version 2.6.0

.github/workflows/autogpt-infra-ci.yml

@@ -23,6 +23,9 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
       - name: TFLint
         uses: pauloconnor/tflint-action@v0.0.2
         env:
@@ -31,3 +34,23 @@ jobs:
             tflint_path: terraform/
             tflint_recurse: true
             tflint_changed_only: false
+
+      - name: Set up Helm
+        uses: azure/setup-helm@v4.2.0
+        with:
+          version: v3.14.4
+
+      - name: Set up chart-testing
+        uses: helm/chart-testing-action@v2.6.0
+
+      - name: Run chart-testing (list-changed)
+        id: list-changed
+        run: |
+          changed=$(ct list-changed --target-branch ${{ github.event.repository.default_branch }})
+          if [[ -n "$changed" ]]; then
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Run chart-testing (lint)
+        if: steps.list-changed.outputs.changed == 'true'
+        run: ct lint --target-branch ${{ github.event.repository.default_branch }}

rnd/autogpt_server/autogpt_server/server/server.py

@@ -15,7 +15,6 @@ from fastapi import (
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse
-from fastapi.staticfiles import StaticFiles
 
 import autogpt_server.server.ws_api
 from autogpt_server.data import block, db
@@ -34,7 +33,6 @@ from autogpt_server.server.model import (
     SetGraphActiveVersion,
     WsMessage,
 )
-from autogpt_server.util.data import get_frontend_path
 from autogpt_server.util.lock import KeyedMutex
 from autogpt_server.util.service import AppService, expose, get_service_client
 from autogpt_server.util.settings import Settings
@@ -190,12 +188,6 @@ class AgentServer(AppService):
 
         app.add_exception_handler(500, self.handle_internal_error)  # type: ignore
 
-        app.mount(
-            path="/frontend",
-            app=StaticFiles(directory=get_frontend_path(), html=True),
-            name="example_files",
-        )
-
         app.include_router(router)
 
         @app.websocket("/ws")

rnd/autogpt_server/autogpt_server/util/service.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import os
 import threading
 import time
 from abc import abstractmethod
@@ -16,6 +17,8 @@ logger = logging.getLogger(__name__)
 conn_retry = retry(stop=stop_after_delay(5), wait=wait_exponential(multiplier=0.1))
 T = TypeVar("T")
 
+host = os.environ.get("PYRO_HOST", "localhost")
+
 
 def expose(func: Callable) -> Callable:
     def wrapper(*args, **kwargs):
@@ -33,7 +36,7 @@ class PyroNameServer(AppProcess):
     def run(self):
         try:
             print("Starting NameServer loop")
-            nameserver.start_ns_loop()
+            nameserver.start_ns_loop(host=host, port=9090)
         except KeyboardInterrupt:
             print("Shutting down NameServer")
 
@@ -77,8 +80,8 @@ class AppService(AppProcess):
 
     @conn_retry
     def __start_pyro(self):
-        daemon = pyro.Daemon()
-        ns = pyro.locate_ns()
+        daemon = pyro.Daemon(host=host)
+        ns = pyro.locate_ns(host=host, port=9090)
         uri = daemon.register(self)
         ns.register(self.service_name, uri)
         logger.warning(f"Service [{self.service_name}] Ready. Object URI = {uri}")

rnd/infra/helm/autogpt-server/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

rnd/infra/helm/autogpt-server/Chart.yaml

@@ -0,0 +1,10 @@
+apiVersion: v2
+name: autogpt-server
+description: A Helm chart for AutoGPT on Kubernetes
+
+type: application
+
+
+version: 0.1.0
+
+appVersion: "1.0.0"

rnd/infra/helm/autogpt-server/templates/NOTES.txt

@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "autogpt-server.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "autogpt-server.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "autogpt-server.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "autogpt-server.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}

rnd/infra/helm/autogpt-server/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "autogpt-server.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "autogpt-server.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "autogpt-server.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "autogpt-server.labels" -}}
+helm.sh/chart: {{ include "autogpt-server.chart" . }}
+{{ include "autogpt-server.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "autogpt-server.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "autogpt-server.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "autogpt-server.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "autogpt-server.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

rnd/infra/helm/autogpt-server/templates/configmap.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "autogpt-server.fullname" . }}-config
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+data:
+  {{- range $key, $value := .Values.env }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}

rnd/infra/helm/autogpt-server/templates/deployment.yaml

@@ -0,0 +1,80 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "autogpt-server.fullname" . }}
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "autogpt-server.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "autogpt-server.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "autogpt-server.serviceAccountName" . }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Chart.Name }}
+          envFrom:
+            - configMapRef:
+                name: {{ include "autogpt-server.fullname" . }}-config
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          livenessProbe:
+            {{- toYaml .Values.livenessProbe | nindent 12 }}
+          readinessProbe:
+            {{- toYaml .Values.readinessProbe | nindent 12 }}
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+          {{- with .Values.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+        - name: cloud-sql-proxy
+          image: "{{ .Values.cloudSqlProxy.image.repository }}:{{ .Values.cloudSqlProxy.image.tag }}"
+          args:
+            - "--structured-logs"
+            {{- if .Values.cloudSqlProxy.usePrivateIp }}
+            - "--private-ip"
+            {{- end }}
+            - "--port={{ .Values.cloudSqlProxy.port }}"
+            - "{{ .Values.cloudSqlProxy.instanceConnectionName }}"
+      {{- with .Values.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}

rnd/infra/helm/autogpt-server/templates/hpa.yaml

@@ -0,0 +1,32 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "autogpt-server.fullname" . }}
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "autogpt-server.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}

rnd/infra/helm/autogpt-server/templates/ingress.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "autogpt-server.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
+  {{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
+  {{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
+  {{- end }}
+{{- end }}
+{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1beta1
+{{- else -}}
+apiVersion: extensions/v1beta1
+{{- end }}
+kind: Ingress
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+              service:
+                name: {{ $fullName }}
+                port:
+                  number: {{ $svcPort }}
+              {{- else }}
+              serviceName: {{ $fullName }}
+              servicePort: {{ $svcPort }}
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

rnd/infra/helm/autogpt-server/templates/managedcert.yaml

@@ -0,0 +1,7 @@
+apiVersion: networking.gke.io/v1
+kind: ManagedCertificate
+metadata:
+  name: {{ include "autogpt-server.fullname" . }}-cert
+spec:
+  domains:
+    - {{ .Values.domain }}

rnd/infra/helm/autogpt-server/templates/service.yaml

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "autogpt-server.fullname" . }}
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+  {{- with .Values.service.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    {{- include "autogpt-server.selectorLabels" . | nindent 4 }}

rnd/infra/helm/autogpt-server/templates/serviceaccount.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "autogpt-server.serviceAccountName" . }}
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
+{{- end }}

rnd/infra/helm/autogpt-server/templates/tests/test-connection.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "autogpt-server.fullname" . }}-test-connection"
+  labels:
+    {{- include "autogpt-server.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "autogpt-server.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never

rnd/infra/helm/autogpt-server/values.dev.yaml

@@ -0,0 +1,83 @@
+# dev values, overwrite base values as needed.
+
+image:
+  repository: us-east1-docker.pkg.dev/agpt-dev/agpt-server-dev/agpt-server-dev
+  pullPolicy: Always
+  tag: "latest"
+
+serviceAccount:
+  annotations:
+    iam.gke.io/gcp-service-account: "dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  name: "dev-agpt-server-sa"
+
+service:
+  type: ClusterIP
+  port: 8000
+  targetPort: 8000
+  annotations:
+    cloud.google.com/neg: '{"ingress": true}'
+
+ingress:
+  enabled: true
+  className: "gce"
+  annotations:
+    kubernetes.io/ingress.class: gce
+    kubernetes.io/ingress.global-static-ip-name: "agpt-dev-agpt-server-ip"
+    networking.gke.io/managed-certificates: "autogpt-server-cert"
+    kubernetes.io/ingress.allow-http: "true"
+  hosts:
+    - host: dev-server.agpt.co
+      paths:
+        - path: /
+          pathType: Prefix
+      backend:
+        service:
+          name: autogpt-server
+          port: 8000
+  defaultBackend:
+    service:
+      name: autogpt-server
+      port:
+        number: 8000
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+livenessProbe:
+  httpGet:
+    path: /docs
+    port: 8000
+  initialDelaySeconds: 30
+  periodSeconds: 10
+  timeoutSeconds: 5
+  failureThreshold: 6
+readinessProbe:
+  httpGet:
+    path: /docs
+    port: 8000
+  initialDelaySeconds: 30
+  periodSeconds: 10
+  timeoutSeconds: 5
+  failureThreshold: 6
+
+domain: "dev-server.agpt.co"
+
+cloudSqlProxy:
+  image:
+    repository: gcr.io/cloud-sql-connectors/cloud-sql-proxy
+    tag: 2.11.4
+  instanceConnectionName: "agpt-dev:us-central1:agpt-server-dev"
+  port: 5432
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "1"
+
+env:
+  APP_ENV: "dev"
+  PYRO_HOST: "0.0.0.0"

rnd/infra/helm/autogpt-server/values.yaml

@@ -0,0 +1,87 @@
+# base values, environment specific variables should be specified/overwritten in environment values
+
+replicaCount: 1
+
+image:
+  repository: us-east1-docker.pkg.dev/agpt-dev/agpt-server-dev/agpt-server-dev
+  pullPolicy: IfNotPresent
+  tag: "latest"
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  create: true
+  automount: true
+  annotations: {}
+  name: ""
+
+podAnnotations: {}
+podLabels: {}
+
+podSecurityContext: {}
+
+securityContext: {}
+
+service:
+  type: ClusterIP
+  port: 80
+
+ingress:
+  enabled: false
+  className: ""
+  annotations: {}
+  hosts:
+    - host: chart-example.local
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls: []
+
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+livenessProbe:
+  httpGet:
+    path: /
+    port: http
+readinessProbe:
+  httpGet:
+    path: /
+    port: http
+
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  targetMemoryUtilizationPercentage: 80
+
+volumes: []
+
+volumeMounts: []
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+domain: ""
+
+cloudSqlProxy:
+  image:
+    repository: gcr.io/cloud-sql-connectors/cloud-sql-proxy
+    tag: 2.11.4
+  instanceConnectionName: ""
+  port: 5432
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "1"

rnd/infra/terraform/environments/dev.tfvars

@@ -10,3 +10,46 @@ node_pool_name  = "dev-main-pool"
 machine_type    = "e2-medium"
 disk_size_gb    = 100
 static_ip_names = ["agpt-server-ip", "agpt-builder-ip", "auth-ip"]
+
+
+service_accounts = {
+  "dev-agpt-server-sa" = {
+    display_name = "AutoGPT Dev Server Account"
+    description  = "Service account for agpt dev server"
+  }
+}
+
+workload_identity_bindings = {
+  "dev-agpt-server-workload-identity" = {
+    service_account_name = "dev-agpt-server-sa"
+    namespace            = "dev-agpt"
+    ksa_name             = "dev-agpt-server-sa"
+  }
+}
+
+role_bindings = {
+  "roles/container.developer" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ],
+  "roles/cloudsql.client" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ],
+  "roles/cloudsql.editor" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ],
+  "roles/cloudsql.instanceUser" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ],
+  "roles/iam.workloadIdentityUser" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ]
+  "roles/compute.networkUser" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ],
+  "roles/container.hostServiceAgentUser" = [
+    "serviceAccount:dev-agpt-server-sa@agpt-dev.iam.gserviceaccount.com"
+  ]
+}
+
+pods_ip_cidr_range     = "10.1.0.0/16"
+services_ip_cidr_range = "10.2.0.0/20"

rnd/infra/terraform/main.tf

@@ -6,10 +6,12 @@ terraform {
       version = "~> 4.0"
     }
   }
+
   backend "gcs" {
     bucket = "agpt-dev-terraform"
     prefix = "terraform/state"
   }
+
 }
 
 provider "google" {
@@ -28,11 +30,13 @@ module "static_ips" {
 module "networking" {
   source = "./modules/networking"
 
-  project_id   = var.project_id
-  region       = var.region
-  network_name = var.network_name
-  subnet_name  = var.subnet_name
-  subnet_cidr  = var.subnet_cidr
+  project_id             = var.project_id
+  region                 = var.region
+  network_name           = var.network_name
+  subnet_name            = var.subnet_name
+  subnet_cidr            = var.subnet_cidr
+  pods_ip_cidr_range     = var.pods_ip_cidr_range
+  services_ip_cidr_range = var.services_ip_cidr_range
 }
 
 module "gke_cluster" {
@@ -49,3 +53,12 @@ module "gke_cluster" {
   subnetwork       = module.networking.subnet_self_link
   enable_autopilot = var.enable_autopilot
 }
+
+module "iam" {
+  source = "./modules/iam"
+
+  project_id                 = var.project_id
+  service_accounts           = var.service_accounts
+  workload_identity_bindings = var.workload_identity_bindings
+  role_bindings              = var.role_bindings
+}

rnd/infra/terraform/modules/gke_cluster/main.tf

@@ -2,6 +2,11 @@ resource "google_container_cluster" "primary" {
   name     = var.cluster_name
   location = var.zone
 
+  workload_identity_config {
+    workload_pool = "${var.project_id}.svc.id.goog"
+  }
+
+
   dynamic "node_pool" {
     for_each = var.enable_autopilot ? [] : [1]
     content {
@@ -11,11 +16,20 @@ resource "google_container_cluster" "primary" {
       node_config {
         machine_type = var.machine_type
         disk_size_gb = var.disk_size_gb
+
+        workload_metadata_config {
+          mode = "GKE_METADATA"
+        }
       }
     }
   }
 
   network    = var.network
   subnetwork = var.subnetwork
+
+  ip_allocation_policy {
+    cluster_secondary_range_name  = "pods"
+    services_secondary_range_name = "services"
+  }
 }
 

rnd/infra/terraform/modules/iam/main.tf

@@ -0,0 +1,26 @@
+resource "google_service_account" "service_accounts" {
+  for_each     = var.service_accounts
+  account_id   = each.key
+  display_name = each.value.display_name
+  description  = each.value.description
+}
+
+# IAM policy binding for Workload Identity
+resource "google_service_account_iam_binding" "workload_identity_binding" {
+  for_each           = var.workload_identity_bindings
+  service_account_id = google_service_account.service_accounts[each.value.service_account_name].name
+  role               = "roles/iam.workloadIdentityUser"
+
+  members = [
+    "serviceAccount:${var.project_id}.svc.id.goog[${each.value.namespace}/${each.value.ksa_name}]"
+  ]
+}
+
+# Role bindings grouped by role
+resource "google_project_iam_binding" "role_bindings" {
+  for_each = var.role_bindings
+  project  = var.project_id
+  role     = each.key
+
+  members = each.value
+}

rnd/infra/terraform/modules/iam/outputs.tf

@@ -0,0 +1,4 @@
+output "service_account_emails" {
+  description = "The emails of the created service accounts"
+  value       = { for k, v in google_service_account.service_accounts : k => v.email }
+}

rnd/infra/terraform/modules/iam/variables.tf

@@ -0,0 +1,29 @@
+variable "project_id" {
+  description = "The ID of the project"
+  type        = string
+}
+
+variable "service_accounts" {
+  description = "Map of service accounts to create"
+  type = map(object({
+    display_name = string
+    description  = string
+  }))
+  default = {}
+}
+
+variable "workload_identity_bindings" {
+  description = "Map of Workload Identity bindings to create"
+  type = map(object({
+    service_account_name = string
+    namespace            = string
+    ksa_name             = string
+  }))
+  default = {}
+}
+
+variable "role_bindings" {
+  description = "Map of roles to list of members"
+  type        = map(list(string))
+  default     = {}
+}

rnd/infra/terraform/modules/networking/main.tf

@@ -8,5 +8,15 @@ resource "google_compute_subnetwork" "subnet" {
   ip_cidr_range = var.subnet_cidr
   region        = var.region
   network       = google_compute_network.vpc_network.self_link
+
+  secondary_ip_range {
+    range_name    = "pods"
+    ip_cidr_range = var.pods_ip_cidr_range
+  }
+
+  secondary_ip_range {
+    range_name    = "services"
+    ip_cidr_range = var.services_ip_cidr_range
+  }
 }
 

rnd/infra/terraform/modules/networking/variables.tf

@@ -18,4 +18,12 @@ variable "subnet_cidr" {
   description = "The CIDR range for the subnet"
 }
 
+variable "pods_ip_cidr_range" {
+  description = "The IP address range for pods"
+  default     = "10.1.0.0/16"
+}
 
+variable "services_ip_cidr_range" {
+  description = "The IP address range for services"
+  default     = "10.2.0.0/20"
+}

rnd/infra/terraform/modules/static_ip/main.tf

@@ -1,6 +1,5 @@
-resource "google_compute_address" "static_ip" {
+resource "google_compute_global_address" "static_ip" {
   count        = length(var.ip_names)
   name         = "${var.project_id}-${var.ip_names[count.index]}"
-  region       = var.region
   address_type = "EXTERNAL"
 }

rnd/infra/terraform/modules/static_ip/outputs.tf

@@ -1,9 +1,9 @@
 output "ip_addresses" {
   description = "Map of created static IP addresses"
-  value       = { for i, ip in google_compute_address.static_ip : var.ip_names[i] => ip.address }
+  value       = { for i, ip in google_compute_global_address.static_ip : var.ip_names[i] => ip.address }
 }
 
 output "ip_names" {
   description = "List of full names of the created static IP addresses"
-  value       = google_compute_address.static_ip[*].name
+  value       = google_compute_global_address.static_ip[*].name
 }

rnd/infra/terraform/variables.tf

@@ -74,3 +74,40 @@ variable "static_ip_names" {
   type        = list(string)
   default     = ["ip-1", "ip-2", "ip-3"]
 }
+
+variable "service_accounts" {
+  description = "Map of service accounts to create"
+  type = map(object({
+    display_name = string
+    description  = string
+  }))
+  default = {}
+}
+
+variable "workload_identity_bindings" {
+  description = "Map of Workload Identity bindings to create"
+  type = map(object({
+    service_account_name = string
+    namespace            = string
+    ksa_name             = string
+  }))
+  default = {}
+}
+
+variable "role_bindings" {
+  description = "Map of roles to list of members"
+  type        = map(list(string))
+  default     = {}
+}
+
+variable "pods_ip_cidr_range" {
+  description = "The IP address range for pods"
+  type        = string
+  default     = "10.1.0.0/16"
+}
+
+variable "services_ip_cidr_range" {
+  description = "The IP address range for services"
+  type        = string
+  default     = "10.2.0.0/20"
+}