实现和配置 Story 代理

任务 1：实现 Story 代理

Story 代理是一个在模块 1中使用 --protocol=AG-UI 生成的 Strands 代理，因此 UI 可以通过 CopilotKit 使用 Agent-User Interaction 协议从中进行流式传输。它使用 Inventory MCP Server 来管理玩家的物品，并使用 Strands 内置的 S3SessionManager 将对话历史持久化到我们在模块 2 中配置的会话存储桶中。

代理实现

更新 packages/story/dungeon_adventure_story/agent 中的以下文件：

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],
        )

更改内容如下：

• main.py 添加了一个 session_manager_provider，在部署时为每个 thread_id 创建一个 S3SessionManager，并在 agent-dev 下运行时（LOCAL_DEV=true）回退到 /tmp/strands-sessions 下的磁盘 FileSessionManager。在部署时，S3 存储桶与 Game API 的 queryActions 读取的存储桶相同，因此浏览器可以在重新访问时重建记录；在本地，代理将会话持久化到磁盘并与本地 MCP 服务器通信，无需部署。
• agent.py 删除了示例 subtract 工具，并将系统提示替换为地牢主持人提示，邀请第一条用户消息说明玩家的名字和类型，并使用 Inventory MCP Server 的工具。

任务 2：在本地测试您的代理

构建代码

要构建代码：

pnpm

pnpm build

yarn

yarn build

npm

npm run build

bun

bun build

修复 Lint 错误

如果遇到任何 lint 错误，请运行以下命令自动修复它们。

pnpm

pnpm lint

yarn

yarn lint

npm

npm run lint

bun

bun lint

与您的代理聊天

生成的 agent-chat 目标会针对您的代理打开一个交互式 REPL。它独立运行并连接到您本地运行的代理，因此首先在一个终端中启动代理的本地服务器：

pnpm

pnpm nx agent-dev story

yarn

yarn nx agent-dev story

npm

npx nx agent-dev story

bun

bunx nx agent-dev story

然后，在第二个终端中启动聊天：

pnpm

pnpm nx agent-chat story

yarn

yarn nx agent-chat story

npm

npx nx agent-chat story

bun

bunx nx agent-chat story

您的第一条消息应该告诉代理您的英雄名字和类型（例如：My name is Alice. Start my zombie adventure.），故事将流式返回。

需要 AWS 凭证

尽管代理在本地运行，但它会调用 Amazon Bedrock 来使用 LLM。您需要在环境中配置 AWS 凭证，并具有访问 Strands 默认模型的权限。有关详细信息，请参阅 Strands 模型提供程序文档。

恭喜。您已经在本地构建并测试了您的第一个 Strands 代理！🎉🎉🎉