trading 6

DeepSeek Harness bundle wiring the dsh-trading research stack into a profile

DSH (DeepSeek Harness) plugin for investment decisions: evidence-gated research, a forced bull/bear debate, Python-settled outcomes the model cannot grade, and the Decision Mind tab that pins every real trade to its plan and T+1 verdict

🐳 The Everything-Plugin Quant OS — AI-native & DSH-native: 46 tools, 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET pipeline. Methods open, secrets internal.

dsh plugin: quantitative tools for agents — market data (Binance public API), technical indicators (SMA/EMA/RSI/MACD/Bollinger/ATR) and MA-crossover backtest, with structured canonical outputs consumable from Code Mode

SparkElf-maintained fork of dsh-quant: AI-native & DSH-native quant toolkit — 59 tools across 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET research pipeline. Fork adds A-share-correct annualization, cross-sectional IC, and u

在对话中直接渲染交易图表：trade_chart 工具 + 内联 SVG 图表卡片（K线/折线/柱状/面积，含成交量副图、MA/EMA/BOLL 主图指标、MACD/RSI/KDJ 副图指标、波段与自由标注、滚轮缩放平移），数据来自行情技能（longbridge / hithink）。