Jeremy Adk Orchestrator

🎯 VERTEX AI AGENT ENGINE + ADK DEPLOYMENT ONLY

Expert Agent-to-Agent (A2A) protocol manager for communicating with Vertex AI Agent Development Kit (ADK) agents deployed on Agent Engine.

⚠️ Important: What This Plugin Is For

✅ THIS PLUGIN IS FOR:

• ADK agents deployed to Vertex AI Agent Engine (fully-managed runtime)
• A2A Protocol communication between Claude Code and ADK agents
• Multi-agent orchestration with ADK supervisory agents
• Python, Java, and Go ADK agents on Agent Engine
• Agent Engine features: Code Execution Sandbox, Memory Bank, Sessions

❌ THIS PLUGIN IS NOT FOR:

• LangChain agents (use LangSmith)
• LlamaIndex agents (not ADK compatible)
• Cloud Run deployments (use jeremy-genkit-terraform with --cloud-run)
• Self-hosted agent infrastructure
• Non-ADK agent frameworks

Overview

This plugin enables Claude Code to communicate with ADK agents deployed on Vertex AI Agent Engine using the standardized A2A (Agent-to-Agent) Protocol. It handles task submission, status checking, session management, and AgentCard discovery for building multi-agent systems.

Key Capabilities:

• AgentCard discovery and capability inspection
• Task submission with structured inputs
• Session management for Memory Bank persistence
• Status polling and result retrieval
• Streaming responses for long-running tasks
• Multi-agent orchestration with supervisory patterns

Installation

/plugin install jeremy-adk-orchestrator@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:
- roles/aiplatform.user              # Query Agent Engine resources
- roles/discoveryengine.admin        # Manage agents and sessions
- roles/logging.viewer               # Read agent logs
- roles/monitoring.viewer            # Access metrics

Required Python Packages

Install via pip:

# Core ADK SDK (required for agent development)
pip install google-adk>=1.15.1

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

# A2A Protocol SDK (for protocol-level communication)
pip install a2a-sdk>=0.3.4

# HTTP client for REST API calls
pip install requests>=2.31.0

# 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

All dependencies at once:

pip install --upgrade \
    'google-adk>=1.15.1' \
    'google-cloud-aiplatform[agent_engines]>=1.120.0' \
    'a2a-sdk>=0.3.4' \
    'requests>=2.31.0' \
    'google-cloud-logging>=3.10.0' \
    'google-cloud-monitoring>=2.21.0' \
    'google-cloud-trace>=1.13.0'

Agent Engine Management (Python SDK Only)

There is no gcloud CLI for Agent Engine. All management is done via the Python SDK:

import vertexai

client = vertexai.Client(project="YOUR_PROJECT_ID", location="us-central1")

# List all deployed agents (reasoning engines)
for agent in client.agent_engines.list():
    print(f"{agent.display_name}: {agent.resource_name}")

# Get a specific agent
agent = client.agent_engines.get(
    name="projects/YOUR_PROJECT/locations/us-central1/reasoningEngines/12345"
)

# Delete an agent
# client.agent_engines.delete(name=agent.resource_name)

Verify SDK Installation:

python3 -c "import vertexai; print('Vertex AI SDK ready')"
python3 -c "import google.adk; print(f'ADK SDK version: {google.adk.__version__}')"

ADK Agent Deployment Methods

This plugin works with ADK agents deployed via:

1. ADK CLI Deployment:

# Install ADK CLI
pip install google-adk

# Deploy agent to Agent Engine (interactive — prompts for project/location)
adk deploy cloud_run  # Deploy to Cloud Run
# Or deploy via the Python SDK (see method 2 below) for Agent Engine

1. Python SDK Deployment:

from google.adk.agents import Agent
import vertexai

# Define ADK agent
agent = Agent(
    name="my-adk-agent",
    model="gemini-2.5-flash",
    instruction="Production ADK agent for deployment tasks.",
    tools=[my_tool_function],
)

# Deploy to Agent Engine
client = vertexai.Client(project=PROJECT_ID, location=LOCATION)
remote_agent = client.agent_engines.create(
    agent_engine=agent,
    requirements=["google-adk>=1.15.1"],
    display_name="my-adk-agent",
)
…