Jeremy Adk Terraform

🎯 VERTEX AI AGENT ENGINE INFRASTRUCTURE ONLY

Terraform infrastructure-as-code specialist for deploying ADK agents to Vertex AI Agent Engine with complete observability, security, and production-ready configurations.

⚠️ Important: What This Plugin Is For

✅ THIS PLUGIN IS FOR:

• Vertex AI Agent Engine infrastructure (fully-managed runtime)
• ADK agents Terraform deployment (google_vertex_ai_reasoning_engine)
• Agent Engine features: Code Execution Sandbox, Memory Bank, VPC-SC, IAM
• Observability infrastructure: Cloud Monitoring dashboards, alert policies, BigQuery connectors
• Production ADK deployments with security hardening

❌ THIS PLUGIN IS NOT FOR:

• Cloud Run deployments (use jeremy-genkit-terraform)
• LangChain/LlamaIndex on other platforms
• Self-hosted agent infrastructure
• Non-Agent Engine Terraform

Overview

This plugin provides Terraform modules and configurations for deploying ADK agents to Vertex AI Agent Engine with production-ready infrastructure including VPC Service Controls, IAM least privilege, Code Execution Sandbox configuration, Memory Bank setup, observability dashboards, and BigQuery analytics connectors.

Key Infrastructure Components:

• google_vertex_ai_reasoning_engine resource for Agent Engine
• VPC Service Controls perimeter
• IAM roles and service accounts
• Cloud Monitoring dashboards and alerts
• BigQuery datasets for agent analytics
• Cloud Storage buckets for artifacts
• Secret Manager for credentials

Installation

/plugin install jeremy-adk-terraform@claude-code-plugins-plus

Prerequisites & Dependencies

Required Tools

1. Terraform:

# Install Terraform 1.5+
wget https://releases.hashicorp.com/terraform/1.6.0/terraform_1.6.0_linux_amd64.zip
unzip terraform_1.6.0_linux_amd64.zip
sudo mv terraform /usr/local/bin/

# Verify
terraform version  # Should show 1.5.0+

2. gcloud CLI:

# Install gcloud
curl https://sdk.cloud.google.com | bash
exec -l $SHELL

# Update to latest
gcloud components update

# Install alpha commands (for Agent Engine)
gcloud components install alpha

# Authenticate
gcloud auth application-default login

3. Terraform Google Provider:

terraform {
  required_version = ">= 1.5.0"

  required_providers {
    google = {
      source  = "hashicorp/google"
      version = "~> 5.0"
    }
    google-beta = {
      source  = "hashicorp/google-beta"
      version = "~> 5.0"
    }
  }
}

Required Google Cloud APIs

# Enable all required APIs
gcloud services enable \
    aiplatform.googleapis.com \
    discoveryengine.googleapis.com \
    logging.googleapis.com \
    monitoring.googleapis.com \
    cloudtrace.googleapis.com \
    bigquery.googleapis.com \
    storage.googleapis.com \
    secretmanager.googleapis.com \
    compute.googleapis.com \
    servicenetworking.googleapis.com \
    --project=YOUR_PROJECT_ID

Required IAM Permissions

# Service account for Terraform needs:
- roles/aiplatform.admin              # Deploy Agent Engine resources
- roles/iam.serviceAccountAdmin       # Create service accounts
- roles/resourcemanager.projectIamAdmin  # Manage IAM bindings
- roles/compute.networkAdmin          # VPC configuration
- roles/monitoring.admin              # Create dashboards/alerts
- roles/bigquery.admin                # Create datasets
- roles/storage.admin                 # Create buckets

Features

✅ Agent Engine Deployment: google_vertex_ai_reasoning_engine with ADK framework ✅ Code Execution Sandbox: Secure isolation, state persistence (1-14 days TTL) ✅ Memory Bank: Firestore-backed persistent memory with retention policies ✅ VPC Service Controls: Perimeter security for Agent Engine ✅ IAM Least Privilege: Service accounts with minimal permissions ✅ Observability Infrastructure: Dashboards, alerts, SLOs, token tracking ✅ BigQuery Analytics: Automated log export and analytics datasets ✅ Cloud Storage: Artifact storage with lifecycle policies ✅ Secret Management: API keys and credentials in Secret Manager ✅ Multi-Region: Agent Engine deployments in multiple regions

Quick Start

Natural Language Activation

Simply mention what you need:

"Create Terraform for ADK agent deployment to Agent Engine"
"Provision Agent Engine infrastructure with VPC-SC"
"Deploy ADK agent with Code Execution and Memory Bank"
"Set up observability infrastructure for Agent Engine"
"Create multi-region Agent Engine deployment"

The skill auto-activates and generates production-ready Terraform.

Terraform Module Structure

Core Agent Engine Resource

# main.tf
resource "google_vertex_ai_reasoning_engine" "adk_agent" {
  display_name = var.agent_name
  region       = var.region
  project      = var.project_id

  spec {
    # REQUIRED: Specify ADK framework
    agent_framework = "google-adk"

    # Agent package (ADK agent code)
    package_spec {
      pickle_object_gcs_uri    = google_storage_bucket_object.agent_package.self_link
      python_version           = "3.12"
      requirements_gcs_uri     = google_storage_bucket_object.requirements.self_link
    }

    # Runtime configuration
…