Fixed critical issues in historical trade record and performance analysis:
1. PnL Calculation: Changed from percentage-only to actual USDT amount
- Now correctly calculates: positionValue × priceChange% × leverage
- Previously: 100U@5% and 1000U@5% both showed 5.0
- Now: Properly reflects different position sizes and leverage
2. Position Tracking: Added quantity and leverage to open position records
- Store complete trade data for accurate PnL calculation
- Previously only stored: side, openPrice, openTime
- Now includes: quantity, leverage for proper accounting
3. Position Key: Fixed to distinguish long/short positions
- Changed from symbol to symbol_side (e.g., BTCUSDT_long)
- Prevents conflicts when holding both long and short positions
4. Sharpe Ratio: Replaced custom Newton's method with math.Sqrt
- Simplified standard deviation calculation
- More reliable and maintainable
Impact: Win rate, profit factor, and Sharpe ratio now based on accurate USDT amounts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove prescriptive indicator combinations and let AI freely use all available data.
**Changes**:
- Emphasized AI has access to **raw sequence data** (MidPrices array, 4h candles)
- Listed all available sequences: price, technical (EMA/MACD/RSI), and capital flow (volume/OI)
- Removed hard-coded indicator combinations (e.g., "MACD + RSI + Volume")
- Changed from prescriptive examples to open-ended analysis freedom
- AI can now freely perform trend analysis, pattern recognition, support/resistance calculation
- Reduced minimum close-open interval from 30min to 15min for more flexibility
**Before**:
```
强信号示例:
- 趋势突破 + 多个指标确认（MACD + RSI + 成交量）
- 持仓量暴增 + 价格突破关键位
```
**After**:
```
你拥有的完整数据：
- 📊 原始序列：3分钟价格序列(MidPrices数组) + 4小时K线序列
- 📈 技术序列：EMA20序列、MACD序列、RSI7序列、RSI14序列
- 💰 资金序列：成交量序列、持仓量(OI)序列、资金费率
分析方法（完全由你自主决定）：
- 自由运用序列数据，你可以做趋势分析、形态识别、支撑阻力计算
- 多维度交叉验证（价格+量+OI+指标+序列形态）
- 用你认为最有效的方法发现高确定性机会
```
**Philosophy**: Trust AI to discover effective patterns in raw data rather than constraining it to pre-defined indicator combinations.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Track and display how long each position has been held to help AI make better timing decisions.
**Implementation**:
- Added UpdateTime field to PositionInfo struct (decision/engine.go:26)
- Added positionFirstSeenTime map to AutoTrader for tracking (trader/auto_trader.go:60)
- Record opening time when position is created successfully:
- executeOpenLongWithRecord: Records timestamp for long positions (trader/auto_trader.go:540-541)
- executeOpenShortWithRecord: Records timestamp for short positions (trader/auto_trader.go:593-594)
- Fallback tracking in buildTradingContext for program restart scenarios (trader/auto_trader.go:386-392)
- Auto-cleanup closed positions from tracking map (trader/auto_trader.go:409-414)
- Display duration in user prompt with smart formatting:
- Under 60 min: "持仓时长25分钟"
- Over 60 min: "持仓时长2小时15分钟"
**Example Output**:
```
1. TAOUSDT LONG | 入场价435.5300 当前价433.1900 | 盈亏-0.54% | 杠杆20x | 保证金25 | 强平价418.1528 | 持仓时长2小时15分钟
```
**Benefits**:
- AI can see how long positions have been held
- Helps enforce minimum holding period (30-60 min) from system prompt
- Simple implementation with minimal overhead
- Auto-cleanup prevents memory leaks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements to the AI trading decision engine:
**Core Changes in decision/engine.go** (175 lines modified):
1. **Sharpe Ratio Optimization Focus**
- Restructured system prompt to emphasize Sharpe ratio maximization
- Added clear guidance: high-quality trades over frequent trading
- Explained that 3-minute scan interval ≠ trade every cycle
2. **Trading Frequency Controls**
- Defined optimal frequency: 2-4 trades/day (0.1-0.2 trades/hour)
- Over-trading threshold: >2 trades/hour indicates issues
- Minimum holding period: 30-60 minutes per position
3. **Long/Short Balance Incentives**
- Emphasized equal profit potential for long and short positions
- Removed long-bias with explicit short trading encouragement
- Clear guidance: uptrend→long, downtrend→short, sideways→wait
4. **Stricter Entry Signal Standards**
- Strong signals only: confidence ≥75, multi-indicator confirmation
- Weak signals explicitly discouraged (single indicator, unclear trend)
- Self-check mechanism to prevent premature re-entry (<30min)
5. **Enhanced Sharpe Ratio Feedback Loop**
- Sharpe < -0.5: Stop trading for 6+ cycles (18min), deep reflection
- Sharpe -0.5~0: Strict control, confidence >80 only
- Sharpe 0~0.7: Maintain current strategy
- Sharpe >0.7: Consider position size increase
6. **Risk-Reward Ratio Validation**
- Added hard constraint: R:R must be ≥ 3.0:1
- Automatic calculation and validation in `validateDecision()`
- Rejects trades with insufficient risk-reward ratio
7. **Improved Prompt Structure**
- More organized sections with clear headers
- Actionable guidance instead of abstract principles
- Better examples for JSON output format
**Impact**: These changes should significantly improve trading quality,
reduce over-trading, and increase Sharpe ratio through better risk management
and trade selection discipline.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Full code synchronization from nofx internal repository to open-nofx.
Updated all source files, documentation, and configuration.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Full synchronization of all files from nofx to open-nofx repository.
Updated documentation and source code to match internal version.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Synchronize all source code, documentation, and configuration files
from the internal nofx repository to the open-nofx public repository.
This includes:
- Updated README files (EN/ZH/RU/UK) with Binance registration info
- Latest source code across all modules
- Current dependencies and configurations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update .gitignore to align with nofx configuration
- Sync README files across all languages (EN/ZH/RU/UK)
- Update web/package-lock.json with latest dependencies
This commit synchronizes the open-nofx repository with the latest
changes from the internal nofx version to maintain consistency.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove deprecated files that don't exist in nofx internal version:
- market/ai_decision_engine.go
- market/ai_signal.go
- market/market_data.go
- scanner/ai_scanner.go
Keep only market/data.go to align with internal version structure.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove node_modules directory and update .gitignore:
- Remove all web/node_modules files from git tracking
- Add node_modules/, web/dist/, web/.vite/ to .gitignore
- Remove backup files (*.bak) and empty directories (web/web/)
- Align open-nofx repository structure with nofx internal version
This cleanup ensures the open-source version only contains necessary
source files and proper gitignore configuration.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Architecture improvements:
- Extract AI decision engine to dedicated `decision` package
- Create `mcp` package for Model Context Protocol client
- Separate market data structures into `market/data.go`
- Update trader to use new modular structure
New packages:
- `decision/engine.go` - AI decision logic and prompt building
- `mcp/client.go` - Unified AI API client (DeepSeek/Qwen)
- `market/data.go` - Market data type definitions
Benefits:
- Better separation of concerns
- Improved code organization and maintainability
- Easier to test individual components
- More flexible AI provider integration
- Cleaner dependency management
Updated imports:
- trader/auto_trader.go now uses decision and mcp packages
- Consistent API across different AI providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements:
- Replace useState+useEffect with useMemo for better performance
- Use timestamp-based grouping instead of cycle_number
- Fix data alignment issues when backend resets cycles
- Add detailed console logging for debugging
- Optimize data merging logic with Map structures
Chart updates:
- Display sequence number instead of cycle number on X-axis
- Improve tooltip to show actual time and sequence
- Better handling of multi-trader data synchronization
- More reliable data point matching across traders
Performance:
- Reduce unnecessary re-renders with useMemo
- More efficient data processing with Maps
- Better dependency tracking in hooks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major improvements:
- Use period-level Sharpe ratio (range -2 to +2) instead of annualized
- Save full user prompt in decision logs for debugging
- Format complete market data (3m + 4h candles) for AI analysis
- Prevent position stacking with duplicate position checks
- Update Sharpe ratio interpretation thresholds
Market data enhancements:
- Display full technical indicators in user prompt
- Include 3-minute and 4-hour timeframe data
- Add OI (Open Interest) change and funding rate signals
Risk control:
- Block opening duplicate positions (same symbol + direction)
- Suggest close action first before opening new position
- Prevent margin usage from exceeding limits
UI improvements:
- Update multi-language translations
- Refine AI learning dashboard display
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Problem: When TotalTrades == 0 (no completed trades), formatPerformanceFeedback
would return early, hiding Sharpe ratio and adaptive behavior recommendations
from AI's prompt. This caused AI to say "no historical data" even though Sharpe
ratio was calculated and displayed on frontend.
Solution:
- Display Sharpe ratio BEFORE checking TotalTrades
- Don't return early when TotalTrades == 0
- Always show adaptive behavior recommendations if Sharpe ratio exists
- Sharpe ratio is calculated from account equity changes, not just closed trades
Impact: AI can now properly use Sharpe ratio for self-evolution, even in early
stages before any trades are closed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implement Sharpe ratio calculation in decision logger
- Add adaptive behavior recommendations based on Sharpe ratio
- Display Sharpe ratio in AI learning dashboard with visual indicators
- Enable AI to adjust trading strategy based on risk-adjusted returns
- Color-coded performance levels (red/yellow/green) for easy monitoring
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Split AI prompts into system (cacheable) and user (dynamic) messages
- Add confidence and risk_usd fields to trading decisions
- Reduce temperature to 0.5 for more stable JSON output
- Add retry mechanism for AI API calls
- Simplify candidate display (show top 10 only)
- Improve prompt structure for better AI decision quality
- Replace regex-based quote fixing with simple character replacement
- Add Twitter/X contact link to all README versions
- Remove complex regex pattern for better performance
- Fix Chinese quote mark handling in AI responses
- Add focused position strategy (max 3 concurrent positions)
- Increase position sizes for better capital efficiency
- Add historical reflection prompts for AI learning
- Fix JSON parsing with missing quotes in reasoning field
- Update position limits and leverage recommendations
- Enhance risk management with concentrated positions
- Add language context and translation system (Chinese/English)
- Enhance UI components with i18n support
- Update AILearning, EquityChart, and CompetitionPage
- Add language toggle in header
- Improve user experience with localized text
- Frontend trading records and UI enhancements
- Optimized AI prompts and decision engine
- Performance analysis and comparison features
- Binance-style UI improvements
- Remove hardcoded API URL and auth token from pool/coin_pool.go
- Update config.json.example with placeholder format
- Credentials should now be configured via config.json file
- Add English README.md with language switcher
- Add Chinese README.zh-CN.md (中文版)
- Add Ukrainian README.uk.md (Українська версія)
- Add Russian README.ru.md (Русская версия)
- Each README includes language navigation links
- Covers all core features, installation, and usage
- Multi-AI competition mode (Qwen vs DeepSeek)
- Binance Futures integration
- AI self-learning mechanism
- Professional web dashboard
- Complete risk management system
