## Features
- Add full Aster DEX integration with Binance-compatible API
- Support Web3 authentication with API wallet system
- Add comprehensive Aster integration guide (ASTER_INTEGRATION.md)
- Add example Aster configuration (config.aster.example.json)
## Bug Fixes
- Fix precision error (code -1111) for all order types
- Implement proper float-to-string conversion with exchange precision
- Add automatic precision fetching from /exchangeInfo endpoint
- Remove trailing zeros from formatted values
## Documentation
- Update README.md with Aster quick start guide
- Add detailed setup instructions for creating API wallet
- Include troubleshooting FAQ and security best practices
- Update core features to mention three supported exchanges
## Technical Details
- Added formatFloatWithPrecision() helper function
- Updated all order functions to use proper precision formatting
- Added precision logging for debugging
- Fully backward compatible with existing configurations
Closes #[issue number if applicable]
Previously, the frontend DecisionRecord type was missing the input_prompt
field that exists in the backend DecisionLog, causing the input context
sent to AI to not be displayed in the UI.
Changes:
- Add input_prompt field to DecisionRecord interface in both type files
- Add collapsible Input Prompt section in DecisionCard component
- Display input_prompt before AI Chain of Thought with blue styling
- Use same expand/collapse interaction pattern as CoT trace
Now users can view both the input context and AI's reasoning process
in the decision cards.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes:
- Updated `docker-compose.yml` to include a new shared volume `frontend-dist` for frontend files.
- Modified the `nofx` service command to copy frontend files to the shared volume.
- Updated `Dockerfile` to use Go 1.25 and added necessary build dependencies for TA-Lib installation.
These changes improve the Docker environment by facilitating shared access to frontend assets and ensuring the build process is up-to-date with the latest Go version.
This update enables users to configure any OpenAI-compatible API endpoint,
allowing the use of:
- OpenAI official API (GPT-4, GPT-4o, etc.)
- OpenRouter (access to multiple models)
- Local deployed models (Ollama, LM Studio, etc.)
- Other OpenAI-format compatible API services
Changes:
- config: Add custom_api_url, custom_api_key, custom_model_name fields
- mcp: Add SetCustomAPI function and ProviderCustom constant
- trader: Update AI initialization logic to support custom API
- manager: Pass custom API config to trader instances
- Add CUSTOM_API.md documentation with usage examples
- Update config.json.example with custom API sample
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes to decision/engine.go:
- Clean up Context struct field alignment for better readability
- Enhance system prompt to include more technical analysis methods:
* Added: technical resistance levels, Fibonacci, volatility bands
* Changed wording from "you can do X" to "you can do but not limited to X"
to encourage AI to use broader range of analysis techniques
This gives the AI decision engine more explicit guidance on available
technical analysis tools while maintaining flexibility.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Previously, ComparisonChart was hardcoded to only fetch equity history
data for the first 2 traders, causing the 3rd and subsequent traders'
data to not be displayed on the chart.
Changes:
- Replaced multiple individual useSWR calls with single consolidated call
- Use Promise.all() to fetch all traders' equity data concurrently
- Generate dynamic cache key based on all trader IDs
- Maintain backward compatibility with existing component structure
- Update useMemo dependencies to properly track data changes
This fix allows the comparison chart to properly display any number of
competing traders, not just 2.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Resolved conflicts in manager/trader_manager.go by combining:
- Upstream: Exchange field, Hyperliquid API keys, Hyperliquid testnet
- Local: BTCETHLeverage and AltcoinLeverage fields
Both features are now working together.
Root cause:
ComparisonChart was calling useSWR hooks dynamically inside a .map() loop,
which violates React's Rules of Hooks. When the traders array length changed
(e.g., from 0 to 2, or during initial load), the number of hook calls would
change between renders, triggering React Error #310.
Previous code:
```tsx
const traderHistories = traders.map((trader) => {
return useSWR(`equity-history-${trader.trader_id}`, ...); // ❌ Dynamic hooks
});
```
The eslint-disable comment on line 24 was masking this critical issue.
Fix:
- Always call exactly 2 useSWR hooks (trader1, trader2) unconditionally
- Pass null as the key when trader doesn't exist (SWR handles this gracefully)
- Build traderHistories array from these fixed hooks
- Ensures same number of hooks called on every render
This follows React's Rules of Hooks:
✅ Only call hooks at the top level
✅ Don't call hooks inside loops, conditions, or nested functions
✅ Call hooks in the same order every render
Fixes: React Error #310 (Rendered more hooks than during previous render)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Root cause analysis:
The previous fix (0cb1f37) only addressed App.tsx Debug Info section,
but missed CompetitionPage.tsx which also directly accesses trader data
fields without null safety checks.
When competition data is loading or incomplete, trader objects may exist
but contain undefined fields (total_pnl, total_equity, etc.), causing:
"TypeError: Cannot read properties of undefined (reading 'total_pnl')"
Fixed locations in CompetitionPage.tsx:
1. Line 76-77: Leader display in header (total_pnl, total_pnl_pct)
2. Line 142: Leaderboard total_equity display
3. Line 151-157: Leaderboard P&L section (total_pnl checks and displays)
4. Line 229-230: Head-to-Head comparison (total_pnl display)
Changes applied:
- Replace direct property access with optional chaining (?.)
- Use nullish coalescing (?? 0) for numeric comparisons
- Add fallback values ('0.00') for undefined fields
- Ensure consistent null safety across all trader data displays
This completes the null safety coverage for the entire frontend.
Fixes: TypeError in CompetitionPage at index-R21Yay1P.js:116:51447
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Previously fixed StatCard components but missed the Debug Info section,
causing "Cannot read properties of undefined (reading 'total_pnl')" error
when account data is loading or incomplete.
Root cause:
- Frontend uses SWR with async data fetching (5s refresh interval)
- During initial load or API delays, account object may exist but fields undefined
- Previous fix (93e331a) only covered StatCard section (lines 369-384)
- Debug Info section (lines 360-362) still used direct property access
Changes:
- Add optional chaining (?.) to all account field accesses in Debug Info
- Add fallback values ('0.00') for undefined fields
- Ensures consistent null safety across all account data displays
This prevents runtime errors during data loading and API failures.
Fixes: TypeError: Cannot read properties of undefined (reading 'total_pnl')
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update Chinese (README.zh-CN.md) with leverage configuration documentation
- Update Russian (README.ru.md) with leverage configuration documentation
- Update Ukrainian (README.uk.md) with leverage configuration documentation
All language versions now include:
- Updated risk management section (fixed → configurable leverage)
- Leverage configuration in JSON examples
- New leverage fields in configuration tables
- Comprehensive leverage configuration section with:
- Configuration format and examples
- Binance subaccount restriction warnings (≤5x)
- Recommended settings for different account types
- Safe and aggressive configuration examples
- Explanation of AI leverage usage
This ensures all users can read the leverage documentation in their preferred language.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Document new configurable leverage feature in Risk Management section
- Add detailed leverage configuration section with examples
- Explain Binance subaccount restrictions (≤5x leverage)
- Provide recommended settings for different account types and risk levels
- Add leverage fields to configuration table
- Include warnings and best practices
Key documentation updates:
- Clear distinction between subaccount (≤5x) and main account limits
- Example configurations for safe, medium, high, and maximum risk levels
- Explanation of how AI uses leverage within configured limits
- Updated default values from fixed 20x/50x to configurable 5x
This documentation helps users safely configure leverage based on their account type.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Pass leverage config through TraderManager to AutoTrader
- Add BTCETHLeverage and AltcoinLeverage fields to Context and AutoTraderConfig
- Update decision validation to use configured leverage limits
- Display configured leverage in startup message
- Update error messages to show current leverage limits
Changes:
- main.go: Pass leverage config to AddTrader, update startup message
- manager/trader_manager.go: Accept and forward leverage config
- trader/auto_trader.go: Store leverage config, pass to Context
- decision/engine.go: Use dynamic leverage limits in validation
This completes the leverage configuration feature implementation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add LeverageConfig struct with btc_eth_leverage and altcoin_leverage fields
- Set default leverage to 5x (safe for Binance subaccounts)
- Add validation warnings for leverage >5x (subaccount restrictions)
- Update config.json.example with leverage configuration
Breaking changes:
- None (backward compatible with default 5x leverage)
Migration:
- Existing configs will auto-default to 5x leverage (safe)
- Main accounts can increase to 20x (altcoins) or 50x (BTC/ETH) in config.json
- Subaccounts must keep leverage ≤5x to avoid trade failures
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Upgrade Dockerfile to Go 1.24 with multi-stage build (backend + frontend)
- Add TA-Lib installation for technical analysis support
- Integrate frontend build into main container image
- Add Nginx reverse proxy configuration for API routing
- Update docker-compose.yml to simplified single-container architecture
- Update .dockerignore to include web source for build
- Improve health checks and startup time handling
Benefits:
- One-click deployment with single Docker image
- Better resource utilization with multi-stage build
- Production-ready Nginx frontend serving
- Easier maintenance and deployment
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major changes:
- Add full Hyperliquid trading support (long/short, leverage, SL/TP)
- Create unified Trader interface for multi-exchange support
- Implement automatic precision handling for orders and prices
- Fix balance calculation and unrealized P&L display
- Add comprehensive configuration guide in README
New features:
- Support for both Binance and Hyperliquid exchanges
- Automatic order size precision based on szDecimals
- Price formatting with 5 significant figures
- Non-custodial trading with Ethereum private key
- Seamless exchange switching via configuration
Technical details:
- Add trader/interface.go for unified trader interface
- Add trader/hyperliquid_trader.go for Hyperliquid implementation
- Update manager and auto_trader to support multiple exchanges
- Add go-hyperliquid SDK dependency
- Fix precision errors (float_to_wire, invalid price)
Fixes:
- Correct calculation of wallet balance and unrealized P&L
- Proper handling of AccountValue vs TotalRawUsd
- Frontend display issues for total equity and P&L
Documentation:
- Add Hyperliquid setup guide in README
- Update config.json.example with both exchanges
- Add troubleshooting section for common errors
Tested with live trading on Hyperliquid mainnet.
No breaking changes - backward compatible with existing configs.
Critical bug fix in Sharpe Ratio calculation logic:
Problem:
- Previously calculated equity as TotalBalance + TotalUnrealizedProfit
- This was incorrect because TotalBalance already stores TotalEquity
- TotalUnrealizedProfit actually stores TotalPnL (not unrealized profit)
- This caused: equity = 2 * TotalEquity - InitialBalance (wrong!)
Root cause:
- Field naming mismatch between AccountSnapshot and actual stored values
- TotalBalance field actually contains TotalEquity (wallet + unrealized)
- TotalUnrealizedProfit field actually contains TotalPnL (equity - initial)
Solution:
- Use TotalBalance directly as it already represents complete account equity
- Added clear comments explaining the field name vs content mismatch
- Sharpe Ratio now correctly calculates risk-adjusted returns
Impact:
- Sharpe Ratio values are now mathematically accurate
- AI performance assessment is now reliable
- No changes needed to data storage or API layer
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Backend changes (logger/decision_logger.go):
- Fixed Profit Factor to use standard formula (total profit / total loss)
- Previously used average values which was incorrect when win/loss counts differ
- Now saves total amounts before calculating averages for accurate ratio
Frontend changes (web/src/components/AILearning.tsx):
- Fixed display units: changed USDT amounts from "%" to "USDT"
- Updated avg_win and avg_loss to show "USDT Average" instead of "%"
- Updated best/worst performer displays to show "USDT" instead of "%"
- Added "(USDT)" labels to table headers for clarity
- Removed "%" from all table data cells showing monetary amounts
This ensures accurate performance metrics and eliminates user confusion
between percentage values and absolute USDT amounts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
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>
