Implementare e configurare l'agente Story

Task 1: Implementare lo Story Agent

Lo Story Agent è un agente Strands generato con --protocol=AG-UI nel Modulo 1, in modo che l’interfaccia utente possa ricevere lo streaming da esso tramite il protocollo Agent-User Interaction via CopilotKit. Utilizza il server MCP dell’inventario per gestire gli oggetti del giocatore e l’S3SessionManager integrato di Strands per persistere la cronologia delle conversazioni nel bucket delle sessioni che abbiamo fornito nel Modulo 2.

Implementazione dell’agente

Aggiorna i seguenti file in 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],
        )

Le modifiche sono:

• main.py aggiunge un session_manager_provider che crea un S3SessionManager per ogni thread_id quando deployato, e ricade su un FileSessionManager su disco sotto /tmp/strands-sessions quando eseguito con agent-dev (LOCAL_DEV=true). In deployment, il bucket S3 è lo stesso da cui legge il queryActions della Game API, così il browser può ricostruire le trascrizioni alla rivisitazione; localmente l’agente persiste le sessioni su disco e comunica con il server MCP locale, senza un deployment.
• agent.py rimuove lo strumento di esempio subtract e sostituisce il prompt di sistema con uno da dungeon-master che invita il primo messaggio dell’utente a dichiarare il nome del giocatore e il genere, e utilizza gli strumenti del server MCP dell’inventario.

Task 2: Testare il tuo Agent localmente

Compilare il codice

Per compilare il codice:

pnpm

pnpm build

yarn

yarn build

npm

npm run build

bun

bun build

Correzione errori di lint

Se incontri errori di linting, esegui il seguente comando per correggerli automaticamente.

pnpm

pnpm lint

yarn

yarn lint

npm

npm run lint

bun

bun lint

Chattare con il tuo Agent

Il target generato agent-chat apre un REPL interattivo contro il tuo agente. Viene eseguito in modo autonomo e si connette al tuo agente in esecuzione locale, quindi prima avvia il server locale dell’agente in un terminale:

pnpm

pnpm nx agent-dev story

yarn

yarn nx agent-dev story

npm

npx nx agent-dev story

bun

bunx nx agent-dev story

Poi, in un secondo terminale, avvia la 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

Il tuo primo messaggio dovrebbe dire all’agente il nome del tuo eroe e il genere (per esempio: My name is Alice. Start my zombie adventure.) e la storia verrà trasmessa in streaming.

Credenziali AWS richieste

Sebbene l’agente venga eseguito localmente, invoca Amazon Bedrock per l’LLM. Avrai bisogno di credenziali AWS nel tuo ambiente con accesso al modello predefinito di Strands. Consulta la documentazione del provider di modelli Strands per i dettagli.

Complimenti. Hai creato e testato il tuo primo Strands Agent localmente! 🎉🎉🎉