RightNow-AI/openfang v0.3.45

v0.3.45 — Trading Hand + Bug Fixes

on GitHub

New: Trading Hand (8th Bundled Hand)

Full autonomous trading agent built from extensive market research on what traders actually need in 2026.

Architecture

• HAND.toml (740 lines) — 12 configurable settings, 10 dashboard metrics, 470-line system prompt with 8-phase pipeline:

  1. State Recovery — restore position/context on restart
  2. Portfolio Setup — read config, validate risk parameters
  3. Market Intelligence Scan — gather data from free sources (Yahoo Finance, FRED, Fear & Greed Index)
  4. Multi-Factor Analysis — technical (RSI/MACD/Bollinger/VWAP/ATR), fundamental, sentiment, macro
  5. Adversarial Bull/Bear Debate — structured debate with entry zones, stop-loss, take-profit, R:R ratios
  6. Risk Management Gate — circuit breakers, position sizing caps, drawdown limits, correlation checks
  7. Trade Execution — three modes: analysis-only, paper trading, live via Alpaca API
  8. Analytics & Reporting — structured tables for dashboard metrics

• SKILL.md (937 lines) — Expert reference material:

  • RSI/MACD/Bollinger/VWAP/ATR formulas with interpretation guides
  • 22 candlestick pattern definitions
  • Position sizing + Kelly criterion + Value-at-Risk calculations
  • Full Alpaca API reference (discovered they have an official MCP server)
  • Free financial data sources catalog
  • Superforecasting calibration guide
  • Cognitive bias mitigations for trading decisions

Settings

• trading_mode (analysis/paper/live), risk_per_trade (default 2%), max_portfolio_pct (10%), watchlist, alpaca_api_key, preferred_timeframe, report_frequency, max_daily_trades, stop_loss_atr_multiplier, take_profit_atr_multiplier, circuit_breaker_drawdown, rebalance_interval

Live-Tested Behaviors

• Refuses to bypass risk management (100% portfolio / no stop-loss = rejected)
• Calculates position sizing correctly including cap violation detection
• Produces adversarial bull/bear debates with concrete price levels
• Generates structured Phase 7 reports with dashboard-ready tables
• Pause/resume/deactivate lifecycle works correctly

Bug Fixes

• #503 — Streaming <think> tag leak: Created StreamingThinkFilter that processes text deltas incrementally, buffering reasoning content so it never reaches the client during streaming. Handles partial tags split across chunks. 17 new tests.
• #504 — Cron jobs orphaned after agent deletion: kill_agent() now calls remove_agent_jobs() on the cron scheduler and persists the change to disk. 3 new tests.

Stats

• 2031 tests, 0 clippy warnings, 8 bundled hands, 184 models, 40 providers

Full Changelog: v0.3.44...v0.3.45