用 Kiro构建 AI：基于 AWS 基础设施快速构建企业级 Agentic AI 平台

### Requirement 1: User Authentication
**User Story:** As a user, I want to sign in with my Google account,
so that I can securely access my personal workspace and deliverables.

### Requirement 3: Agent Tool Integration
**User Story:** As a user, I want the Agent to execute code, browse web,
generate images/videos, and deploy web pages...

- [x] 1.1 Initialize frontend project with React, TypeScript, and TailwindCSS
- [x] 1.2 Initialize backend project with FastAPI
- [x] 1.3 Set up database schemas and connections
- [x] 1.4 Set up Redis connection and utilities
- [x] 2.1 Implement Google OAuth authentication flow
- [x] 3.1 Implement Strands Agent with BedrockModel
- [x] 3.2 Implement Code Interpreter tool with AgentCore
...

{
  "name": "API Postman Testing",
  "when": {
    "type": "fileEdited",
    "patterns": ["backend/app/routers/*.py", "backend/app/schemas/*.py"]
  },
  "then": {
    "type": "askAgent",
    "prompt": "API source code has been modified. Run Postman collection tests..."
  }
}

from strands import Agent
from strands.models import BedrockModel
from strands.agent.conversation_manager import SlidingWindowConversationManager

class MyAgent:
    def __init__(self, user_id: str, conversation_id: str, config: AgentConfig):
        # 通过 Amazon Bedrock 初始化模型
        self.model = BedrockModel(
            model_id="us.anthropic.claude-sonnet-4-6",
            region_name="us-west-2",
            temperature=0.7,
            max_tokens=128000,
        )

        # 加载工具——核心工具始终加载，领域工具按用户启用的 Skills 动态加载
        self.tools = get_agent_tools(
            user_id=user_id,
            conversation_id=conversation_id,
            config=config,
        )

        # 创建 Strands Agent
        self.agent = Agent(
            model=self.model,
            tools=self.tools,
            system_prompt=config.system_prompt,
            conversation_manager=SlidingWindowConversationManager(window_size=35),
        )

from strands import tool

class CodeInterpreterTool:
    def __init__(self, region: str, user_id: str, conversation_id: str):
        self.region = region
        self.user_id = user_id

    @tool
    def execute_code(self, code: str, language: str = "python") -> str:
        """在安全沙箱中执行代码。支持 Python、JavaScript 和 Shell。

        Args:
            code: 要执行的代码
            language: 编程语言 (python, javascript, shell)
        """
        # 通过 Amazon Bedrock AgentCore Code Interpreter 执行——隔离沙箱
        ...

# 核心工具——始终加载
tools = [code_interpreter, browser, web_search, file_ops, ...]

# 领域工具——仅在对应 Skills 启用时加载
requested = set(domain_tool_names or [])
if "aws_pricing" in requested:
    tools.append(AWSPricingTool(region=config.aws_region).query_price)
if "architecture_diagram" in requested:
    tools.extend([arch.generate_diagram, arch.modify_diagram, arch.list_aws_icons])

from bedrock_agentcore import BedrockAgentCoreApp
from bedrock_agentcore.runtime.context import RequestContext

app = BedrockAgentCoreApp()

@app.entrypoint
async def invoke(payload: dict, context: RequestContext):
    """AgentCore Runtime 的 HTTP SSE 流式入口"""
    user_id = payload.get("user_id", context.session_id)
    conversation_id = payload.get("conversation_id", context.session_id)

    agent = MyAgent(user_id=user_id, conversation_id=conversation_id)

    async for event in agent.process_message(payload["prompt"]):
        yield event  # Server-Sent Events (SSE) 流式返回给调用方

if __name__ == "__main__":
    app.run()

# 构建并推送容器到 Amazon Elastic Container Registry (Amazon ECR)
docker build --platform linux/arm64 -t $ECR_URI:latest -f Dockerfile.agentcore .
docker push $ECR_URI:latest

# 更新 AgentCore Runtime
aws bedrock-agentcore-control update-agent-runtime \
    --agent-runtime-id $AGENT_ID \
    --agent-runtime-artifact '{"containerConfiguration":{"containerUri":"'$ECR_URI':latest"}}'

if settings.agentcore_runtime_enabled:
    # 生产：通过 AgentCore Runtime 流式传输 (HTTP SSE)
    async for event in agentcore_service.invoke_stream(payload):
        await websocket.send_json(event)
else:
    # 开发：Agent 直接在进程内运行
    async for event in agent.process_message(message):
        await websocket.send_json(event)

from bedrock_agentcore.memory.integrations.strands.session_manager import (
    AgentCoreMemorySessionManager,
)
from bedrock_agentcore.memory.integrations.strands.config import (
    AgentCoreMemoryConfig,
    RetrievalConfig,
)

memory_config = AgentCoreMemoryConfig(
    memory_id="my_agent_memory_id",
    region="us-west-2",
    retrieval_config=RetrievalConfig(max_results=20, retrieval_type="SEMANTIC"),
)

session_manager = AgentCoreMemorySessionManager(config=memory_config)

# 传给 Strands Agent——自动处理持久化和上下文检索
agent = Agent(model=self.model, tools=self.tools, session_manager=session_manager)

// Amazon Virtual Private Cloud (Amazon VPC)：公有、私有、隔离三层子网
const vpc = new ec2.Vpc(this, 'Vpc', {
    maxAzs: 2,
    natGateways: 1,  // 成本优化：单 NAT Gateway
    subnetConfiguration: [
        { name: 'Public', subnetType: ec2.SubnetType.PUBLIC },
        { name: 'Private', subnetType: ec2.SubnetType.PRIVATE_WITH_EGRESS },
        { name: 'Isolated', subnetType: ec2.SubnetType.PRIVATE_ISOLATED },
    ],
});

// Amazon Relational Database Service (Amazon RDS) MySQL 8.4 放在隔离子网——无互联网访问
const mysql = new rds.DatabaseInstance(this, 'Mysql', {
    engine: rds.DatabaseInstanceEngine.mysql({
        version: rds.MysqlEngineVersion.VER_8_4_7,
    }),
    instanceType: ec2.InstanceType.of(ec2.InstanceClass.T4G, ec2.InstanceSize.MICRO),
    vpcSubnets: { subnetType: ec2.SubnetType.PRIVATE_ISOLATED },
});

// Amazon ElastiCache Redis 7.1 用于会话和缓存
const redis = new elasticache.CfnCacheCluster(this, 'Redis', {
    cacheNodeType: 'cache.t4g.micro',
    engine: 'redis',
    engineVersion: '7.1',
});