Entorno y sistema de archivos

response = client.invoke_agent_runtime_command(
    agentRuntimeArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    body={"command": "ls -la /workspace"},
)

for event in response["stream"]:
    chunk = event.get("chunk", {})
    if "contentDelta" in chunk:
        delta = chunk["contentDelta"]
        if "stdout" in delta:
            print(delta["stdout"], end="", flush=True)
        if "stderr" in delta:
            print(delta["stderr"], end="", flush=True)
    elif "contentStop" in chunk:
        print(f"\n[exit code: {chunk['contentStop']['exitCode']}]")

# Install dependencies before the agent starts
agentcore invoke --exec --harness my-agent --session-id "$(uuidgen)" \
  "pip install pandas matplotlib"

# After the agent finishes, inspect what it created
agentcore invoke --exec --harness my-agent --session-id "$(uuidgen)" \
  "ls -la /tmp && cat /tmp/results.csv"

En la interfaz gráfica de usuario, pulse ! para entrar en el modo exec y ejecutar los comandos en línea.

aws bedrock-agentcore-control create-harness \
  --harness-name "CodingAgent" \
  --execution-role-arn "arn:aws:iam::123456789012:role/MyHarnessRole" \
  --environment-artifact '{"containerConfiguration": {"containerUri": "123456789012.dkr.ecr.us-west-2.amazonaws.com/my-dev-env:latest"}}' \
  --system-prompt '[{"text": "You are an expert TypeScript developer."}]'

La función de ejecución necesita permisos de extracción de ECR. Consulte la política de funciones de ejecución para obtener más información.

Arregla un arnés con un Dockerfile:

agentcore create --name coding-agent --container ./Dockerfile
agentcore deploy

En el momento de la implementación, la CLI crea la imagen, la envía al ECR y la conecta al arnés.

O haga referencia a una imagen prediseñada:

agentcore create --name node-agent \
  --container public.ecr.aws/docker/library/node:slim
agentcore deploy

aws bedrock-agentcore-control create-harness \
  --harness-name "MyHarness" \
  --execution-role-arn "arn:aws:iam::123456789012:role/MyHarnessRole" \
  --environment-variables '{"MY_API_URL": "https://api.example.com", "LOG_LEVEL": "debug"}'

Defina las variables de entorno enharness.json:

{
  "environmentVariables": {
    "MY_API_URL": "https://api.example.com",
    "LOG_LEVEL": "debug"
  }
}

Ejecute agentcore deploy para aplicar.

Ejecute agentcore en un directorio de proyecto para abrir la TUI, seleccione agregar y, a continuación, elija Harness. El asistente le guiará por el entorno de ejecución y, en la configuración avanzada, por el sistema de archivos persistente.

Confirme el asistente y, a continuación, ejecútelo agentcore deploy para aplicarlo.

aws bedrock-agentcore-control update-harness \
  --harness-id "MyHarness-UuFdkQoXSL" \
  --environment '{"agentCoreRuntimeEnvironment": {"filesystemConfigurations": [{"sessionStorage": {"mountPath": "/mnt/data/"}}]}}'

# At create time
agentcore create --name myagent --session-storage-mount-path /mnt/data/

# Or add to an existing harness
agentcore add harness --name my-agent --session-storage /mnt/data/
agentcore deploy

aws bedrock-agentcore-control create-harness \
  --harness-name "SharedToolsAgent" \
  --execution-role-arn "arn:aws:iam::123456789012:role/MyHarnessRole" \
  --environment '{
    "agentCoreRuntimeEnvironment": {
      "networkConfiguration": {
        "networkMode": "VPC",
        "networkModeConfig": {
          "subnets": ["subnet-abc123", "subnet-def456"],
          "securityGroups": ["sg-abc123"]
        }
      },
      "filesystemConfigurations": [
        {
          "efsAccessPoint": {
            "accessPointArn": "arn:aws:elasticfilesystem:us-west-2:123456789012:access-point/fsap-0123456789abcdef0",
            "mountPath": "/mnt/efs"
          }
        }
      ]
    }
  }'

Adjunte un punto de acceso EFS con --efs-access-point as<accessPointArn>:<mountPath>. EFS requiere el modo de red VPC:

agentcore add harness --name shared-tools-agent \
  --network-mode VPC \
  --subnets subnet-abc123,subnet-def456 \
  --security-groups sg-abc123 \
  --efs-access-point arn:aws:elasticfilesystem:us-west-2:123456789012:access-point/fsap-0123456789abcdef0:/mnt/efs
agentcore deploy

aws bedrock-agentcore-control create-harness \
  --harness-name "DataAgent" \
  --execution-role-arn "arn:aws:iam::123456789012:role/MyHarnessRole" \
  --environment '{
    "agentCoreRuntimeEnvironment": {
      "networkConfiguration": {
        "networkMode": "VPC",
        "networkModeConfig": {
          "subnets": ["subnet-abc123", "subnet-def456"],
          "securityGroups": ["sg-abc123"]
        }
      },
      "filesystemConfigurations": [
        {
          "s3FilesAccessPoint": {
            "accessPointArn": "arn:aws:s3files:us-west-2:123456789012:file-system/fs-0123456789abcdef0/access-point/fsap-0123456789abcdef0",
            "mountPath": "/mnt/s3data"
          }
        }
      ]
    }
  }'

Adjunte un punto de acceso de S3 Files con un as--s3-access-point. <accessPointArn>:<mountPath> S3 Files requiere el modo de red VPC:

agentcore add harness --name data-agent \
  --network-mode VPC \
  --subnets subnet-abc123,subnet-def456 \
  --security-groups sg-abc123 \
  --s3-access-point arn:aws:s3files:us-west-2:123456789012:file-system/fs-0123456789abcdef0/access-point/fsap-0123456789abcdef0:/mnt/s3data
agentcore deploy