "task-webhook"
|
||
}
|
||
port {
|
||
port = 80
|
||
target_port = 8080
|
||
}
|
||
}
|
||
}
|
||
|
||
module "task_webhook_ingress" {
|
||
source = "../../modules/kubernetes/ingress_factory"
|
||
auth = "required"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
name = "task-webhook"
|
||
tls_secret_name = var.tls_secret_name
|
||
host = "task-webhook"
|
||
port = 80
|
||
external_monitor = false
|
||
}
|
||
|
||
# --- Shared ServiceAccount: grants pod-exec into the openclaw pod ---
|
||
# Used by the task_processor CronJob (below). Previously also used by the
|
||
# cluster_healthcheck CronJob, which has been decommissioned — the local
|
||
# `scripts/cluster_healthcheck.sh` is now the single authoritative runner.
|
||
|
||
resource "kubernetes_service_account" "healthcheck" {
|
||
metadata {
|
||
name = "cluster-healthcheck"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_role" "healthcheck_exec" {
|
||
metadata {
|
||
name = "healthcheck-pod-exec"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
rule {
|
||
api_groups = [""]
|
||
resources = ["pods"]
|
||
verbs = ["get", "list"]
|
||
}
|
||
rule {
|
||
api_groups = [""]
|
||
resources = ["pods/exec"]
|
||
verbs = ["create"]
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_role_binding" "healthcheck_exec" {
|
||
metadata {
|
||
name = "healthcheck-pod-exec"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
subject {
|
||
kind = "ServiceAccount"
|
||
name = kubernetes_service_account.healthcheck.metadata[0].name
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
role_ref {
|
||
api_group = "rbac.authorization.k8s.io"
|
||
kind = "Role"
|
||
name = kubernetes_role.healthcheck_exec.metadata[0].name
|
||
}
|
||
}
|
||
|
||
# --- CronJob: Task processor — polls Forgejo issues and triggers OpenClaw ---
|
||
|
||
resource "kubernetes_cron_job_v1" "task_processor" {
|
||
metadata {
|
||
name = "task-processor"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "task-processor"
|
||
tier = local.tiers.aux
|
||
}
|
||
}
|
||
spec {
|
||
schedule = "*/5 * * * *"
|
||
concurrency_policy = "Forbid"
|
||
failed_jobs_history_limit = 3
|
||
successful_jobs_history_limit = 3
|
||
|
||
job_template {
|
||
metadata {
|
||
labels = {
|
||
app = "task-processor"
|
||
}
|
||
}
|
||
spec {
|
||
active_deadline_seconds = 600
|
||
backoff_limit = 0
|
||
ttl_seconds_after_finished = 86400
|
||
template {
|
||
metadata {
|
||
labels = {
|
||
app = "task-processor"
|
||
}
|
||
}
|
||
spec {
|
||
service_account_name = kubernetes_service_account.healthcheck.metadata[0].name
|
||
restart_policy = "Never"
|
||
|
||
container {
|
||
name = "task-processor"
|
||
image = "bitnami/kubectl:latest"
|
||
command = ["bash", "-c", <<-EOF
|
||
# Find the openclaw pod
|
||
POD=$(kubectl get pods -n openclaw -l app=openclaw -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
|
||
if [ -z "$POD" ]; then
|
||
echo "ERROR: OpenClaw pod not found"
|
||
exit 1
|
||
fi
|
||
echo "Executing task processor in pod $POD..."
|
||
kubectl exec -n openclaw "$POD" -c openclaw -- \
|
||
env FORGEJO_TOKEN="$FORGEJO_TOKEN" \
|
||
FORGEJO_URL="http://forgejo.forgejo.svc.cluster.local" \
|
||
OPENCLAW_TOKEN="$OPENCLAW_TOKEN" \
|
||
OPENCLAW_URL="https://integrate.api.nvidia.com" \
|
||
bash /workspace/infra/scripts/task-processor.sh
|
||
EOF
|
||
]
|
||
|
||
env {
|
||
name = "FORGEJO_TOKEN"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "forgejo_api_token"
|
||
}
|
||
}
|
||
}
|
||
env {
|
||
name = "OPENCLAW_TOKEN"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "nvidia_api_key"
|
||
}
|
||
}
|
||
}
|
||
|
||
resources {
|
||
requests = {
|
||
cpu = "50m"
|
||
memory = "64Mi"
|
||
}
|
||
limits = {
|
||
memory = "64Mi"
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
||
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
||
}
|
||
}
|
||
|
||
# --- CronJob: claude-memory → memory-core sync (daily) ---
|
||
# Pulls all (non-sensitive) memories from claude-memory's REST API and
|
||
# writes them into memory-core's QMD-backed tree at
|
||
# /home/node/.openclaw/memory/projects/claude-memory-sync/. Then runs
|
||
# `openclaw memory index --force` to rebuild the search index so the
|
||
# OpenClaw agent can `memory_search` over the shared knowledge.
|
||
#
|
||
# Note: the central claude-memory MCP transport (/mcp/mcp) is broken
|
||
# on the deployed image (beads code-z1so) — this REST sync is the
|
||
# workaround. Once that's fixed we can also wire claude_memory as a
|
||
# native MCP server in the mcp.servers block above.
|
||
|
||
resource "kubernetes_config_map" "memory_sync_script" {
|
||
metadata {
|
||
name = "memory-sync-script"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
}
|
||
data = {
|
||
"memory-sync.py" = file("${path.module}/files/memory-sync.py")
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_cron_job_v1" "memory_sync" {
|
||
metadata {
|
||
name = "memory-sync"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "memory-sync"
|
||
tier = local.tiers.aux
|
||
}
|
||
}
|
||
spec {
|
||
schedule = "0 3 * * *"
|
||
concurrency_policy = "Forbid"
|
||
failed_jobs_history_limit = 3
|
||
successful_jobs_history_limit = 3
|
||
|
||
job_template {
|
||
metadata {
|
||
labels = {
|
||
app = "memory-sync"
|
||
}
|
||
}
|
||
spec {
|
||
active_deadline_seconds = 600
|
||
backoff_limit = 0
|
||
ttl_seconds_after_finished = 86400
|
||
template {
|
||
metadata {
|
||
labels = {
|
||
app = "memory-sync"
|
||
}
|
||
}
|
||
spec {
|
||
# Reuses the SA created for the (decommissioned) cluster
|
||
# healthcheck job — already has pods + pods/exec in this ns.
|
||
service_account_name = kubernetes_service_account.healthcheck.metadata[0].name
|
||
restart_policy = "Never"
|
||
|
||
container {
|
||
name = "memory-sync"
|
||
image = "bitnami/kubectl:latest"
|
||
command = ["bash", "-c", <<-EOF
|
||
set -eu
|
||
POD=$(kubectl get pods -n openclaw -l app=openclaw -o jsonpath='{.items[0].metadata.name}')
|
||
if [ -z "$POD" ]; then
|
||
echo "ERROR: no openclaw pod"
|
||
exit 1
|
||
fi
|
||
echo "syncing into pod $POD ..."
|
||
kubectl exec -n openclaw "$POD" -c openclaw -i -- python3 -u - < /scripts/memory-sync.py
|
||
echo "reindexing memory-core ..."
|
||
kubectl exec -n openclaw "$POD" -c openclaw -- sh -c 'cd /app && node openclaw.mjs memory index --force 2>&1 | tail -20'
|
||
echo "memory-sync complete."
|
||
EOF
|
||
]
|
||
|
||
volume_mount {
|
||
name = "script"
|
||
mount_path = "/scripts"
|
||
read_only = true
|
||
}
|
||
|
||
resources {
|
||
requests = {
|
||
cpu = "20m"
|
||
memory = "64Mi"
|
||
}
|
||
limits = {
|
||
memory = "64Mi"
|
||
}
|
||
}
|
||
}
|
||
|
||
volume {
|
||
name = "script"
|
||
config_map {
|
||
name = kubernetes_config_map.memory_sync_script.metadata[0].name
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
||
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
||
}
|
||
}
|
||
|
||
# --- OpenLobster: Multi-user Telegram AI assistant (trial) ---
|
||
|
||
resource "kubernetes_persistent_volume_claim" "openlobster_data_proxmox" {
|
||
wait_until_bound = false
|
||
metadata {
|
||
name = "openlobster-data-proxmox"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
annotations = {
|
||
"resize.topolvm.io/threshold" = "10%"
|
||
"resize.topolvm.io/increase" = "100%"
|
||
"resize.topolvm.io/storage_limit" = "5Gi"
|
||
}
|
||
}
|
||
spec {
|
||
access_modes = ["ReadWriteOnce"]
|
||
storage_class_name = "proxmox-lvm"
|
||
resources {
|
||
requests = {
|
||
storage = "1Gi"
|
||
}
|
||
}
|
||
}
|
||
lifecycle {
|
||
# The autoresizer expands requests.storage up to storage_limit and
|
||
# PVCs can't shrink. Without this, every TF apply tries to revert
|
||
# to the spec value, K8s rejects the shrink, and the PVC ends up
|
||
# in Terminating-but-in-use limbo.
|
||
ignore_changes = [spec[0].resources[0].requests]
|
||
}
|
||
}
|
||
|
||
resource "random_password" "openlobster_graphql_token" {
|
||
length = 32
|
||
special = false
|
||
}
|
||
|
||
resource "kubernetes_deployment" "openlobster" {
|
||
metadata {
|
||
name = "openlobster"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "openlobster"
|
||
tier = local.tiers.aux
|
||
}
|
||
}
|
||
spec {
|
||
strategy {
|
||
type = "Recreate"
|
||
}
|
||
replicas = 0
|
||
selector {
|
||
match_labels = {
|
||
app = "openlobster"
|
||
}
|
||
}
|
||
template {
|
||
metadata {
|
||
labels = {
|
||
app = "openlobster"
|
||
}
|
||
}
|
||
spec {
|
||
# node4 has corrupted containerd content store — avoid it
|
||
affinity {
|
||
node_affinity {
|
||
required_during_scheduling_ignored_during_execution {
|
||
node_selector_term {
|
||
match_expressions {
|
||
key = "kubernetes.io/hostname"
|
||
operator = "NotIn"
|
||
values = ["k8s-node4"]
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
container {
|
||
name = "openlobster"
|
||
image = "ghcr.io/neirth/openlobster/openlobster:latest"
|
||
port {
|
||
container_port = 8080
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_GRAPHQL_AUTH_TOKEN"
|
||
value = random_password.openlobster_graphql_token.result
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_PROVIDERS_ANTHROPIC_API_KEY"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "anthropic_api_key"
|
||
}
|
||
}
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_PROVIDERS_ANTHROPIC_MODEL"
|
||
value = "claude-sonnet-4-20250514"
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_CHANNELS_TELEGRAM_TOKEN"
|
||
value_from {
|
||
secret_key_ref {
|
||
name = "openclaw-secrets"
|
||
key = "telegram_bot_token"
|
||
}
|
||
}
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_DATABASE_DRIVER"
|
||
value = "sqlite"
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_DATABASE_DSN"
|
||
value = "/app/data/openlobster.db"
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_AGENT_NAME"
|
||
value = "Lobster"
|
||
}
|
||
env {
|
||
name = "OPENLOBSTER_MEMORY_BACKEND"
|
||
value = "file"
|
||
}
|
||
volume_mount {
|
||
name = "openlobster-data"
|
||
mount_path = "/app/data"
|
||
}
|
||
resources {
|
||
requests = {
|
||
cpu = "10m"
|
||
memory = "64Mi"
|
||
}
|
||
limits = {
|
||
memory = "256Mi"
|
||
}
|
||
}
|
||
}
|
||
volume {
|
||
name = "openlobster-data"
|
||
persistent_volume_claim {
|
||
claim_name = kubernetes_persistent_volume_claim.openlobster_data_proxmox.metadata[0].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
|
||
]
|
||
}
|
||
}
|
||
|
||
resource "kubernetes_service" "openlobster" {
|
||
metadata {
|
||
name = "openlobster"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
labels = {
|
||
app = "openlobster"
|
||
}
|
||
}
|
||
spec {
|
||
selector = {
|
||
app = "openlobster"
|
||
}
|
||
port {
|
||
port = 80
|
||
target_port = 8080
|
||
}
|
||
}
|
||
}
|
||
|
||
module "openlobster_ingress" {
|
||
source = "../../modules/kubernetes/ingress_factory"
|
||
dns_type = "proxied"
|
||
namespace = kubernetes_namespace.openclaw.metadata[0].name
|
||
name = "openlobster"
|
||
tls_secret_name = var.tls_secret_name
|
||
host = "openlobster"
|
||
port = 80
|
||
auth = "required"
|
||
}
|