7 Commits

Author SHA1 Message Date
GifariKemal e8355b3f62 feat: add 5 dashboard features — dark mode, trade history, backtests, model insights, alerts
- Dark mode: class-based theme toggle with localStorage persistence and flash prevention
- Trade History (/trades): paginated table, stats cards, equity curve chart with DB API endpoints
- Backtest Viewer (/backtests): log parser for 35 backtest results, sidebar + detail + comparison tabs
- Model Insights: dashboard card + dialog showing feature importance, regime distribution, training history
- Alert/Signal Log (/alerts): signal stats, filterable table with execution tracking
- API: 8 new endpoints with psycopg2 DB connection pool
- Dark mode sweep across books page, about dialog, and all dashboard components
- Architecture docs rewritten with Mermaid diagrams (23 docs)
- README and FEATURES.md rewritten bilingual (Indonesian + English)
- main_live.py: write model_metrics.json on startup and retrain

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-09 05:46:54 +07:00
GifariKemal 757b499033 docs: sync architecture docs with v5 major issues fix
5 major issues reflected in documentation:

1. Confidence calibration (03-SMC, 00-ARSITEKTUR):
   - Base 55% + 10% each → base 40% + weighted scoring
   - Structure +15%, BOS/CHoCH +12%, FVG +8%, OB +10%, Trend +10%

2. ATR-based pullback filter (09-Entry, 00-ARSITEKTUR):
   - Hardcoded $2/$1.5 → bounce 15% ATR, consolidation 10% ATR

3. Smarter time-based exit (10-Exit, 05-Risk, 00-ARSITEKTUR):
   - 4h: check profit growth, not just profit<$5
   - 6h: extend to 8h if profit>$10 and growing + ML agrees

4. Slippage validation (09-Entry, 23-Main, 00-ARSITEKTUR):
   - Check actual vs expected price, log if >0.15%

5. Partial fill handling (09-Entry, 23-Main, 00-ARSITEKTUR):
   - Check filled volume, use actual values for tracking

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 10:06:43 +07:00
GifariKemal e0ef14b08f docs: update comprehensive architecture doc to match v4 source code
- Loop: ~1 detik → candle-based (M15) + position check ~10 detik
- Exit Kondisi 3: Golden Time Hold → Early Cut (Smart Hold dihapus)
- AUC rollback threshold: 0.52 → 0.60
- Train/test: tambah 50-bar gap info
- Timer periodik: candle-based intervals
- Performance: split full analysis vs position-check-only
- Golden Time: hapus referensi hold losers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 09:51:50 +07:00
GifariKemal 092926415c chore: add training data, backups, and research docs
- Add model backups from training sessions
- Add training data parquet file
- Add risk state persistence file
- Add research documents (Gemini analysis)
- Update architecture docs

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 09:44:49 +07:00
GifariKemal 07e12f5229 docs: add comprehensive full architecture document (00-ARSITEKTUR-LENGKAP.md)
Complete system architecture in 1 document covering:
- System overview with 3 AI brains (SMC + XGBoost + HMM)
- Full architecture diagrams and data flow
- All 23 components table and relationships
- Data pipeline: OHLCV → Features → SMC → HMM → XGBoost → Decision
- 11 entry filters detailed flow
- 10 exit conditions detailed flow
- 4-layer risk protection system (Broker SL → Software → Emergency → Circuit Breaker)
- 4 trading modes (Normal → Recovery → Protected → Stopped)
- Kelly Criterion lot sizing with ML confidence boost
- SMC concepts explained (Swing, FVG, OB, BOS, CHoCH, Liquidity)
- Position lifecycle from signal to close
- Auto-retraining & model management
- Database schema & graceful degradation
- All configuration parameters & session schedule
- Performance targets (~50ms per loop)
- Error handling & fault tolerance (6 levels)
- Complete source code file listing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 09:27:33 +07:00
GifariKemal a240d974f6 docs: add architecture documentation for remaining 8 components (16-23)
New documentation files:
- 16-MT5-Connector: Broker bridge with auto-reconnect & Polars native
- 17-Configuration: 6 sub-configs with capital mode auto-adjustment
- 18-Trade-Logger: Dual storage (PostgreSQL + CSV), thread-safe
- 19-Position-Manager: 7 action conditions, trailing SL, market close handler
- 20-Risk-Engine: Kelly Criterion sizing, circuit breaker, order validation
- 21-Database: PostgreSQL integration with 6 repositories
- 22-Train-Models: Initial training script (HMM + XGBoost)
- 23-Main-Live-Orchestrator: Main loop coordinating 15+ components

Updated README.md with complete index of all 23 components.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 09:17:20 +07:00
GifariKemal 7af9183af3 feat: Smart AI Trading Bot for XAUUSD with ML and SMC
- XGBoost ML model with 37 features for market direction prediction
- Smart Money Concepts (SMC): Order Blocks, FVG, BOS, CHoCH
- HMM market regime detection (trending/ranging/volatile)
- ATR-based stop loss with 1.5 ATR minimum distance
- Broker-level SL protection with fallback
- Time-based exit (max 6 hours per trade)
- Session-aware trading optimized for London/NY overlap
- Auto-retraining based on market conditions
- Telegram notifications and web dashboard
- Backtest results: 63.9% win rate, 2.64 profit factor, 4.83 Sharpe

Backtest period: Jan 2025 - Feb 2026, 654 trades, $4,189 net P/L

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 09:01:35 +07:00