Implementar y configurar el agente Story

Tarea 1: Implementar el Agente Story

El Agente Story es un agente de Strands generado con --protocol=AG-UI en el Módulo 1, para que la interfaz de usuario pueda transmitir desde él a través del protocolo Agent-User Interaction mediante CopilotKit. Utiliza el Servidor MCP de Inventario para gestionar los objetos del jugador, y el S3SessionManager integrado de Strands para persistir el historial de conversación en el bucket de sesiones que aprovisionamos en el Módulo 2.

Implementación del agente

Actualiza los siguientes archivos en packages/story/dungeon_adventure_story/agent:

main.py

+

import logging
import os
import uuid
from functools import cache
from typing import Any, cast

from ag_ui.core import RunAgentInput
from ag_ui_strands import StrandsAgent, StrandsAgentConfig, create_strands_app
from aws_lambda_powertools.utilities import parameters
from dungeon_adventure_agent_connection import session_id_context
from fastapi import Request
from starlette.middleware.base import BaseHTTPMiddleware
from strands.session import FileSessionManager, S3SessionManager, SessionManager

from .agent import get_agent

logging.basicConfig(level=logging.INFO)

SESSION_ID_HEADER = "x-amzn-bedrock-agentcore-runtime-session-id"


@cache
def _resolve_sessions_bucket() -> str:
    """Read the conversation-history bucket name from runtime config.

    Resolved lazily (and memoised) so `fastapi dev` can import this module
    before ``RUNTIME_CONFIG_APP_ID`` is in the environment.
    """
    application = os.environ.get("RUNTIME_CONFIG_APP_ID")
    if not application:
        raise RuntimeError("RUNTIME_CONFIG_APP_ID is not set — cannot resolve the StorySessions bucket.")
    provider = parameters.AppConfigProvider(environment="default", application=application)
    buckets = cast(dict[str, Any], provider.get("buckets", transform="json"))
    return buckets["StorySessions"]["bucketName"]


def _session_manager_provider(input_data: RunAgentInput) -> SessionManager:
    """Create a session manager keyed by the AG-UI thread_id.

    - In AgentCore (and `agent-serve`), persist to the shared ``StorySessions``
      S3 bucket — the same bucket the Game API reads from to rebuild
      conversation history on revisit.
    - In `agent-dev` (`LOCAL_DEV=true`), persist to a temp
      directory so the agent can run fully offline against the local MCP
      server without any AWS calls.
    """
    session_id = input_data.thread_id or "default"
    if os.environ.get("LOCAL_DEV") == "true":
        return FileSessionManager(session_id=session_id, storage_dir="/tmp/strands-sessions")
    return S3SessionManager(session_id=session_id, bucket=_resolve_sessions_bucket())


# The template Agent is cloned per thread_id by ``StrandsAgent`` — we plug in
# a ``session_manager_provider`` so each thread gets its own session manager
# and conversation history is replayed on subsequent turns and survives agent
# restarts.
_agent_ctx = get_agent()
_agent = _agent_ctx.__enter__()

agui_agent = StrandsAgent(
    agent=_agent,
    name="StoryAgent",
    description="A Strands Agent exposed via the AG-UI protocol.",
    config=StrandsAgentConfig(session_manager_provider=_session_manager_provider),
)


class _SessionIdMiddleware(BaseHTTPMiddleware):
    """Bind the session ID for this request so downstream MCP / A2A clients forward it on outbound calls."""

    async def dispatch(self, request: Request, call_next):
        session_id = request.headers.get(SESSION_ID_HEADER) or str(uuid.uuid4())
        with session_id_context(session_id):
            return await call_next(request)


app = create_strands_app(agui_agent, path="/invocations")
app.add_middleware(_SessionIdMiddleware)

+-

import logging
import os
import uuid
from functools import cache
from typing import Any, cast

from ag_ui_strands import StrandsAgent, create_strands_app
from ag_ui.core import RunAgentInput
from ag_ui_strands import StrandsAgent, StrandsAgentConfig, create_strands_app
from aws_lambda_powertools.utilities import parameters
from dungeon_adventure_agent_connection import session_id_context
from fastapi import Request
from starlette.middleware.base import BaseHTTPMiddleware
from strands.session import FileSessionManager, S3SessionManager, SessionManager

from .agent import get_agent

logging.basicConfig(level=logging.INFO)

SESSION_ID_HEADER = "x-amzn-bedrock-agentcore-runtime-session-id"

# Create AG-UI agent wrapper

@cache
def _resolve_sessions_bucket() -> str:
    """Read the conversation-history bucket name from runtime config.

    Resolved lazily (and memoised) so `fastapi dev` can import this module
    before ``RUNTIME_CONFIG_APP_ID`` is in the environment.
    """
    application = os.environ.get("RUNTIME_CONFIG_APP_ID")
    if not application:
        raise RuntimeError("RUNTIME_CONFIG_APP_ID is not set — cannot resolve the StorySessions bucket.")
    provider = parameters.AppConfigProvider(environment="default", application=application)
    buckets = cast(dict[str, Any], provider.get("buckets", transform="json"))
    return buckets["StorySessions"]["bucketName"]


def _session_manager_provider(input_data: RunAgentInput) -> SessionManager:
    """Create a session manager keyed by the AG-UI thread_id.

    - In AgentCore (and `agent-serve`), persist to the shared ``StorySessions``
      S3 bucket — the same bucket the Game API reads from to rebuild
      conversation history on revisit.
    - In `agent-dev` (`LOCAL_DEV=true`), persist to a temp
      directory so the agent can run fully offline against the local MCP
      server without any AWS calls.
    """
    session_id = input_data.thread_id or "default"
    if os.environ.get("LOCAL_DEV") == "true":
        return FileSessionManager(session_id=session_id, storage_dir="/tmp/strands-sessions")
    return S3SessionManager(session_id=session_id, bucket=_resolve_sessions_bucket())


# The template Agent is cloned per thread_id by ``StrandsAgent`` — we plug in
# a ``session_manager_provider`` so each thread gets its own session manager
# and conversation history is replayed on subsequent turns and survives agent
# restarts.
_agent_ctx = get_agent()
_agent = _agent_ctx.__enter__()

agui_agent = StrandsAgent(
    agent=_agent,
    name="StoryAgent",
    description="A Strands Agent exposed via the AG-UI protocol.",
    config=StrandsAgentConfig(session_manager_provider=_session_manager_provider),
)


class _SessionIdMiddleware(BaseHTTPMiddleware):
    """Bind the session ID for this request so downstream MCP / A2A clients forward it on outbound calls."""

    async def dispatch(self, request: Request, call_next):
        session_id = request.headers.get(SESSION_ID_HEADER) or str(uuid.uuid4())
        with session_id_context(session_id):
            return await call_next(request)


# Create FastAPI app with AG-UI endpoint and health check
app = create_strands_app(agui_agent, path="/invocations")
app.add_middleware(_SessionIdMiddleware)

agent.py

+

from contextlib import contextmanager

from dungeon_adventure_agent_connection import InventoryMcpServerClientStrands, log_model_errors
from strands import Agent


@contextmanager
def get_agent():
    inventory_mcp_server = InventoryMcpServerClientStrands.create()
    with (
        inventory_mcp_server,
    ):
        yield Agent(
            system_prompt="""
You are running a text adventure game for a lone adventurer. When a new story
begins, the first user message will tell you the player's name and the genre
(one of 'medieval', 'zombie', 'superhero'). Greet the player by name, set the
scene in the chosen genre, and populate their inventory with a few starting
items. On subsequent turns, advance the story in response to the player's
actions and keep item state in sync with the narrative.
Use the tools to manage the player's inventory as items are obtained or lost.
Item names in the inventory must be Title Case — match them exactly.
Only use list-inventory-items if you are unsure of the exact item name before modifying it.
IMPORTANT: Only call ONE tool per response turn. Never batch multiple tool calls in a single turn.
Ensure you specify a suitable emoji when adding items if available.
Items should be a key part of the narrative.
Keep responses under 100 words.
""",
            tools=[*inventory_mcp_server.list_tools_sync()],
            hooks=[log_model_errors],
        )

+-

from contextlib import contextmanager

from dungeon_adventure_agent_connection import InventoryMcpServerClientStrands, log_model_errors
from strands import Agent, tool
from strands_tools import current_time
from strands import Agent


@tool
def subtract(a: int, b: int) -> int:
    return a - b


@contextmanager
def get_agent():
    inventory_mcp_server = InventoryMcpServerClientStrands.create()
    with (
        inventory_mcp_server,
    ):
        yield Agent(
            name="StoryAgent",
            description="StoryAgent Strands Agent",
            system_prompt="""
You are a mathematical wizard.
Use your tools for mathematical tasks.
Refer to tools as your 'spellbook'.
You are running a text adventure game for a lone adventurer. When a new story
begins, the first user message will tell you the player's name and the genre
(one of 'medieval', 'zombie', 'superhero'). Greet the player by name, set the
scene in the chosen genre, and populate their inventory with a few starting
items. On subsequent turns, advance the story in response to the player's
actions and keep item state in sync with the narrative.
Use the tools to manage the player's inventory as items are obtained or lost.
Item names in the inventory must be Title Case — match them exactly.
Only use list-inventory-items if you are unsure of the exact item name before modifying it.
IMPORTANT: Only call ONE tool per response turn. Never batch multiple tool calls in a single turn.
Ensure you specify a suitable emoji when adding items if available.
Items should be a key part of the narrative.
Keep responses under 100 words.
""",
            tools=[subtract, current_time, *inventory_mcp_server.list_tools_sync()],
            tools=[*inventory_mcp_server.list_tools_sync()],
            hooks=[log_model_errors],
        )

Los cambios son:

• main.py añade un session_manager_provider que crea un S3SessionManager por thread_id cuando se despliega, y recurre a un FileSessionManager en disco bajo /tmp/strands-sessions cuando se ejecuta bajo agent-serve-local (SERVE_LOCAL=true). En despliegue, el bucket de S3 es el mismo del que lee queryActions de la API del juego, por lo que el navegador puede reconstruir las transcripciones al volver a visitar; localmente el agente persiste las sesiones en disco y se comunica con el servidor MCP local, sin necesidad de un despliegue.
• agent.py elimina la herramienta de ejemplo subtract y cambia el prompt del sistema por uno de maestro de mazmorras que invita al primer mensaje del usuario a indicar el nombre del jugador y el género, y utiliza las herramientas del Servidor MCP de Inventario.

Tarea 2: Probar tu Agente localmente

Construir el código

Para construir el código:

pnpm

pnpm build

yarn

yarn build

npm

npm run build

bun

bun build

Corregir errores de Lint

Si encuentras algún error de lint, ejecuta el siguiente comando para corregirlos automáticamente.

pnpm

pnpm lint

yarn

yarn lint

npm

npm run lint

bun

bun lint

Chatear con tu Agente

El target generado agent-chat abre un REPL interactivo contra tu agente. Se ejecuta de forma independiente y se conecta a tu agente en ejecución local, así que primero inicia el servidor local del agente en una terminal:

pnpm

pnpm nx agent-dev story

yarn

yarn nx agent-dev story

npm

npx nx agent-dev story

bun

bunx nx agent-dev story

Luego, en una segunda terminal, inicia el chat:

pnpm

pnpm nx agent-chat story

yarn

yarn nx agent-chat story

npm

npx nx agent-chat story

bun

bunx nx agent-chat story

Tu primer mensaje debe indicarle al agente el nombre de tu héroe y el género (por ejemplo: Mi nombre es Alice. Comienza mi aventura zombie.) y la historia se transmitirá de vuelta.

Credenciales de AWS requeridas

Aunque el agente se ejecuta localmente, invoca Amazon Bedrock para el LLM. Necesitarás credenciales de AWS en tu entorno con acceso al modelo predeterminado de Strands. Consulta la documentación del proveedor de modelos de Strands para más detalles.

¡Felicitaciones! ¡Has construido y probado tu primer Agente Strands localmente! 🎉🎉🎉