diff --git a/CLAUDE.md b/CLAUDE.md
index d6b22fb..c2142fe 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -1,108 +1,225 @@
 # CLAUDE.md
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+本文件为 Claude Code (claude.ai/code) 在此代码库中工作时提供指导。
 
-## Project Overview
+## 项目概述
 
-EvoTraders is a self-evolving multi-agent trading system where 6 AI agents (4 analysts + portfolio manager + risk manager) collaborate to make trading decisions. Agents use the AgentScope framework with a ReMe memory system for continuous learning.
+EvoTraders 是一个自进化多智能体交易系统，由 6 个 AI Agent（4 名分析师 + 投资经理 + 风控经理）协作完成交易决策。Agent 基于 AgentScope 框架构建，配合 ReMe 记忆系统实现持续学习。
 
-## Development Commands
+## 常用命令
 
 ### Backend (Python)
 
 ```bash
-# Install dependencies
+# 安装依赖
 uv pip install -e .
 
-# Run commands
-evotraders backtest --start 2025-11-01 --end 2025-12-01  # Backtest mode
-evotraders backtest --start 2025-11-01 --end 2025-12-01 --enable-memory
-evotraders live                              # Live trading
-evotraders live --mock                       # Mock/testing mode
-evotraders live -t 22:30                     # Scheduled daily trading
-evotraders frontend                          # Launch visualization UI
+# 运行命令
+evotraders backtest --start 2025-11-01 --end 2025-12-01  # 回测模式
+evotraders backtest --start 2025-11-01 --end 2025-12-01 --enable-memory  # 带记忆回测
+evotraders live                              # 实盘交易
+evotraders live --mock                       # 模拟/测试模式
+evotraders live -t 22:30                     # 定时每日交易
+evotraders frontend                          # 启动可视化界面
 
-# Dev server (starts FastAPI on port 8000)
-./start-dev.sh
-# Or manually:
-python -m uvicorn backend.app:app --host 0.0.0.0 --port 8000 --reload --reload-dir backend
+# 开发服务器
+./start-dev.sh  # 启动全部 4 个微服务
 
-# Testing
-pytest backend/tests
+# 单独启动某个服务
+python -m uvicorn backend.apps.agent_service:app --host 0.0.0.0 --port 8000 --reload
+python -m uvicorn backend.apps.runtime_service:app --host 0.0.0.0 --port 8003 --reload
+python -m uvicorn backend.apps.trading_service:app --host 0.0.0.0 --port 8001 --reload
+python -m uvicorn backend.apps.news_service:app --host 0.0.0.0 --port 8002 --reload
+
+# 测试
+pytest backend/tests                          # 运行全部测试
+pytest backend/tests/test_news_service_app.py -v  # 运行单个测试文件
+pytest backend/tests/test_news_service_app.py::test_news_service_routes_are_exposed -v  # 运行单个测试
 ```
 
 ### Frontend (React)
 
 ```bash
 cd frontend
-npm run dev          # Vite dev server (http://localhost:5173)
-npm run build        # Production build
-npm run lint         # ESLint
-npm run test         # Vitest
-npm run test:watch   # Watch mode
+npm run dev          # Vite 开发服务器 (http://localhost:5173)
+npm run build        # 生产构建
+npm run lint         # ESLint 检查
+npm run lint:fix     # ESLint 自动修复
+npm run test         # Vitest 单元测试
+npm run test:watch   # 监听模式
 ```
 
-## Architecture
+## 架构概览
 
-### Multi-Agent System (`backend/agents/`)
+### 微服务架构 (`backend/apps/`)
 
-**6 Agent Roles** (configured in `prompts/analyst/personas.yaml`):
-- **fundamentals_analyst** - Financial health, profitability, growth quality
-- **technical_analyst** - Price trends, indicators, momentum
-- **sentiment_analyst** - Market sentiment, news, insider trading
-- **valuation_analyst** - DCF, EV/EBITDA, intrinsic value
-- **portfolio_manager** - Decision execution, trade coordination
-- **risk_manager** - Real-time risk monitoring, position limits
+项目采用 split-first 微服务架构，4 个独立的 FastAPI 服务：
 
-**Key Agent Files**:
-- `base/evo_agent.py` - Core agent implementation extending AgentScope
-- `base/hooks.py` - Lifecycle hooks for agent execution (BootstrapHook, MemoryCompactionHook, HeartbeatHook, WorkspaceWatchHook)
-- `base/evaluation_hook.py` - Post-execution evaluation
-- `base/skill_adaptation_hook.py` - Dynamic skill adaptation
-- `factory.py` - Agent factory for creating agent instances
-- `skills_manager.py` - Skill loading and management (6 scopes: builtin/customized/installed/active/disabled/local)
-- `toolkit_factory.py` - Tool collection factory for agents
-- `team/` - Team coordination (registry, coordinator, messenger, task_delegator)
+| 服务 | 入口 | 端口 | 职责 |
+|------|------|------|------|
+| agent_service | `backend.apps.agent_service:app` | 8000 | Agent 生命周期、工作区管理 |
+| runtime_service | `backend.apps.runtime_service:app` | 8003 | 运行时配置、任务启动 |
+| trading_service | `backend.apps.trading_service:app` | 8001 | 市场数据、交易操作 |
+| news_service | `backend.apps.news_service:app` | 8002 | 新闻、新闻富化、解释功能 |
 
-**Hook System** (`base/hooks.py`):
-- **MemoryCompactionHook**: 基于 CoPaw 设计的内存压缩，支持:
-  - `memory_compact_ratio`: 压缩目标比例 (默认 0.75)
-  - `memory_reserve_ratio`: 保留比例 (默认 0.1)
-  - `enable_tool_result_compact`: 工具结果压缩
-  - `tool_result_compact_keep_n`: 保留最近 N 条工具结果
+服务间通过环境变量通信（详见 `start-dev.sh`）：
+```bash
+export TRADING_SERVICE_URL=http://localhost:8001
+export NEWS_SERVICE_URL=http://localhost:8002
+export RUNTIME_SERVICE_URL=http://localhost:8003
+```
 
-**Adding Custom Analysts**:
-1. Register in `backend/agents/prompts/analyst/personas.yaml`
-2. Add to `ANALYST_TYPES` dict in `backend/config/constants.py`
-3. Optionally update frontend config in `frontend/src/config/constants.js`
+### Gateway 网关 (`backend/services/gateway.py`)
 
-### Backend Structure
+Gateway 是统一的请求路由器，根据路径前缀将请求转发到对应的微服务：
+- `/control/*` → agent_service
+- `/runtime/*` → runtime_service
+- `/trading/*` → trading_service
+- `/news/*` → news_service
+
+新增接口时应注册到对应的 service app，而非直接添加到 gateway。
+
+### 共享客户端 (`shared/client/`)
+
+统一的服务客户端库，所有前端和后端服务间通信都使用此处定义的客户端：
+
+| 客户端 | 用途 |
+|--------|------|
+| `ControlPlaneClient` | Agent 服务通信 |
+| `RuntimeServiceClient` | 运行时服务通信 |
+| `TradingServiceClient` | 交易服务通信 |
+| `NewsServiceClient` | 新闻服务通信 |
+
+### 领域层 (`backend/domains/`)
+
+业务逻辑按领域分离：
+
+- `news.py` - 新闻领域操作
+- `trading.py` - 交易领域操作
+
+## 后端结构
 
 ```
 backend/
-├── agents/          # Multi-agent implementation
-│   ├── base/        # Base classes, hooks, evaluation
-│   ├── prompts/     # Agent prompts and personas
-│   └── team/        # Team coordination logic
-├── api/             # FastAPI endpoints
-├── config/          # Constants and configuration
-├── core/            # Pipeline execution logic
-├── data/            # Market data handling
-├── enrich/          # LLM response enrichment
-├── explain/         # Decision explanation
-├── llm/             # LLM integrations (with RetryChatModel, TokenRecordingModelWrapper)
-├── services/        # Gateway, WebSocket services
-├── skills/          # Skill definitions (builtin + custom)
-└── tools/           # Trading and analysis tools
+├── agents/           # 多智能体实现
+│   ├── base/         # 核心类、Hooks、评估
+│   │   ├── evo_agent.py        # 基于 AgentScope 的核心实现
+│   │   ├── hooks.py             # 生命周期 Hooks
+│   │   │   ├── BootstrapHook           # 启动初始化
+│   │   │   ├── MemoryCompactionHook    # 内存压缩（基于 CoPaw）
+│   │   │   ├── HeartbeatHook           # 心跳检测
+│   │   │   └── WorkspaceWatchHook      # 工作区监控
+│   │   ├── evaluation_hook.py   # 执行后评估
+│   │   ├── skill_adaptation_hook.py  # 动态技能适配
+│   │   └── tool_guard.py        # 工具调用守卫
+│   ├── prompts/      # Agent 提示词和角色定义
+│   │   ├── analyst/personas.yaml  # 分析师角色配置
+│   │   └── portfolio_manager/
+│   ├── team/         # 团队协作逻辑
+│   │   ├── registry.py        # Agent 注册表
+│   │   ├── coordinator.py     # 协作协调器
+│   │   ├── messenger.py       # 消息传递
+│   │   └── task_delegator.py  # 任务分发
+│   ├── factory.py     # Agent 实例工厂
+│   ├── skills_manager.py  # 技能加载管理（6 种作用域）
+│   └── toolkit_factory.py  # 工具集工厂
+├── apps/             # 微服务入口（split-first）
+│   ├── agent_service.py
+│   ├── runtime_service.py
+│   ├── trading_service.py
+│   └── news_service.py
+├── domains/          # 领域业务逻辑
+│   ├── news.py
+│   └── trading.py
+├── services/         # Gateway 和辅助服务
+│   ├── gateway.py           # 统一路由网关
+│   ├── gateway_*.py         # Gateway 子模块
+│   └── market.py            # 市场数据服务
+├── api/              # FastAPI 端点
+├── config/           # 常量和配置
+│   └── constants.py   # Agent 配置、显示名称等
+├── core/             # Pipeline 执行逻辑
+├── data/             # 市场数据处理
+│   ├── provider_router.py  # 数据源路由
+│   └── schema.py          # 数据 schema
+├── enrich/           # LLM 响应富化
+├── explain/          # 交易决策解释
+├── llm/              # LLM 集成
+│   └── models.py     # RetryChatModel、TokenRecordingModelWrapper
+├── skills/           # 技能定义（内置 + 自定义）
+├── tools/            # 交易和分析工具
+└── utils/            # 工具函数
 ```
 
-### LLM Model Wrappers (`backend/llm/models.py`)
+## 前端结构
+
+```
+frontend/src/
+├── App.jsx              # React 主应用
+├── components/          # React 组件
+│   ├── RuntimeView.jsx           # 交易运行时 UI
+│   ├── TraderView.jsx            # 交易员界面
+│   ├── RoomView.jsx              # 聊天室视图
+│   ├── StockExplainView.jsx      # 股票解释视图
+│   ├── RuntimeSettingsPanel.jsx  # 运行时设置面板
+│   ├── WatchlistPanel.jsx        # 关注列表
+│   ├── PerformanceView.jsx       # 绩效视图
+│   ├── StatisticsView.jsx        # 统计视图
+│   ├── NetValueChart.jsx         # 净值曲线图
+│   ├── AgentCard.jsx             # Agent 卡片
+│   ├── AgentFeed.jsx             # Agent 动态
+│   └── explain/                  # 解释相关组件
+│       ├── ExplainNewsSection.jsx
+│       ├── ExplainRangeSection.jsx
+│       ├── ExplainSimilarDaysSection.jsx
+│       ├── ExplainStorySection.jsx
+│       └── useExplainModel.js
+├── services/            # API 服务
+│   ├── runtimeApi.js     # 运行时 API 调用
+│   ├── websocket.js      # WebSocket 实时通信
+│   ├── newsApi.js        # 新闻服务客户端
+│   └── tradingApi.js     # 交易服务客户端
+├── config/
+│   └── constants.js      # Agent 定义、配置
+└── hooks/               # React Hooks
+```
+
+## Agent 系统
+
+### 6 种 Agent 角色
+
+| 角色 ID | 名称 | 职责 |
+|---------|------|------|
+| `fundamentals_analyst` | 基本面分析师 | 财务健康、盈利能力、成长质量 |
+| `technical_analyst` | 技术分析师 | 价格趋势、技术指标、动量分析 |
+| `sentiment_analyst` | 情绪分析师 | 市场情绪、新闻情绪、内幕交易 |
+| `valuation_analyst` | 估值分析师 | DCF、EV/EBITDA、 intrinsic value |
+| `portfolio_manager` | 投资经理 | 决策执行、交易协调 |
+| `risk_manager` | 风控经理 | 实时价格/波动率监控、仓位限制、多层风险预警 |
+
+### Hook 系统 (`base/hooks.py`)
+
+- **MemoryCompactionHook**: 基于 CoPaw 的内存压缩
+  - `memory_compact_ratio`: 压缩目标比例（默认 0.75）
+  - `memory_reserve_ratio`: 保留比例（默认 0.1）
+  - `enable_tool_result_compact`: 工具结果压缩
+  - `tool_result_compact_keep_n`: 保留最近 N 条工具结果
+
+### 添加自定义分析师
+
+1. 在 `backend/agents/prompts/analyst/personas.yaml` 注册
+2. 在 `backend/config/constants.py` 的 `ANALYST_TYPES` 字典中添加
+3. 可选：在 `frontend/src/config/constants.js` 中更新前端配置
+
+### LLM 模型封装 (`backend/llm/models.py`)
+
+基于 CoPaw 的模型封装设计：
 
-Based on CoPaw's model wrapper design:
 - **RetryChatModel**: 自动重试瞬态 LLM 错误（rate limit、timeout、502/503 等），指数退避
-  - `max_retries`: 最大重试次数 (默认 3)
-  - `initial_delay`: 初始延迟秒数 (默认 1.0)
-  - `backoff_multiplier`: 退避倍数 (默认 2.0)
+  - `max_retries`: 最大重试次数（默认 3）
+  - `initial_delay`: 初始延迟秒数（默认 1.0）
+  - `backoff_multiplier`: 退避倍数（默认 2.0）
+
 - **TokenRecordingModelWrapper**: 追踪每个 provider 的 token 消耗和成本
 
 ```python
@@ -111,60 +228,75 @@ from backend.llm.models import create_model, RetryChatModel
 model = RetryChatModel(create_model("gpt-4o", "OPENAI"), max_retries=3)
 ```
 
-### Frontend Structure
+## 技能系统 (`backend/skills/`)
 
-```
-frontend/src/
-├── App.jsx              # Main React application
-├── components/          # React components
-│   ├── RuntimeView.jsx  # Trading runtime UI
-│   ├── TraderView.jsx   # Trader interface
-│   └── RuntimeSettingsPanel.jsx
-├── services/            # API and WebSocket services
-│   ├── runtimeApi.js    # Backend API calls
-│   └── websocket.js      # Real-time communication
-└── config/
-    └── constants.js      # Agent definitions, configuration
-```
+技能定义在 `SKILL.md` 文件中，包含：
+- `instructions` - 技能说明
+- `triggers` - 触发条件
+- `parameters` - 输入/输出 schema
+- `available_tools` - 技能可使用的工具
 
-### Skill System (`backend/skills/`)
+技能由 `skills_manager.py` 加载，通过 `skill_adaptation_hook.py` 绑定到 Agent。
 
-Skills are defined in `SKILL.md` files with:
-- `instructions` - What the skill does
-- `triggers` - When to invoke
-- `parameters` - Input/output schema
-- `available_tools` - Tools the skill can use
+技能管理器支持 6 种作用域：builtin、customized、installed、active、disabled、local。
 
-Skills are loaded by `skills_manager.py` and attached to agents via `skill_adaptation_hook.py`.
+## Pipeline 执行 (`backend/core/`)
 
-### Pipeline Execution (`backend/core/`)
+每日交易流程：
 
-The daily trading flow:
-1. **Analysis Stage** - Each agent analyzes independently
-2. **Communication Stage** - Agent-to-agent messaging (1v1, 1vN, NvN)
-3. **Decision Stage** - Portfolio manager makes final trades
-4. **Evaluation Stage** - Performance tracking
-5. **Review Stage** - Memory updates via ReMe
+1. **分析阶段** - 各 Agent 基于工具和历史经验独立分析
+2. **沟通阶段** - 通过私聊、通知、会议等方式交换观点（1v1/1vN/NvN）
+3. **决策阶段** - 投资经理综合判断，给出最终交易
+4. **评估阶段** - 绩效跟踪
+5. **复盘阶段** - Agent 根据当日实际收益反思总结，通过 ReMe 记忆框架更新经验
 
-## Environment Configuration
+## 前端状态管理
+
+项目正在向 Zustand 状态管理过渡，已创建的 store：
 
-Required in `.env`:
 ```bash
+frontend/src/store/
+├── index.js           # 导出所有 store
+├── runtimeStore.js    # 连接状态、运行时配置
+├── marketStore.js     # 市场数据、股票价格
+├── portfolioStore.js  # 组合、持仓、交易
+├── agentStore.js      # Agent 技能、工作区
+└── uiStore.js         # UI 状态、视图切换
+```
+
+**迁移状态**：
+- Stores 已创建但尚未在 App.jsx 中使用
+- 计划：逐步迁移 60+ 个 useState 到对应 store
+
+## 环境配置
+
+`.env` 必需配置：
+
+```bash
+# 金融数据源
 FIN_DATA_SOURCE=finnhub|financial_datasets
-FINANCIAL_DATASETS_API_KEY=   # Required for backtest
-FINNHUB_API_KEY=              # Required for live trading
-OPENAI_API_KEY=               # Agent LLM
+FINANCIAL_DATASETS_API_KEY=   # 回测必需
+FINNHUB_API_KEY=              # 实盘必需
+
+# Agent LLM
+OPENAI_API_KEY=
 OPENAI_BASE_URL=
 MODEL_NAME=qwen3-max-preview
-MEMORY_API_KEY=               # For ReMe memory system
+
+# 可为不同 Agent 指定不同模型
+AGENT_SENTIMENT_ANALYST_MODEL_NAME=qwen3-max-preview
+AGENT_FUNDAMENTALS_ANALYST_MODEL_NAME=deepseek-chat
+
+# ReMe 记忆系统
+MEMORY_API_KEY=
 ```
 
-## Key Dependencies
+## 关键依赖
 
-- **AgentScope** - Multi-agent framework
-- **ReMe** - Memory system for continuous learning
-- **FastAPI** + **uvicorn** - Backend API server
-- **websockets** - Real-time communication
-- **React 19** + **Vite** + **TailwindCSS** - Frontend
-- **Zustand** - Frontend state management
-- **Three.js** / **React-Three-Fiber** - 3D visualizations
+- **AgentScope** - 多智能体框架
+- **ReMe** - 持续学习记忆系统
+- **FastAPI** + **uvicorn** - 后端 API 服务器
+- **websockets** - 实时通信
+- **React 19** + **Vite** + **TailwindCSS** - 前端
+- **React Context** - 前端状态管理（App.jsx 中使用 useState + useCallback）
+- **Three.js** / **React-Three-Fiber** - 3D 可视化
diff --git a/frontend/src/store/agentStore.js b/frontend/src/store/agentStore.js
new file mode 100644
index 0000000..6f2d3ac
--- /dev/null
+++ b/frontend/src/store/agentStore.js
@@ -0,0 +1,58 @@
+import { create } from 'zustand';
+
+/**
+ * Agent Store - Agent skills, profiles, workspaces
+ */
+export const useAgentStore = create((set) => ({
+  // Selected agent for skill/workspace editing
+  selectedSkillAgentId: null,
+  setSelectedSkillAgentId: (selectedSkillAgentId) => set({ selectedSkillAgentId }),
+
+  // Agent profiles
+  agentProfilesByAgent: {},
+  setAgentProfilesByAgent: (agentProfilesByAgent) => set({ agentProfilesByAgent }),
+
+  // Agent skills
+  agentSkillsByAgent: {},
+  setAgentSkillsByAgent: (agentSkillsByAgent) => set({ agentSkillsByAgent }),
+
+  // Skill details
+  skillDetailsByName: {},
+  setSkillDetailsByName: (skillDetailsByName) => set({ skillDetailsByName }),
+
+  // Local skill drafts
+  localSkillDraftsByKey: {},
+  setLocalSkillDraftsByKey: (localSkillDraftsByKey) => set({ localSkillDraftsByKey }),
+
+  // Loading states
+  isAgentSkillsLoading: false,
+  setIsAgentSkillsLoading: (isAgentSkillsLoading) => set({ isAgentSkillsLoading }),
+
+  skillDetailLoadingKey: null,
+  setSkillDetailLoadingKey: (skillDetailLoadingKey) => set({ skillDetailLoadingKey }),
+
+  agentSkillsSavingKey: null,
+  setAgentSkillsSavingKey: (agentSkillsSavingKey) => set({ agentSkillsSavingKey }),
+
+  agentSkillsFeedback: null,
+  setAgentSkillsFeedback: (agentSkillsFeedback) => set({ agentSkillsFeedback }),
+
+  // Workspace files
+  selectedWorkspaceFile: null,
+  setSelectedWorkspaceFile: (selectedWorkspaceFile) => set({ selectedWorkspaceFile }),
+
+  workspaceFilesByAgent: {},
+  setWorkspaceFilesByAgent: (workspaceFilesByAgent) => set({ workspaceFilesByAgent }),
+
+  workspaceDraftContent: '',
+  setWorkspaceDraftContent: (workspaceDraftContent) => set({ workspaceDraftContent }),
+
+  isWorkspaceFileLoading: false,
+  setIsWorkspaceFileLoading: (isWorkspaceFileLoading) => set({ isWorkspaceFileLoading }),
+
+  workspaceFileSavingKey: null,
+  setWorkspaceFileSavingKey: (workspaceFileSavingKey) => set({ workspaceFileSavingKey }),
+
+  workspaceFileFeedback: null,
+  setWorkspaceFileFeedback: (workspaceFileFeedback) => set({ workspaceFileFeedback }),
+}));
diff --git a/frontend/src/store/index.js b/frontend/src/store/index.js
new file mode 100644
index 0000000..c6e2951
--- /dev/null
+++ b/frontend/src/store/index.js
@@ -0,0 +1,5 @@
+export { useRuntimeStore } from './runtimeStore';
+export { useMarketStore } from './marketStore';
+export { usePortfolioStore } from './portfolioStore';
+export { useAgentStore } from './agentStore';
+export { useUIStore } from './uiStore';
diff --git a/frontend/src/store/marketStore.js b/frontend/src/store/marketStore.js
new file mode 100644
index 0000000..250e9c3
--- /dev/null
+++ b/frontend/src/store/marketStore.js
@@ -0,0 +1,44 @@
+import { create } from 'zustand';
+
+/**
+ * Market Store - Market data, stock prices, news
+ */
+export const useMarketStore = create((set) => ({
+  // Ticker prices
+  tickers: [],
+  setTickers: (tickers) => set({ tickers }),
+  rollingTickers: {},
+  setRollingTickers: (rollingTickers) => set({ rollingTickers }),
+
+  // Price history
+  priceHistoryByTicker: {},
+  setPriceHistoryByTicker: (priceHistoryByTicker) => set({ priceHistoryByTicker }),
+
+  // OHLC history
+  ohlcHistoryByTicker: {},
+  setOhlcHistoryByTicker: (ohlcHistoryByTicker) => set({ ohlcHistoryByTicker }),
+
+  // History source tracking
+  historySourceByTicker: {},
+  setHistorySourceByTicker: (historySourceByTicker) => set({ historySourceByTicker }),
+
+  // Explain events
+  explainEventsByTicker: {},
+  setExplainEventsByTicker: (explainEventsByTicker) => set({ explainEventsByTicker }),
+
+  // Selected explain symbol
+  selectedExplainSymbol: '',
+  setSelectedExplainSymbol: (selectedExplainSymbol) => set({ selectedExplainSymbol }),
+
+  // News by ticker
+  newsByTicker: {},
+  setNewsByTicker: (newsByTicker) => set({ newsByTicker }),
+
+  // Insider trades
+  insiderTradesByTicker: {},
+  setInsiderTradesByTicker: (insiderTradesByTicker) => set({ insiderTradesByTicker }),
+
+  // Technical indicators
+  technicalIndicatorsByTicker: {},
+  setTechnicalIndicatorsByTicker: (technicalIndicatorsByTicker) => set({ technicalIndicatorsByTicker }),
+}));
diff --git a/frontend/src/store/portfolioStore.js b/frontend/src/store/portfolioStore.js
new file mode 100644
index 0000000..c185dc4
--- /dev/null
+++ b/frontend/src/store/portfolioStore.js
@@ -0,0 +1,38 @@
+import { create } from 'zustand';
+
+/**
+ * Portfolio Store - Portfolio data, holdings, trades, statistics
+ */
+export const usePortfolioStore = create((set) => ({
+  // Portfolio data
+  portfolioData: {
+    netValue: 10000,
+    pnl: 0,
+    equity: [],
+    baseline: [],
+    baseline_vw: [],
+    momentum: [],
+    strategies: [],
+    equity_return: 0,
+    baseline_return: 0,
+    baseline_vw_return: 0,
+    momentum_return: 0,
+  },
+  setPortfolioData: (portfolioData) => set({ portfolioData }),
+
+  // Holdings
+  holdings: [],
+  setHoldings: (holdings) => set({ holdings }),
+
+  // Trades
+  trades: [],
+  setTrades: (trades) => set({ trades }),
+
+  // Statistics
+  stats: null,
+  setStats: (stats) => set({ stats }),
+
+  // Leaderboard
+  leaderboard: [],
+  setLeaderboard: (leaderboard) => set({ leaderboard }),
+}));
diff --git a/frontend/src/store/runtimeStore.js b/frontend/src/store/runtimeStore.js
new file mode 100644
index 0000000..5f864e8
--- /dev/null
+++ b/frontend/src/store/runtimeStore.js
@@ -0,0 +1,90 @@
+import { create } from 'zustand';
+
+/**
+ * Runtime Store - Connection state and runtime configuration
+ */
+export const useRuntimeStore = create((set) => ({
+  // Connection state
+  isConnected: false,
+  connectionStatus: 'connecting', // 'connecting' | 'connected' | 'disconnected'
+  setIsConnected: (isConnected) => set({ isConnected }),
+  setConnectionStatus: (connectionStatus) => set({ connectionStatus }),
+
+  // System state
+  systemStatus: 'initializing', // 'initializing' | 'running' | 'completed'
+  currentDate: null,
+  setSystemStatus: (systemStatus) => set({ systemStatus }),
+  setCurrentDate: (currentDate) => set({ currentDate }),
+
+  // Progress
+  progress: { current: 0, total: 0 },
+  setProgress: (progress) => set({ progress }),
+
+  // Server mode
+  serverMode: null, // 'live' | 'backtest' | null
+  setServerMode: (serverMode) => set({ serverMode }),
+
+  // Market status
+  marketStatus: null,
+  virtualTime: null,
+  setMarketStatus: (marketStatus) => set({ marketStatus }),
+  setVirtualTime: (virtualTime) => set({ virtualTime }),
+
+  // Data sources
+  dataSources: null,
+  setDataSources: (dataSources) => set({ dataSources }),
+
+  // Runtime config
+  runtimeConfig: null,
+  setRuntimeConfig: (runtimeConfig) => set({ runtimeConfig }),
+
+  // Watchlist panel
+  isWatchlistPanelOpen: false,
+  setIsWatchlistPanelOpen: (isWatchlistPanelOpen) => set({ isWatchlistPanelOpen }),
+
+  // Watchlist draft
+  watchlistDraftSymbols: [],
+  watchlistInputValue: '',
+  watchlistFeedback: null,
+  isWatchlistSaving: false,
+  setWatchlistDraftSymbols: (watchlistDraftSymbols) => set({ watchlistDraftSymbols }),
+  setWatchlistInputValue: (watchlistInputValue) => set({ watchlistInputValue }),
+  setWatchlistFeedback: (watchlistFeedback) => set({ watchlistFeedback }),
+  setIsWatchlistSaving: (isWatchlistSaving) => set({ isWatchlistSaving }),
+
+  // Runtime settings panel
+  isRuntimeSettingsOpen: false,
+  setIsRuntimeSettingsOpen: (isRuntimeSettingsOpen) => set({ isRuntimeSettingsOpen }),
+
+  // Runtime config drafts
+  scheduleModeDraft: 'daily',
+  intervalMinutesDraft: '60',
+  triggerTimeDraft: '09:30',
+  maxCommCyclesDraft: '2',
+  initialCashDraft: '100000',
+  marginRequirementDraft: '0',
+  enableMemoryDraft: false,
+  modeDraft: 'live',
+  pollIntervalDraft: '10',
+  startDateDraft: '',
+  endDateDraft: '',
+  enableMockDraft: false,
+  setScheduleModeDraft: (scheduleModeDraft) => set({ scheduleModeDraft }),
+  setIntervalMinutesDraft: (intervalMinutesDraft) => set({ intervalMinutesDraft }),
+  setTriggerTimeDraft: (triggerTimeDraft) => set({ triggerTimeDraft }),
+  setMaxCommCyclesDraft: (maxCommCyclesDraft) => set({ maxCommCyclesDraft }),
+  setInitialCashDraft: (initialCashDraft) => set({ initialCashDraft }),
+  setMarginRequirementDraft: (marginRequirementDraft) => set({ marginRequirementDraft }),
+  setEnableMemoryDraft: (enableMemoryDraft) => set({ enableMemoryDraft }),
+  setModeDraft: (modeDraft) => set({ modeDraft }),
+  setPollIntervalDraft: (pollIntervalDraft) => set({ pollIntervalDraft }),
+  setStartDateDraft: (startDateDraft) => set({ startDateDraft }),
+  setEndDateDraft: (endDateDraft) => set({ endDateDraft }),
+  setEnableMockDraft: (enableMockDraft) => set({ enableMockDraft }),
+
+  // Runtime config feedback
+  runtimeConfigFeedback: null,
+  isRuntimeConfigSaving: false,
+  setRuntimeConfigFeedback: (runtimeConfigFeedback) => set({ runtimeConfigFeedback }),
+  setIsRuntimeConfigSaving: (isRuntimeConfigSaving) => set({ isRuntimeConfigSaving }),
+}));
diff --git a/frontend/src/store/uiStore.js b/frontend/src/store/uiStore.js
new file mode 100644
index 0000000..daf7f75
--- /dev/null
+++ b/frontend/src/store/uiStore.js
@@ -0,0 +1,40 @@
+import { create } from 'zustand';
+
+/**
+ * UI Store - UI state, view management, layout
+ */
+export const useUIStore = create((set) => ({
+  // Current view
+  currentView: 'traders', // 'traders' | 'room' | 'explain' | 'chart' | 'statistics' | 'runtime'
+  setCurrentView: (currentView) => set({ currentView }),
+
+  // Chart tab
+  chartTab: 'all',
+  setChartTab: (chartTab) => set({ chartTab }),
+
+  // Initial animation
+  isInitialAnimating: true,
+  setIsInitialAnimating: (isInitialAnimating) => set({ isInitialAnimating }),
+
+  // Last update timestamp
+  lastUpdate: new Date(),
+  setLastUpdate: (lastUpdate) => set({ lastUpdate }),
+
+  // Is updating
+  isUpdating: false,
+  setIsUpdating: (isUpdating) => set({ isUpdating }),
+
+  // Room bubbles
+  bubbles: {},
+  setBubbles: (bubbles) => set({ bubbles }),
+
+  // Resizable panels
+  leftWidth: 70,
+  setLeftWidth: (leftWidth) => set({ leftWidth }),
+  isResizing: false,
+  setIsResizing: (isResizing) => set({ isResizing }),
+
+  // Now timestamp (for current time display)
+  now: new Date(),
+  setNow: (now) => set({ now }),
+}));