120 lines
3.4 KiB
Python
120 lines
3.4 KiB
Python
#!/usr/bin/env python3
|
|
"""OpenClaw Phase 2 功能验证 Demo"""
|
|
|
|
print('=' * 60)
|
|
print('🦞 OpenClaw Trading - Phase 2 功能验证')
|
|
print('=' * 60)
|
|
print()
|
|
|
|
# 1. 验证导入
|
|
print('📦 模块导入测试...')
|
|
from openclaw.core.config import get_config
|
|
from openclaw.core.economy import TradingEconomicTracker, SurvivalStatus
|
|
from openclaw.core.costs import DecisionCostCalculator
|
|
from openclaw.agents.base import BaseAgent, AgentState, ActivityType
|
|
from openclaw.agents.trader import TraderAgent
|
|
from openclaw.indicators.technical import sma, ema, rsi, macd, bollinger_bands
|
|
from openclaw.monitoring.status import StatusMonitor
|
|
print('✅ 所有模块导入成功！')
|
|
print()
|
|
|
|
# 2. 配置系统
|
|
print('⚙️ 配置系统...')
|
|
config = get_config()
|
|
print(f' 初始资金: {config.initial_capital}')
|
|
print(f' LLM成本: ${config.cost_structure.llm_input_per_1m}/1M tokens')
|
|
print(f' 模拟天数: {config.simulation_days}')
|
|
print()
|
|
|
|
# 3. 成本计算器
|
|
print('💰 成本计算器...')
|
|
calculator = DecisionCostCalculator.from_config(config.cost_structure)
|
|
cost = calculator.calculate_decision_cost(
|
|
tokens_input=1000,
|
|
tokens_output=500,
|
|
market_data_calls=10
|
|
)
|
|
print(f' 决策成本: ${cost:.4f}')
|
|
print()
|
|
|
|
# 4. 经济追踪器
|
|
print('📊 经济追踪器...')
|
|
tracker = TradingEconomicTracker(
|
|
agent_id='demo-trader',
|
|
initial_capital=10000.0
|
|
)
|
|
print(f' Agent: {tracker.agent_id}')
|
|
print(f' 初始资金: ${tracker.initial_capital:,.2f}')
|
|
print(f' 当前余额: ${tracker.balance:,.2f}')
|
|
print(f' 生存状态: {tracker.get_survival_status().value}')
|
|
print()
|
|
|
|
# 5. TraderAgent
|
|
print('🤖 TraderAgent...')
|
|
agent = TraderAgent(
|
|
agent_id='trader-001',
|
|
initial_capital=10000.0,
|
|
skill_level=0.7
|
|
)
|
|
print(f' Agent ID: {agent.agent_id}')
|
|
print(f' 技能等级: {agent.skill_level:.1%}')
|
|
print(f' 胜率: {agent.win_rate:.1%}')
|
|
print(f' 解锁因子: {agent.state.unlocked_factors}')
|
|
print()
|
|
|
|
# 6. 技术指标
|
|
print('📈 技术指标...')
|
|
import pandas as pd
|
|
import numpy as np
|
|
|
|
# 生成示例数据
|
|
np.random.seed(42)
|
|
prices = pd.Series(100 + np.cumsum(np.random.randn(100) * 0.5))
|
|
|
|
sma20 = sma(prices, 20)
|
|
ema12 = ema(prices, 12)
|
|
rsi_val = rsi(prices, 14)
|
|
macd_result = macd(prices)
|
|
bb_result = bollinger_bands(prices)
|
|
|
|
print(f' 价格数据: {len(prices)} 天')
|
|
print(f' SMA(20): {sma20.iloc[-1]:.2f}')
|
|
print(f' EMA(12): {ema12.iloc[-1]:.2f}')
|
|
print(f' RSI(14): {rsi_val.iloc[-1]:.2f}')
|
|
print(f' MACD: {macd_result["macd"].iloc[-1]:.2f}')
|
|
print(f' 布林带: {bb_result["lower"].iloc[-1]:.2f} ~ {bb_result["upper"].iloc[-1]:.2f}')
|
|
print()
|
|
|
|
# 7. 状态监控
|
|
print('📡 状态监控...')
|
|
monitor = StatusMonitor()
|
|
monitor.register_agent('trader-001', tracker)
|
|
print(f' 监控Agent数: {monitor.agent_count}')
|
|
print(f' 繁荣Agent数: {monitor.thriving_count}')
|
|
print(f' 破产Agent数: {monitor.bankrupt_count}')
|
|
print()
|
|
|
|
# 8. 模拟交易流程
|
|
print('🎮 模拟交易流程...')
|
|
print(' 1. Agent分析市场...')
|
|
print(' 2. 生成交易信号...')
|
|
print(' 3. 执行交易并扣除成本...')
|
|
print(' 4. 更新状态...')
|
|
|
|
# 模拟一次交易
|
|
result = tracker.calculate_trade_cost(
|
|
trade_value=1000.0,
|
|
is_win=True,
|
|
win_amount=50.0
|
|
)
|
|
agent.record_trade(is_win=True, pnl=50.0)
|
|
|
|
print(f' 交易后余额: ${agent.balance:,.2f}')
|
|
print(f' 交易次数: {agent.state.total_trades}')
|
|
print(f' 当前胜率: {agent.win_rate:.1%}')
|
|
print()
|
|
|
|
print('=' * 60)
|
|
print('✅ Phase 2 所有功能验证通过！')
|
|
print('=' * 60)
|