Jogo de Dungeons de IA Agêntica

Módulo 2: Implementação da API do Jogo e do Servidor MCP de Inventário

Vamos começar implementando nossa Game API. Para isso, precisamos criar 5 APIs no total:

1. saveGame - criar ou atualizar um jogo.
2. queryGames - retornar uma lista paginada de jogos salvos anteriormente.
3. saveAction - salvar uma ação para um determinado jogo.
4. queryActions - retornar uma lista paginada de todas as ações relacionadas a um jogo.
5. queryInventory - retornar uma lista paginada de itens no inventário de um jogador.

Esquema da API

Para definir as entradas e saídas da nossa API, vamos criar nosso esquema usando Zod no diretório packages/game-api/src/schema da seguinte forma:

action.ts

import { z } from 'zod';

export const ActionSchema = z.object({
  playerName: z.string(),
  timestamp: z.iso.datetime(),
  role: z.enum(['assistant', 'user']),
  content: z.string(),
});

export type IAction = z.TypeOf<typeof ActionSchema>;

common.ts

import { z } from 'zod';

export const QueryInputSchema = z.object({
  cursor: z.string().optional(),
  limit: z.number().optional().default(100),
});

export const createPaginatedQueryOutput = <ItemType extends z.ZodTypeAny>(
  itemSchema: ItemType,
) => {
  return z.object({
    items: z.array(itemSchema),
    cursor: z.string().nullable(),
  });
};

export type IQueryInput = z.TypeOf<typeof QueryInputSchema>;

game.ts

import { z } from 'zod';

export const GameSchema = z.object({
  playerName: z.string(),
  genre: z.enum(['zombie', 'superhero', 'medieval']),
  lastUpdated: z.iso.datetime(),
});

export type IGame = z.TypeOf<typeof GameSchema>;

inventory.ts

import { z } from 'zod';

export const ItemSchema = z.object({
  playerName: z.string(),
  itemName: z.string(),
  emoji: z.string().optional(),
  lastUpdated: z.iso.datetime(),
  quantity: z.number(),
});

export type IItem = z.TypeOf<typeof ItemSchema>;

index.ts

+

export * from './action.js';
export * from './common.js';
export * from './game.js';
export * from './inventory.js';

+-

export * from './echo.js'
export * from './action.js';
export * from './common.js';
export * from './game.js';
export * from './inventory.js';

Você também pode excluir o arquivo packages/game-api/src/schema/echo.ts já que não o usaremos neste projeto.

Dica

Como visto acima, para cada esquema definido no Zod, também exportamos uma interface usando a sintaxe z.TypeOf. Isso converte nossa definição Zod em uma interface TypeScript sem duplicação de esforço!

Modelagem de entidades

O diagrama ER para nossa aplicação é o seguinte:

Vamos implementar nosso banco de dados no DynamoDB usando a biblioteca cliente ElectroDB para simplificar o processo. Para começar, primeiro precisamos instalar o electrodb e o DynamoDB Client executando o seguinte comando:

pnpm

pnpm add -w electrodb@3.5.0 @aws-sdk/client-dynamodb@3.913.0

yarn

yarn add electrodb@3.5.0 @aws-sdk/client-dynamodb@3.913.0

npm

npm install --legacy-peer-deps electrodb@3.5.0 @aws-sdk/client-dynamodb@3.913.0

bun

bun install electrodb@3.5.0 @aws-sdk/client-dynamodb@3.913.0

Nota

Todas as dependências são adicionadas ao package.json raiz pois o @aws/nx-plugin segue o princípio de política de versão única. Para mais informações, consulte o guia ts#project.

Agora vamos criar os seguintes arquivos na pasta packages/game-api/src/entities para definir nossas entidades ElectroDB de acordo com o diagrama ER acima:

action.ts

import { Entity } from 'electrodb';
import { DynamoDBClient } from '@aws-sdk/client-dynamodb';

export const createActionEntity = (client?: DynamoDBClient) =>
  new Entity(
    {
      model: {
        entity: 'Action',
        version: '1',
        service: 'game',
      },
      attributes: {
        playerName: { type: 'string', required: true, readOnly: true },
        timestamp: {
          type: 'string',
          required: true,
          readOnly: true,
          set: () => new Date().toISOString(),
          default: () => new Date().toISOString(),
        },
        role: { type: 'string', required: true, readOnly: true },
        content: { type: 'string', required: true, readOnly: true },
      },
      indexes: {
        primary: {
          pk: { field: 'pk', composite: ['playerName'] },
          sk: { field: 'sk', composite: ['timestamp'] },
        },
      },
    },
    { client, table: process.env.TABLE_NAME },
  );

game.ts

import { Entity } from 'electrodb';
import { DynamoDBClient } from '@aws-sdk/client-dynamodb';

export const createGameEntity = (client?: DynamoDBClient) =>
  new Entity(
    {
      model: {
        entity: 'Game',
        version: '1',
        service: 'game',
      },
      attributes: {
        playerName: { type: 'string', required: true, readOnly: true },
        genre: { type: 'string', required: true, readOnly: true },
        lastUpdated: {
          type: 'string',
          required: true,
          default: () => new Date().toISOString(),
        },
      },
      indexes: {
        primary: {
          pk: { field: 'pk', composite: ['playerName'] },
          sk: {
            field: 'sk',
            composite: [],
          },
        },
      },
    },
    { client, table: process.env.TABLE_NAME },
  );

inventory.ts

import { Entity } from 'electrodb';
import { DynamoDBClient } from '@aws-sdk/client-dynamodb';

export const createInventoryEntity = (client?: DynamoDBClient) =>
  new Entity(
    {
      model: {
        entity: 'Inventory',
        version: '1',
        service: 'game',
      },
      attributes: {
        playerName: { type: 'string', required: true, readOnly: true },
        lastUpdated: {
          type: 'string',
          required: true,
          default: () => new Date().toISOString(),
        },
        itemName: {
          type: 'string',
          required: true,
        },
        emoji: {
          type: 'string',
          required: false,
        },
        quantity: {
          type: 'number',
          required: true,
        },
      },
      indexes: {
        primary: {
          pk: { field: 'pk', composite: ['playerName'] },
          sk: { field: 'sk', composite: ['itemName'] },
        },
      },
    },
    { client, table: process.env.TABLE_NAME },
  );

O ElectroDB nos permite não apenas definir nossos tipos, mas também fornecer valores padrão para certos campos como os timestamps acima. Além disso, o ElectroDB segue o design de tabela única, que é a melhor prática ao usar DynamoDB.

Nota

Embora o ElectroDB suporte coleções, optamos por não usá-las neste tutorial para simplificar.

Para preparar o servidor MCP para interagir com o inventário, vamos garantir que exportamos a entidade de inventário em packages/game-api/src/index.ts:

packages/game-api/src/index.ts

export type { AppRouter } from './router.js';
export { appRouter } from './router.js';
export type { Context } from './init.js';
export * from './client/index.js';
export * from './schema/index.js';
export * from './entities/inventory.js';

Nota

A estrutura do pacote seria melhor se refatorássemos as entidades em seu próprio projeto compartilhado, para que o servidor MCP não precise depender da API.

Adicionando o cliente DynamoDB ao contexto do tRPC

Como precisamos de acesso ao cliente DynamoDB em cada um de nossos procedimentos, queremos criar uma única instância do cliente que possamos passar via contexto. Para isso, faça as seguintes alterações em packages/game-api/src:

middleware/dynamodb.ts

import { DynamoDBClient } from '@aws-sdk/client-dynamodb';
import { initTRPC } from '@trpc/server';

export interface IDynamoDBContext {
  dynamoDb?: DynamoDBClient;
}

export const createDynamoDBPlugin = () => {
  const t = initTRPC.context<IDynamoDBContext>().create();
  return t.procedure.use(async (opts) => {
    const dynamoDb = new DynamoDBClient();

    const response = await opts.next({
      ctx: {
        ...opts.ctx,
        dynamoDb,
      },
    });

    return response;
  });
};

Este é um plugin que instrumentamos para criar o DynamoDBClient e injetá-lo no contexto.

middleware/index.ts

import { CreateAWSLambdaContextOptions } from '@trpc/server/adapters/aws-lambda';
import type { APIGatewayProxyEvent } from 'aws-lambda';
import { ILoggerContext } from './logger.js';
import { IMetricsContext } from './metrics.js';
import { ITracerContext } from './tracer.js';
import { IDynamoDBContext } from './dynamodb.js';

export * from './dynamodb.js';
export * from './logger.js';
export * from './metrics.js';
export * from './tracer.js';
export * from './error.js';

export type IMiddlewareContext =
  CreateAWSLambdaContextOptions<APIGatewayProxyEvent> &
    IDynamoDBContext &
    ILoggerContext &
    IMetricsContext &
    ITracerContext;

Aumentamos nosso IMiddlewareContext para adicionar o IDynamoDBContext.

init.ts

import { initTRPC } from '@trpc/server';
import {
  createDynamoDBPlugin,
  createErrorPlugin,
  createLoggerPlugin,
  createMetricsPlugin,
  createTracerPlugin,
  IMiddlewareContext,
} from './middleware/index.js';

process.env.POWERTOOLS_SERVICE_NAME = 'GameApi';
process.env.POWERTOOLS_METRICS_NAMESPACE = 'GameApi';

export type Context = IMiddlewareContext;

export const t = initTRPC.context<Context>().create();

export const publicProcedure = t.procedure
  .concat(createDynamoDBPlugin())
  .concat(createLoggerPlugin())
  .concat(createTracerPlugin())
  .concat(createMetricsPlugin())
  .concat(createErrorPlugin());

O plugin DynamoDB é instrumentado.

Nota

A API concat vincula nosso middleware aos procedimentos que definimos. Para mais detalhes, consulte o guia concat.

Definindo nossos procedimentos

Agora é hora de implementar os métodos da API. Para isso, faça as seguintes alterações em packages/game-api/src/procedures:

Consultas

query-actions.ts

import { createActionEntity } from '../entities/action.js';
import {
  ActionSchema,
  IAction,
  QueryInputSchema,
  createPaginatedQueryOutput,
} from '../schema/index.js';
import { publicProcedure } from '../init.js';
import { z } from 'zod';

export const queryActions = publicProcedure
  .input(QueryInputSchema.extend({ playerName: z.string() }))
  .output(createPaginatedQueryOutput(ActionSchema))
  .query(async ({ input, ctx }) => {
    const actionEntity = createActionEntity(ctx.dynamoDb);
    const result = await actionEntity.query
      .primary({ playerName: input.playerName })
      .go({ cursor: input.cursor, count: input.limit });

    return {
      items: result.data as IAction[],
      cursor: result.cursor,
    };
  });

query-games.ts

import { createGameEntity } from '../entities/game.js';
import {
  GameSchema,
  IGame,
  QueryInputSchema,
  createPaginatedQueryOutput,
} from '../schema/index.js';
import { publicProcedure } from '../init.js';

export const queryGames = publicProcedure
  .input(QueryInputSchema)
  .output(createPaginatedQueryOutput(GameSchema))
  .query(async ({ input, ctx }) => {
    const gameEntity = createGameEntity(ctx.dynamoDb);
    const result = await gameEntity.scan.go({
      cursor: input.cursor,
      count: input.limit,
    });

    return {
      items: result.data as IGame[],
      cursor: result.cursor,
    };
  });

query-inventory.ts

import {
  ItemSchema,
  QueryInputSchema,
  createPaginatedQueryOutput,
} from '../schema/index.js';
import { publicProcedure } from '../init.js';
import { z } from 'zod';
import { createInventoryEntity } from '../entities/inventory.js';

export const queryInventory = publicProcedure
  .input(QueryInputSchema.extend({ playerName: z.string() }))
  .output(createPaginatedQueryOutput(ItemSchema))
  .query(async ({ input, ctx }) => {
    const inventoryEntity = createInventoryEntity(ctx.dynamoDb);
    const result = await inventoryEntity.query
      .primary({ playerName: input.playerName })
      .go({ cursor: input.cursor, count: input.limit });

    return {
      items: result.data,
      cursor: result.cursor,
    };
  });

Mutations

save-action.ts

import { ActionSchema, IAction } from '../schema/index.js';
import { publicProcedure } from '../init.js';
import { createActionEntity } from '../entities/action.js';
import { createGameEntity } from '../entities/game.js';

export const saveAction = publicProcedure
  .input(ActionSchema.omit({ timestamp: true }))
  .output(ActionSchema)
  .mutation(async ({ input, ctx }) => {
    const actionEntity = createActionEntity(ctx.dynamoDb);
    const gameEntity = createGameEntity(ctx.dynamoDb);

    const action = await actionEntity.put(input).go();
    await gameEntity
      .update({ playerName: input.playerName })
      .set({ lastUpdated: action.data.timestamp })
      .go();
    return action.data as IAction;
  });

save-game.ts

import { createGameEntity } from '../entities/game.js';
import { GameSchema, IGame } from '../schema/index.js';
import { publicProcedure } from '../init.js';

export const saveGame = publicProcedure
  .input(GameSchema.omit({ lastUpdated: true }))
  .output(GameSchema)
  .mutation(async ({ input, ctx }) => {
    const gameEntity = createGameEntity(ctx.dynamoDb);

    const result = await gameEntity.put(input).go();
    return result.data as IGame;
  });

Você também pode excluir o arquivo echo.ts (de packages/game-api/src/procedures) já que não o usaremos neste projeto.

Configuração do roteador

Agora que definimos nossos procedimentos, vamos conectá-los à nossa API. Para isso, atualize o seguinte arquivo:

packages/game-api/src/router.ts

+

import {
  awsLambdaRequestHandler,
  CreateAWSLambdaContextOptions,
} from '@trpc/server/adapters/aws-lambda';
import { t } from './init.js';
import { APIGatewayProxyEvent } from 'aws-lambda';
import { queryActions } from './procedures/query-actions.js';
import { saveAction } from './procedures/save-action.js';
import { queryGames } from './procedures/query-games.js';
import { saveGame } from './procedures/save-game.js';
import { queryInventory } from './procedures/query-inventory.js';

export const router = t.router;

export const appRouter = router({
  actions: router({
    query: queryActions,
    save: saveAction,
  }),
  games: router({
    query: queryGames,
    save: saveGame,
  }),
  inventory: router({
    query: queryInventory,
  }),
});

export const handler = awsLambdaRequestHandler({
  router: appRouter,
  createContext: (
    ctx: CreateAWSLambdaContextOptions<APIGatewayProxyEvent>,
  ) => ctx,
  responseMeta: () => ({
    headers: {
      'Access-Control-Allow-Origin': '*',
      'Access-Control-Allow-Methods': '*',
    },
  }),
});

export type AppRouter = typeof appRouter;

+-

import {
  awsLambdaRequestHandler,
  CreateAWSLambdaContextOptions,
} from '@trpc/server/adapters/aws-lambda';
import { echo } from './procedures/echo.js';
import { t } from './init.js';
import { APIGatewayProxyEvent } from 'aws-lambda';
import { queryActions } from './procedures/query-actions.js';
import { saveAction } from './procedures/save-action.js';
import { queryGames } from './procedures/query-games.js';
import { saveGame } from './procedures/save-game.js';
import { queryInventory } from './procedures/query-inventory.js';

export const router = t.router;

export const appRouter = router({
  echo,
  actions: router({
    query: queryActions,
    save: saveAction,
  }),
  games: router({
    query: queryGames,
    save: saveGame,
  }),
  inventory: router({
    query: queryInventory,
  }),
});

export const handler = awsLambdaRequestHandler({
  router: appRouter,
  createContext: (
    ctx: CreateAWSLambdaContextOptions<APIGatewayProxyEvent>,
  ) => ctx,
  responseMeta: () => ({
    headers: {
      'Access-Control-Allow-Origin': '*',
      'Access-Control-Allow-Methods': '*',
    },
  }),
});

export type AppRouter = typeof appRouter;

Servidor MCP de Inventário

Agora vamos criar um servidor MCP que permitirá ao nosso agente gerenciar itens no inventário de um jogador.

Definiremos as seguintes ferramentas para nosso Agente:

• list-inventory-items para recuperar os itens atuais do inventário do jogador
• add-to-inventory para adicionar itens ao inventário do jogador
• remove-from-inventory para remover itens do inventário do jogador

Para economizar tempo, definiremos todas as ferramentas inline:

packages/inventory/src/mcp-server/server.ts

+

import { DynamoDBClient } from '@aws-sdk/client-dynamodb';
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import z from 'zod-v3';
import { createInventoryEntity } from ':dungeon-adventure/game-api';

/**
 * Create the MCP Server
 */
export const createServer = () => {
  const server = new McpServer({
    name: 'inventory-mcp-server',
    version: '1.0.0',
  });

  const dynamoDb = new DynamoDBClient();
  const inventory = createInventoryEntity(dynamoDb);

  server.tool(
    'list-inventory-items',
    "List items in the player's inventory. Leave cursor blank unless you are requesting subsequent pages",
    {
      playerName: z.string(),
      cursor: z.string().optional(),
    },
    async ({ playerName }) => {
      const results = await inventory.query
        .primary({
          playerName,
        })
        .go();

      return {
        content: [{ type: 'text', text: JSON.stringify(results) }],
      };
    },
  );

  server.tool(
    'add-to-inventory',
    "Add an item to the player's inventory. Quantity defaults to 1 if omitted.",
    {
      playerName: z.string(),
      itemName: z.string(),
      emoji: z.string(),
      quantity: z.number().optional().default(1),
    },
    async ({ playerName, itemName, emoji, quantity = 1 }) => {
      await inventory
        .put({
          playerName,
          itemName,
          quantity,
          emoji,
        })
        .go();

      return {
        content: [
          {
            type: 'text',
            text: `Added ${itemName} (x${quantity}) to inventory`,
          },
        ],
      };
    },
  );

  server.tool(
    'remove-from-inventory',
    "Remove an item from the player's inventory. If quantity is omitted, all items are removed.",
    {
      playerName: z.string(),
      itemName: z.string(),
      quantity: z.number().optional(),
    },
    async ({ playerName, itemName, quantity }) => {
      // If quantity is omitted, remove the entire item
      if (quantity === undefined) {
        try {
          await inventory.delete({ playerName, itemName }).go();
          return {
            content: [
              { type: 'text', text: `${itemName} removed from inventory.` },
            ],
          } as const;
        } catch {
          return {
            content: [
              { type: 'text', text: `${itemName} not found in inventory` },
            ],
          } as const;
        }
      }

      // If quantity is specified, fetch current quantity and update
      const item = await inventory.get({ playerName, itemName }).go();

      if (!item.data) {
        return {
          content: [
            { type: 'text', text: `${itemName} not found in inventory` },
          ],
        } as const;
      }

      const newQuantity = item.data.quantity - quantity;

      if (newQuantity <= 0) {
        await inventory.delete({ playerName, itemName }).go();
        return {
          content: [
            { type: 'text', text: `${itemName} removed from inventory.` },
          ],
        } as const;
      }

      await inventory
        .put({
          playerName,
          itemName,
          quantity: newQuantity,
          emoji: item.data.emoji,
        })
        .go();

      return {
        content: [
          {
            type: 'text',
            text: `Removed ${itemName} (x${quantity}) from inventory. ${newQuantity} remaining.`,
          },
        ],
      };
    },
  );

  return server;
};

+-

import { DynamoDBClient } from '@aws-sdk/client-dynamodb';
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { registerAddTool } from './tools/add.js';
import { registerSampleGuidanceResource } from './resources/sample-guidance.js';
import z from 'zod-v3';
import { createInventoryEntity } from ':dungeon-adventure/game-api';

/**
 * Create the MCP Server
 */
export const createServer = () => {
  const server = new McpServer({
    name: 'inventory-mcp-server',
    version: '1.0.0',
  });

  registerAddTool(server);
  registerSampleGuidanceResource(server);
  const dynamoDb = new DynamoDBClient();
  const inventory = createInventoryEntity(dynamoDb);

  server.tool(
    'list-inventory-items',
    "List items in the player's inventory. Leave cursor blank unless you are requesting subsequent pages",
    {
      playerName: z.string(),
      cursor: z.string().optional(),
    },
    async ({ playerName }) => {
      const results = await inventory.query
        .primary({
          playerName,
        })
        .go();

      return {
        content: [{ type: 'text', text: JSON.stringify(results) }],
      };
    },
  );

  server.tool(
    'add-to-inventory',
    "Add an item to the player's inventory. Quantity defaults to 1 if omitted.",
    {
      playerName: z.string(),
      itemName: z.string(),
      emoji: z.string(),
      quantity: z.number().optional().default(1),
    },
    async ({ playerName, itemName, emoji, quantity = 1 }) => {
      await inventory
        .put({
          playerName,
          itemName,
          quantity,
          emoji,
        })
        .go();

      return {
        content: [
          {
            type: 'text',
            text: `Added ${itemName} (x${quantity}) to inventory`,
          },
        ],
      };
    },
  );

  server.tool(
    'remove-from-inventory',
    "Remove an item from the player's inventory. If quantity is omitted, all items are removed.",
    {
      playerName: z.string(),
      itemName: z.string(),
      quantity: z.number().optional(),
    },
    async ({ playerName, itemName, quantity }) => {
      // If quantity is omitted, remove the entire item
      if (quantity === undefined) {
        try {
          await inventory.delete({ playerName, itemName }).go();
          return {
            content: [
              { type: 'text', text: `${itemName} removed from inventory.` },
            ],
          } as const;
        } catch {
          return {
            content: [
              { type: 'text', text: `${itemName} not found in inventory` },
            ],
          } as const;
        }
      }

      // If quantity is specified, fetch current quantity and update
      const item = await inventory.get({ playerName, itemName }).go();

      if (!item.data) {
        return {
          content: [
            { type: 'text', text: `${itemName} not found in inventory` },
          ],
        } as const;
      }

      const newQuantity = item.data.quantity - quantity;

      if (newQuantity <= 0) {
        await inventory.delete({ playerName, itemName }).go();
        return {
          content: [
            { type: 'text', text: `${itemName} removed from inventory.` },
          ],
        } as const;
      }

      await inventory
        .put({
          playerName,
          itemName,
          quantity: newQuantity,
          emoji: item.data.emoji,
        })
        .go();

      return {
        content: [
          {
            type: 'text',
            text: `Removed ${itemName} (x${quantity}) from inventory. ${newQuantity} remaining.`,
          },
        ],
      };
    },
  );

  return server;
};

Conforme o número de ferramentas crescer, você pode refatorá-las em arquivos separados se preferir.

Agora você pode excluir os diretórios tools e resources em packages/inventory/src/mcp-server pois não são utilizados.

Infraestrutura

A etapa final é atualizar nossa infraestrutura para criar a tabela DynamoDB e conceder permissões para operações da Game API. Para isso, atualize o packages/infra/src conforme segue:

constructs/electrodb-table.ts

import { CfnOutput } from 'aws-cdk-lib';
import {
  AttributeType,
  BillingMode,
  ProjectionType,
  Table,
  TableProps,
} from 'aws-cdk-lib/aws-dynamodb';
import { Construct } from 'constructs';
import { suppressRules } from ':dungeon-adventure/common-constructs';

export type ElectrodbDynamoTableProps = Omit<
  TableProps,
  'partitionKey' | 'sortKey' | 'billingMode'
>;

export class ElectrodbDynamoTable extends Table {
  constructor(scope: Construct, id: string, props?: ElectrodbDynamoTableProps) {
    super(scope, id, {
      partitionKey: {
        name: 'pk',
        type: AttributeType.STRING,
      },
      sortKey: {
        name: 'sk',
        type: AttributeType.STRING,
      },
      billingMode: BillingMode.PAY_PER_REQUEST,
      ...props,
    });

    this.addGlobalSecondaryIndex({
      indexName: 'gsi1pk-gsi1sk-index',
      partitionKey: {
        name: 'gsi1pk',
        type: AttributeType.STRING,
      },
      sortKey: {
        name: 'gsi1sk',
        type: AttributeType.STRING,
      },
      projectionType: ProjectionType.ALL,
    });

    // Suppress checkov rules that expect a KMS customer managed key and backup to be enabled
    suppressRules(this, ['CKV_AWS_119', 'CKV_AWS_28'], 'No need for custom encryption or backup');

    new CfnOutput(this, 'TableName', { value: this.tableName });
  }
}

stacks/application-stack.ts

+

import {
  GameApi,
  GameUI,
  InventoryMcpServer,
  RuntimeConfig,
  StoryAgent,
  UserIdentity,
} from ':dungeon-adventure/common-constructs';
import { Stack, StackProps, CfnOutput } from 'aws-cdk-lib';
import { Construct } from 'constructs';
import { ElectrodbDynamoTable } from '../constructs/electrodb-table.js';

export class ApplicationStack extends Stack {
  constructor(scope: Construct, id: string, props?: StackProps) {
    super(scope, id, props);

    const userIdentity = new UserIdentity(this, 'UserIdentity');

    const electroDbTable = new ElectrodbDynamoTable(this, 'ElectroDbTable');

    const gameApi = new GameApi(this, 'GameApi', {
      integrations: GameApi.defaultIntegrations(this)
        .withDefaultOptions({
          environment: {
            TABLE_NAME: electroDbTable.tableName,
          },
        })
        .build(),
    });

    electroDbTable.grantReadData(gameApi.integrations['actions.query'].handler);
    electroDbTable.grantReadData(gameApi.integrations['games.query'].handler);
    electroDbTable.grantReadData(gameApi.integrations['inventory.query'].handler);
    electroDbTable.grantReadWriteData(
      gameApi.integrations['actions.save'].handler,
    );
    electroDbTable.grantReadWriteData(
      gameApi.integrations['games.save'].handler,
    );

    const { userPool, userPoolClient } = userIdentity;

    const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer', {
      environment: {
        TABLE_NAME: electroDbTable.tableName,
      },
    });
    electroDbTable.grantReadWriteData(mcpServer.agentCoreRuntime);

    // Use Cognito for user authentication with the agent
    const storyAgent = new StoryAgent(this, 'StoryAgent', {
      authorizerConfiguration: {
        customJwtAuthorizer: {
          discoveryUrl: `https://cognito-idp.${Stack.of(userPool).region}.amazonaws.com/${userPool.userPoolId}/.well-known/openid-configuration`,
          allowedAudience: [userPoolClient.userPoolClientId],
        },
      },
      environment: {
        INVENTORY_MCP_ARN: mcpServer.agentCoreRuntime.arn,
      },
    });
    // Add the Story Agent ARN to runtime-config.json so it can be referenced by the website
    RuntimeConfig.ensure(this).config.agentArn =
      storyAgent.agentCoreRuntime.arn;

    new CfnOutput(this, 'StoryAgentArn', {
      value: storyAgent.agentCoreRuntime.arn,
    });
    new CfnOutput(this, 'InventoryMcpArn', {
      value: mcpServer.agentCoreRuntime.arn,
    });

    // Grant the agent permissions to invoke our mcp server
    mcpServer.agentCoreRuntime.grantInvoke(storyAgent.agentCoreRuntime);

    // Grant the authenticated role access to invoke the api
    gameApi.grantInvokeAccess(userIdentity.identityPool.authenticatedRole);

    // Ensure this is instantiated last so our runtime-config.json can be automatically configured
    new GameUI(this, 'GameUI');
  }
}

+-

import {
  GameApi,
  GameUI,
  InventoryMcpServer,
  RuntimeConfig,
  StoryAgent,
  UserIdentity,
} from ':dungeon-adventure/common-constructs';
import { Stack, StackProps, CfnOutput } from 'aws-cdk-lib';
import { Construct } from 'constructs';
import { ElectrodbDynamoTable } from '../constructs/electrodb-table.js';

export class ApplicationStack extends Stack {
  constructor(scope: Construct, id: string, props?: StackProps) {
    super(scope, id, props);

    const userIdentity = new UserIdentity(this, 'UserIdentity');

    const electroDbTable = new ElectrodbDynamoTable(this, 'ElectroDbTable');

    const gameApi = new GameApi(this, 'GameApi', {
      integrations: GameApi.defaultIntegrations(this).build(),
      integrations: GameApi.defaultIntegrations(this)
        .withDefaultOptions({
          environment: {
            TABLE_NAME: electroDbTable.tableName,
          },
        })
        .build(),
    });

    electroDbTable.grantReadData(gameApi.integrations['actions.query'].handler);
    electroDbTable.grantReadData(gameApi.integrations['games.query'].handler);
    electroDbTable.grantReadData(gameApi.integrations['inventory.query'].handler);
    electroDbTable.grantReadWriteData(
      gameApi.integrations['actions.save'].handler,
    );
    electroDbTable.grantReadWriteData(
      gameApi.integrations['games.save'].handler,
    );

    const { userPool, userPoolClient } = userIdentity;

    const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer');
    const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer', {
      environment: {
        TABLE_NAME: electroDbTable.tableName,
      },
    });
    electroDbTable.grantReadWriteData(mcpServer.agentCoreRuntime);

    // Use Cognito for user authentication with the agent
    const storyAgent = new StoryAgent(this, 'StoryAgent', {
      authorizerConfiguration: {
        customJwtAuthorizer: {
          discoveryUrl: `https://cognito-idp.${Stack.of(userPool).region}.amazonaws.com/${userPool.userPoolId}/.well-known/openid-configuration`,
          allowedAudience: [userPoolClient.userPoolClientId],
        },
      },
      environment: {
        INVENTORY_MCP_ARN: mcpServer.agentCoreRuntime.arn,
      },
    });
    // Add the Story Agent ARN to runtime-config.json so it can be referenced by the website
    RuntimeConfig.ensure(this).config.agentArn =
      storyAgent.agentCoreRuntime.arn;

    new CfnOutput(this, 'StoryAgentArn', {
      value: storyAgent.agentCoreRuntime.arn,
    });
    new CfnOutput(this, 'InventoryMcpArn', {
      value: mcpServer.agentCoreRuntime.arn,
    });

    // Grant the agent permissions to invoke our mcp server
    mcpServer.agentCoreRuntime.grantInvoke(storyAgent.agentCoreRuntime);

    // Grant the authenticated role access to invoke the api
    gameApi.grantInvokeAccess(userIdentity.identityPool.authenticatedRole);

    // Ensure this is instantiated last so our runtime-config.json can be automatically configured
    new GameUI(this, 'GameUI');
  }
}

Nota

Observe que como cada procedimento é atendido por uma função lambda individual, podemos seguir o princípio de menor privilégio e atribuir apenas as permissões de leitura/escrita necessárias com base na implementação do procedimento.

Implantação e testes

Primeiro, vamos construir a base de código:

pnpm

pnpm nx run-many --target build --all

yarn

yarn nx run-many --target build --all

npm

npx nx run-many --target build --all

bun

bunx nx run-many --target build --all

Dica

Se encontrar erros de lint, você pode executar o seguinte comando para corrigi-los automaticamente:

pnpm

pnpm nx run-many --target lint --configuration=fix --all

yarn

yarn nx run-many --target lint --configuration=fix --all

npm

npx nx run-many --target lint --configuration=fix --all

bun

bunx nx run-many --target lint --configuration=fix --all

Sua aplicação agora pode ser implantada executando o seguinte comando:

pnpm

pnpm nx deploy infra dungeon-adventure-infra-sandbox/*

yarn

yarn nx deploy infra dungeon-adventure-infra-sandbox/*

npm

npx nx deploy infra dungeon-adventure-infra-sandbox/*

bun

bunx nx deploy infra dungeon-adventure-infra-sandbox/*

Cuidado

Você pode precisar fazer o bootstrap da sua conta AWS primeiro, execute:

pnpm

pnpm nx bootstrap infra

yarn

yarn nx bootstrap infra

npm

npx nx bootstrap infra

bun

bunx nx bootstrap infra

Sua primeira implantação levará cerca de 8 minutos para ser concluída. Implantações subsequentes levarão cerca de 2 minutos.

Dica

Se estiver iterando em alterações de código de funções lambda, você pode implantar com a flag --hotswap após construir a base de código para um tempo de implantação muito menor (2-3 segundos).

pnpm

pnpm nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox/* --hotswap

yarn

yarn nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox/* --hotswap

npm

npx nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox/* --hotswap

bun

bunx nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox/* --hotswap

Uma vez concluída a implantação, você verá algumas saídas semelhantes às seguintes (alguns valores foram omitidos):

dungeon-adventure-sandbox-Application
dungeon-adventure-sandbox-Application: deploying... [2/2]

 ✅  dungeon-adventure-sandbox-Application

✨  Deployment time: 354s

Outputs:
dungeon-adventure-sandbox-Application.ElectroDbTableTableNameXXX = dungeon-adventure-sandbox-Application-ElectroDbTableXXX-YYY
dungeon-adventure-sandbox-Application.GameApiEndpointXXX = https://xxx.execute-api.region.amazonaws.com/prod/
dungeon-adventure-sandbox-Application.GameUIDistributionDomainNameXXX = xxx.cloudfront.net
dungeon-adventure-sandbox-Application.StoryApiEndpointXXX = https://xxx.execute-api.region.amazonaws.com/prod/
dungeon-adventure-sandbox-Application.UserIdentityUserIdentityIdentityPoolIdXXX = region:xxx
dungeon-adventure-sandbox-Application.UserIdentityUserIdentityUserPoolIdXXX = region_xxx

Podemos testar nossa API de duas formas:

• Iniciando uma instância local do backend tRPC e invocando as APIs usando curl.
• Chamando a API implantada usando curl com Sigv4

Local

Inicie seu servidor local game-api executando o seguinte comando:

pnpm

TABLE_NAME=dungeon-adventure-infra-sandbox-Application-ElectroDbTableXXX-YYY pnpm nx run @dungeon-adventure/game-api:serve

yarn

TABLE_NAME=dungeon-adventure-infra-sandbox-Application-ElectroDbTableXXX-YYY yarn nx run @dungeon-adventure/game-api:serve

npm

TABLE_NAME=dungeon-adventure-infra-sandbox-Application-ElectroDbTableXXX-YYY npx nx run @dungeon-adventure/game-api:serve

bun

TABLE_NAME=dungeon-adventure-infra-sandbox-Application-ElectroDbTableXXX-YYY bunx nx run @dungeon-adventure/game-api:serve

Cuidado

Use o valor de saída do CDK dungeon-adventure-infra-sandbox-Application.ElectroDbTableTableNameXXX para substituir o placeholder destacado.

Com o servidor em execução, você pode chamá-lo executando:

curl -X GET 'http://localhost:2022/games.query?input=%7B%7D'

Implantado

acurl ap-southeast-2 execute-api -X GET 'https://xxx.execute-api.ap-southeast-2.amazonaws.com/prod/games.query?input=%7B%7D'

Cuidado

Use o valor de saída do CDK dungeon-adventure-infra-sandbox-Application.GameApiGameApiEndpointXXX para substituir o placeholder destacado e defina a região adequadamente.

Nota

O %7B%7D que passamos para testar a API é um objeto JSON vazio codificado em URI ({}).

Se o comando for executado com sucesso, você verá uma resposta como:

{"result":{"data":{"items":[],"cursor":null}}}

Parabéns, você construiu e implantou sua primeira API usando tRPC! 🎉🎉🎉