交易与投资模拟平台

构建一个名为“Paper”的模拟交易平台——一个逼真、无风险的学习交易与投资的环境。

核心功能：

• 投资组合设置：用户以100,000美元虚拟现金起步。通过Yahoo Finance或Alpha Vantage API获取实时股票和ETF价格
• 交易执行：支持市价单和限价单。对市价单模拟0.1%的滑点。每笔交易收取1美元佣金（提供逼真的摩擦，但不会过于严苛）
• 业绩仪表盘：盈亏图表（每日）、总回报率、年化回报率、胜率、平均盈利与亏损、夏普比率以及当前行业敞口——全部随每笔交易更新。使用recharts构建
• 交易日志：每次平仓时必填——“我进入这笔交易时的论点是什么？发生了什么？我下次会有什么不同做法？”三个字段，每个最多200个字符。未完成日志则无法平仓
• 行为分析：[LLM API]分析最近20条交易日志条目，识别反复出现的行为模式——“当盈利头寸接近整数价位时，你总是过早退出”——每月呈现一次
• 排行榜：可选，好友群组之间每周重置的排行榜——按风险调整后回报排名，而非按原始盈亏

技术栈：React、Yahoo Finance或Alpha Vantage用于市场数据、[LLM API]用于行为分析、recharts。终端风格设计——数据密集，无装饰性元素。

Build a paper trading simulation platform called "Paper" — a realistic, risk-free environment for learning to trade and invest.

Core features:

• Portfolio setup: user starts with $100,000 in virtual cash. Real-time stock and ETF prices via Yahoo Finance or Alpha Vantage API
• Trade execution: market and limit orders supported. Simulate 0.1% slippage on market orders. Commission of $1 per trade (realistic friction without being punitive)
• Performance dashboard: P&L chart (daily), total return, annualized return, win rate, average gain and loss, Sharpe ratio, and current sector exposure — all updated with each trade. Built with recharts
• Trade journal: required field on every position close — "What was my thesis entering this trade? What happened? What will I do differently?" Three fields, each max 200 characters. Cannot close a position without completing the journal
• Behavioral analysis: [LLM API] analyzes the last 20 trade journal entries and identifies recurring behavioral patterns — "You consistently exit winning positions early when they approach round-number price levels" — surfaced monthly
• Leaderboard: optional, weekly-resetting leaderboard among friend groups — ranked by risk-adjusted return, not raw P&L

Stack: React, Yahoo Finance or Alpha Vantage for market data, [LLM API] for behavioral analysis, recharts. Terminal-inspired design — data dense, no decorative elements.