nmpAgents/nmpOnboardingAgent/README.md

# Agentes NMP en Bedrock AgentCore

Este proyecto contiene los runtimes `NmpOnboardingAgent` y
`MyAgentAwsInfrastructureAgent`, los harnesses de infraestructura y el proxy
Lambda para invocar el agente de onboarding.

## Estructura del código

| Directorio | Responsabilidad |
| --- | --- |
| `app/NmpOnboardingAgent/` | Runtime de onboarding: entrada, modelo, cliente MCP y memoria |
| `app/MyAgentAwsInfrastructureAgent/` | Runtime de consulta de infraestructura AWS |
| `harnesses/` | `AwsInfraHarness` y `AwsInfraRestricted`, con sus configuraciones y prompts |
| `lambdas/agentcore_proxy/` | Proxy HTTP y documentación de empaquetado |
| `schemas/tools/` | Contratos MCP de clientes, KYC, PLD, documentos e infraestructura |
| `infra/iam/` | Políticas IAM y documentos de confianza |
| `examples/proxy/` | Solicitud y respuesta históricas del proxy |
| `artifacts/legacy/` | ZIP original conservado como referencia |
| `agentcore/` | Configuración declarativa, estado local y CDK generado |

Cada runtime conserva sus dependencias e imports dentro de su propio directorio
para que el empaquetado `CodeZip` sea independiente. Las rutas `toolSchemaFile`,
`codeLocation` y las entradas de `harnesses` en `agentcore/agentcore.json` son
relativas a la raíz de este proyecto. Los nombres de recursos AWS no cambian.

El código de la Lambda de infraestructura está en el componente hermano
[`nmpAWSInfraestructure`](../nmpAWSInfraestructure/README.md).

### Validación y uso

Los archivos `app/AwsInfraHarness/harness.json` y
`app/AwsInfraRestricted/harness.json` son copias de compatibilidad para el CLI
que busca los harnesses en `app/<nombre>/` durante la validación.
La configuración de CDK sigue apuntando a `harnesses/`; si se modifica un
`harness.json`, mantener su copia de `app/` idéntica antes de desplegar.

Ejecutar desde este directorio, con AgentCore CLI instalado:

```powershell
agentcore validate
agentcore dev
```

Para generar el ZIP del proxy, seguir
[`lambdas/agentcore_proxy/README.md`](lambdas/agentcore_proxy/README.md).
Los archivos de `artifacts/legacy/` y las respuestas de `examples/` son históricos.

## Referencia de AgentCore CLI

This project was created with the [AgentCore CLI](https://github.com/aws/agentcore-cli).

## Project Structure

```
my-project/
├── AGENTS.md               # AI coding assistant context
├── agentcore/
│   ├── agentcore.json      # Project config (agents, memories, credentials, gateways, evaluators)
│   ├── aws-targets.json    # Deployment targets (account + region)
│   ├── .env.local          # Secrets — API keys (gitignored)
│   ├── .llm-context/       # TypeScript type definitions for AI assistants
│   │   ├── agentcore.ts    # AgentCoreProjectSpec types
│   │   └── aws-targets.ts  # Deployment target types
│   └── cdk/                # CDK infrastructure (@aws/agentcore-cdk)
├── app/                    # Agent runtime application code
├── harnesses/              # Declarative harness configurations
├── lambdas/                # HTTP proxy Lambda
├── schemas/tools/          # Gateway tool contracts
├── infra/iam/              # IAM policies and trust documents
├── examples/               # Historical request/response examples
├── artifacts/legacy/       # Original ZIP packages
└── evaluators/             # Custom evaluator code (if any)
```

## Getting Started

### Prerequisites

- **Node.js** 20.x or later
- **Python 3.10+** and **uv** for Python agents ([install uv](https://docs.astral.sh/uv/getting-started/installation/))
- **AWS credentials** configured (`aws configure` or environment variables)
- **Docker** (only for Container build agents)

### Development

Run your agent locally:

```bash
agentcore dev
```

### Validate Invocation Input

Validate runtime invocation payloads before forwarding them to an agent framework. Keep user prompts typed as strings
and pass only prompt text to the agent.

### Deployment

Deploy to AWS:

```bash
agentcore deploy
```

## Commands

| Command | Description |
| --- | --- |
| `agentcore create` | Create a new AgentCore project |
| `agentcore add` | Add resources (agent, memory, credential, gateway, evaluator, policy) |
| `agentcore remove` | Remove resources |
| `agentcore dev` | Run agent locally with hot-reload |
| `agentcore deploy` | Deploy to AWS via CDK |
| `agentcore status` | Show deployment status |
| `agentcore invoke` | Invoke agent (local or deployed) |
| `agentcore logs` | View agent logs |
| `agentcore traces` | View agent traces |
| `agentcore eval` | Run evaluations |
| `agentcore package` | Package agent artifacts |
| `agentcore validate` | Validate configuration |
| `agentcore pause` | Pause a deployed agent |
| `agentcore resume` | Resume a paused agent |
| `agentcore fetch` | Fetch remote resource definitions |
| `agentcore import` | Import existing resources |
| `agentcore update` | Check for CLI updates |

## Configuration

Edit the JSON files in `agentcore/` to configure your project. See `agentcore/.llm-context/` for type definitions and validation constraints.

The project uses a **flat resource model** — agents, memories, credentials, gateways, evaluators, and policies are top-level arrays in `agentcore.json`. Resources are independent; agents discover memories and credentials at runtime via environment variables or SDK calls.

## Resources

| Resource | Purpose |
| --- | --- |
| Agent (runtime) | HTTP, MCP, or A2A agent deployed to AgentCore Runtime |
| Memory | Persistent context storage with configurable strategies |
| Credential | API key or OAuth credential providers |
| Gateway | MCP gateway that routes tool calls to targets |
| Gateway Target | Tool implementation (Lambda, MCP server, OpenAPI, Smithy, API Gateway) |
| Evaluator | Custom LLM-as-a-Judge or code-based evaluation |
| Online Eval Config | Continuous evaluation pipeline for deployed agents |
| Policy | Cedar authorization policies for gateway tools |

### Agent Types

- **Template agents**: Created from framework templates (Strands, LangChain/LangGraph, GoogleADK, OpenAI Agents, Autogen)
- **BYO agents**: Bring your own code with `agentcore add agent --type byo`
- **Import agents**: Import existing Bedrock agents with `agentcore import`

### Build Types

- **CodeZip**: Python source packaged as a zip and deployed directly to AgentCore Runtime
- **Container**: Docker image built via CodeBuild (ARM64), pushed to ECR, and deployed to AgentCore Runtime

## Documentation

- [AgentCore CLI](https://github.com/aws/agentcore-cli)
- [AgentCore CDK Constructs](https://github.com/aws/agentcore-l3-cdk-constructs)
- [Amazon Bedrock AgentCore](https://aws.amazon.com/bedrock/agentcore/)