Jeremy Vertex Engine

🎯 VERTEX AI AGENT ENGINE DEPLOYMENT ONLY

Expert inspector and orchestrator for Vertex AI Agent Engine - Google Cloud's fully-managed, serverless agent runtime platform.

⚠️ Important: What This Plugin Is For

✅ THIS PLUGIN IS FOR:

• Vertex AI Agent Engine deployments (fully-managed runtime)
• ADK (Agent Development Kit) agents deployed to Agent Engine
• Reasoning Engine API resources (google_vertex_ai_reasoning_engine)
• Agent Engine features: Memory Bank, Code Execution Sandbox, Sessions, A2A Protocol

❌ THIS PLUGIN IS NOT FOR:

• Cloud Run deployments (use jeremy-genkit-terraform or jeremy-adk-terraform with --cloud-run flag)
• LangChain/LlamaIndex on other platforms
• Self-hosted agent infrastructure
• Cloud Functions or other serverless platforms

Overview

This plugin provides comprehensive inspection and validation capabilities for agents deployed to the Vertex AI Agent Engine managed runtime. It acts as a quality assurance layer ensuring agents are properly configured, secure, performant, and production-ready on Google's fully-managed agent infrastructure.

Installation

/plugin install jeremy-vertex-engine@claude-code-plugins-plus

Prerequisites & Dependencies

Required Google Cloud Setup

1. Google Cloud Project with APIs Enabled:

# Enable required APIs
gcloud services enable aiplatform.googleapis.com \
    discoveryengine.googleapis.com \
    logging.googleapis.com \
    monitoring.googleapis.com \
    cloudtrace.googleapis.com \
    --project=YOUR_PROJECT_ID

2. Authentication:

# Application Default Credentials
gcloud auth application-default login

# Or use service account
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"

3. Required IAM Permissions:

# Minimum required roles for inspection:
- roles/aiplatform.user              # Query Agent Engine resources
- roles/discoveryengine.viewer       # View agent configurations
- roles/logging.viewer               # Read agent logs
- roles/monitoring.viewer            # Access metrics
- roles/cloudtrace.user              # View trace data

Required Python Packages

Install via pip:

# Core Vertex AI SDK (with Agent Engine support)
pip install google-cloud-aiplatform[agent_engines]>=1.120.0

# ADK SDK (if building ADK agents)
pip install google-adk>=1.15.1

# Observability & Monitoring
pip install google-cloud-logging>=3.10.0
pip install google-cloud-monitoring>=2.21.0
pip install google-cloud-trace>=1.13.0

# Optional: A2A Protocol SDK
pip install a2a-sdk>=0.3.4

All dependencies at once:

pip install --upgrade \
    'google-cloud-aiplatform[agent_engines]>=1.120.0' \
    'google-adk>=1.15.1' \
    'google-cloud-logging>=3.10.0' \
    'google-cloud-monitoring>=2.21.0' \
    'google-cloud-trace>=1.13.0' \
    'a2a-sdk>=0.3.4'

Required gcloud CLI Tools

The gcloud CLI is used for IAM policy queries, Cloud Monitoring, and Cloud Logging -- not for Agent Engine CRUD operations. There is no gcloud ai agents, gcloud ai reasoning-engines, or gcloud alpha ai agent-engines CLI surface. All Agent Engine operations use the Python SDK.

Install gcloud CLI:

# Install gcloud (if not already installed)
curl https://sdk.cloud.google.com | bash
exec -l $SHELL

# Update to latest version
gcloud components update

Verify Installation:

gcloud --version
# Should show: Google Cloud SDK 450.0.0+ (or higher)

# Test Agent Engine access via Python SDK
python3 -c "
import vertexai
client = vertexai.Client(project='YOUR_PROJECT_ID', location='us-central1')
for engine in client.agent_engines.list():
    print(engine.name, engine.display_name)
"

Vertex AI Agent Engine Requirements

This plugin works with agents deployed via:

1. ADK Deployment to Agent Engine:

import vertexai
from google.adk.agents import Agent

client = vertexai.Client(project=PROJECT_ID, location=LOCATION)

# Define an ADK agent
agent = Agent(name="my-adk-agent", model="gemini-2.5-flash")

# Deploy ADK agent to Agent Engine
agent_engine = client.agent_engines.create(
    agent=agent,
    config={"display_name": "my-adk-agent"},
)

1. Terraform Deployment:

resource "google_vertex_ai_reasoning_engine" "agent" {
  display_name = "my-agent"
  region       = "us-central1"

  spec {
    agent_framework = "google-adk"  # ← ADK agents
    # OR omit for custom agents

    package_spec {
      pickle_object_gcs_uri    = "gs://bucket/agent.pkl"
      python_version           = "3.12"
      requirements_gcs_uri     = "gs://bucket/requirements.txt"
    }
  }
}

1. Direct SDK Deployment:

# Custom agent template (NOT LangChain)
from vertexai.preview.reasoning_engines import ReasoningEngine

agent = ReasoningEngine.create(
    my_agent_instance,
    requirements=["google-cloud-aiplatform[agent_engines]>=1.120.0"],
    display_name="custom-agent"
)