HKUDS / Vibe-Trading

HKUDS / Vibe-Trading

Vibe-Trading: Your Personal Trading Agent

One Command to Empower Your Agent with Comprehensive Trading Capabilities Website · Docs · News · Features · Shadow Account · Demo · Quick Start · Examples · API / MCP · Roadmap · Contributing

Vibe-Trading:您的个人交易智能体

一条指令,赋予您的智能体全面的交易能力 网站 · 文档 · 新闻 · 功能 · 影子账户 · 演示 · 快速入门 · 示例 · API / MCP · 路线图 · 贡献


📰 News

2026-06-28 🧰 Cross-platform setup/dev + runtime and file-tool hardening: vibe-trading setup and vibe-trading dev now handle Windows TypeScript builds, launch the backend from the right cwd, use the Vite 5899 port, and shut child processes down cleanly (#292, thanks @digger-yu). Runtime status polling now degrades instead of crashing (#322); MCP OAuth cache keys are sanitized (#313); OpenAI defaults and Robinhood agent.json validation were tightened (#319, #320, thanks @mvanhorn); and file tools got isolated read/write roots plus broader sandbox tests (#299, thanks @skloxo).

2026-06-28 🧰 跨平台设置/开发 + 运行时与文件工具加固:vibe-trading setupvibe-trading dev 现在支持 Windows TypeScript 构建,从正确的当前工作目录(cwd)启动后端,使用 Vite 5899 端口,并能干净地关闭子进程(#292,感谢 @digger-yu)。运行时状态轮询现在改为降级处理而非崩溃(#322);MCP OAuth 缓存键已清理(#313);OpenAI 默认设置和 Robinhood 的 agent.json 验证已加强(#319, #320,感谢 @mvanhorn);文件工具获得了隔离的读/写根目录以及更广泛的沙箱测试(#299,感谢 @skloxo)。


2026-06-27 🧯 Content-filter resilience + Shadow Account feature contract cleanup: event-driven and swarm runs now skip individual LLM content-moderation hits, warn in run cards when filter rates are high, and recognize Gemini safety finish reasons instead of aborting an entire analysis (#308, closes #307, thanks @shadowinlife). Shadow Account extraction/codegen now share one PRICE_FEATURES contract and keep four-decimal return bounds, preventing rule/codegen drift and precision loss on prior_5d_return (#316, thanks @Robin1987China).

2026-06-27 🧯 内容过滤器韧性 + 影子账户特征契约清理:事件驱动和集群运行现在会跳过个别 LLM 的内容审核拦截,当过滤率过高时会在运行卡片中发出警告,并能识别 Gemini 的安全终止原因,而不是中止整个分析(#308,关闭 #307,感谢 @shadowinlife)。影子账户提取/代码生成现在共享同一个 PRICE_FEATURES 契约,并保持四位小数的收益边界,防止了规则/代码生成偏差以及 prior_5d_return 上的精度损失(#316,感谢 @Robin1987China)。


2026-06-26 🎯 Shadow Account conditional entry + tushare ETF/index/HK routing: extracted Shadow Account rules now carry RSI / prior-return bounds, so the generated SignalEngine enters on real conditions (RSI in range, prior-return in range) instead of blindly replaying the holding cadence (#314, follows #302, thanks @Robin1987China). The tushare loader also routes ETF/LOF → fund_daily(), indices → index_daily(), and HK equities → hk_daily() instead of always calling daily() (which silently returns empty for non-stocks), with per-symbol empty-result + partial-fetch warnings (#315, closes #310, thanks @shadowinlife).

2026-06-26 🎯 影子账户条件入场 + tushare ETF/指数/港股路由:提取的影子账户规则现在携带 RSI / 前期收益边界,因此生成的 SignalEngine 会在真实条件(RSI 在范围内,前期收益在范围内)下入场,而不是盲目地重放持仓节奏(#314,继 #302,感谢 @Robin1987China)。tushare 加载器现在将 ETF/LOF 路由至 fund_daily(),指数路由至 index_daily(),港股路由至 hk_daily(),而不是总是调用 daily()(该函数对非股票标的会静默返回空值),并增加了针对每个标的的空结果 + 部分抓取警告(#315,关闭 #310,感谢 @shadowinlife)。


2026-06-25 🧪 Strict validation JSON + calmer agent context: standalone backtest validation now normalizes nested NaN / Infinity values before writing artifacts/validation.json or CLI stdout, so strict JSON parsers no longer choke on validation payloads (#306, thanks @gyx09212214-prog). The agent prompt also derives the current data-source count from the loader registry, and _microcompact() now waits for real token pressure instead of clearing older tool results during short runs (#296, closes #282, thanks @MarkfuGod).

2026-06-25 🧪 严格的 JSON 验证 + 更稳定的智能体上下文:独立的回测验证现在会在写入 artifacts/validation.json 或 CLI 标准输出之前,对嵌套的 NaN / Infinity 值进行归一化处理,从而使严格的 JSON 解析器不再因验证负载而报错(#306,感谢 @gyx09212214-prog)。智能体提示词现在从加载器注册表中获取当前数据源数量,且 _microcompact() 现在会等待真正的 Token 压力,而不是在短时间运行期间清除旧的工具结果(#296,关闭 #282,感谢 @MarkfuGod)。


2026-06-24 🎯 Shadow Account price context + reactive Chinese UI + LAN auth fix: Shadow Account rule extraction now sees PIT-safe entry context — entry_rsi14 and prior_5d_return fetched through the loader registry as of buy_dt, with graceful offline/no-data degradation (#302, follows #295, thanks @Robin1987China). The main Web UI panels now use reactive English / zh-CN translations across charts, chat, Alpha Library, Correlation, and Run Detail (#301, thanks @skloxo). Remote same-origin Web UI deployments with API_AUTH_KEY can post and upload again after the CSRF hardening, while mismatched cross-site origins remain blocked (#304, thanks @Hinotoi-agent).

2026-06-24 🎯 影子账户价格上下文 + 响应式中文 UI + 局域网认证修复:影子账户规则提取现在可以看到 PIT(点对点)安全的入场上下文——通过加载器注册表在 buy_dt 时获取 entry_rsi14prior_5d_return,并具备优雅的离线/无数据降级处理(#302,继 #295,感谢 @Robin1987China)。主要的 Web UI 面板现在在图表、聊天、Alpha 库、相关性分析和运行详情中支持响应式的英文/中文翻译(#301,感谢 @skloxo)。在 CSRF 加固后,使用 API_AUTH_KEY 的远程同源 Web UI 部署可以再次进行 POST 和上传操作,而不匹配的跨站来源仍被拦截(#304,感谢 @Hinotoi-agent)。


2026-06-23 🛡️ Local API CSRF hardening: a malicious web page can no longer drive unsafe cross-site requests (POST/PUT/DELETE) against the loopback API — CORS blocks reading the response but not the side effect, so loopback dev-mode trust now applies the existing cross-site guard to unsafe methods before honoring it. Safe methods and local CLI / non-browser uploads are unaffected (#293, thanks @Hinotoi-agent).

2026-06-23 🛡️ 本地 API CSRF 加固:恶意网页现在无法再针对回环(loopback)API 发起不安全的跨站请求(POST/PUT/DELETE)—— CORS 虽然阻止了读取响应,但无法阻止副作用,因此回环开发模式的信任机制现在会在执行前对不安全的方法应用现有的跨站防护。安全方法以及本地 CLI / 非浏览器上传不受影响(#293,感谢 @Hinotoi-agent)。


2026-06-22 🔧 Live-authorize OAuth fix + Alpha Zoo headline fix: connector authorize now holds the OAuth handshake open through a multi-minute broker sign-in (tunable via VIBE_LIVE_AUTHORIZE_TIMEOUT_SECONDS) and no longer spawns a competing callback server on retry, so the token actually persists (#281, closes #259, thanks @Robin1987China). The Alpha Zoo page no longer prints its alpha count twice (#287, closes #286, thanks @digger-yu). Scheduled research also picked up end-to-end usage docs (#288).

2026-06-22 🔧 实时授权 OAuth 修复 + Alpha Zoo 标题修复:连接器授权现在可以在长达数分钟的券商登录过程中保持 OAuth 握手开启(可通过 VIBE_LIVE_AUTHORIZE_TIMEOUT_SECONDS 调节),并且在重试时不再生成竞争的回调服务器,从而确保 Token 能够持久保存(#281,关闭 #259,感谢 @Robin1987China)。Alpha Zoo 页面不再重复打印 Alpha 数量(#287,关闭 #286,感谢 @digger-yu)。计划研究功能也增加了端到端的使用文档(#288)。


2026-06-21 ⏰ Scheduled-research executor + Reports library + post-backtest attribution: scheduled research now runs end to end — a default-off background executor (VIBE_TRADING_ENABLE_SCHEDULER) fires due interval/cron jobs through the session runtime (#278, thanks @mvanhorn, closing #254). A new /reports Run Library page lists, searches, and filters report-worthy runs with links into Run Detail + Compare (#224, thanks @LemonCANDY42). And after every backtest the agent now runs layered attribution — trade-level winners/losers, beta regression, market-regime analysis, and a Monte Carlo permutation test, gated by data availability and routing (#280, thanks @shadowinlife).

2026-06-21 ⏰ 计划研究执行器 + 报告库 + 回测后归因分析:计划研究现在可以端到端运行——一个默认关闭的后台执行器(VIBE_TRADING_ENABLE_SCHEDULER)通过会话运行时触发定时/Cron 任务(#278,感谢 @mvanhorn,关闭 #254)。新增的 /reports 运行库页面可以列出、搜索和筛选值得报告的运行记录,并提供指向“运行详情”和“对比”的链接(#224,感谢 @LemonCANDY42)。此外,在每次回测后,智能体会进行分层归因分析——包括交易层面的盈亏、Beta 回归、市场机制分析以及蒙特卡洛置换检验,并受数据可用性和路由控制(#280,感谢 @shadowinlife)。


2026-06-20 🔬 Research Autopilot loop closes (Phase 3) + loader OHLC integrity guard + 4 academic alphas: Research Autopilot now runs hypothesis → signal-engine → backtest end to end — scaffold_signal_engine writes a contract-correct engine and link_autopilot_backtest feeds run metrics back to the hypothesis (68 tools) (#267). A structural OHLC sanity check drops dirty bars (high < low, non-positive prices, bad bracketing) centrally at the loader boundary, guarding every data source (#274, thanks @Shizoqua). And the academic alpha family grows 6 → 10 — Jegadeesh reversal, George-Hwang 52-week-high, Amihud illiquidity, Harvey-Siddique skew (456 factors) (#277, thanks @Robin1987China).

2026-06-20 🔬 研究自动驾驶闭环(第三阶段)+ 加载器 OHLC 完整性防护 + 4 个学术 Alpha 因子:研究自动驾驶现在可以实现“假设 → 信号引擎 → 回测”的端到端运行——scaffold_signal_engine 编写符合契约的引擎,link_autopilot_backtest 将运行指标反馈回假设(68 个工具)(#267)。结构化的 OHLC 合理性检查在加载器边界处集中剔除脏数据(最高价 < 最低价、非正价格、错误的括号),保护每一个数据源(#274,感谢 @Shizoqua)。学术 Alpha 因子家族从 6 个增加到 10 个——包括 Jegadeesh 反转、George-Hwang 52 周高点、Amihud 非流动性、Harvey-Siddique 偏度(共 456 个因子)(#277,感谢 @Robin1987China)。


2026-06-19 🚀 v0.1.10 — Global data layer: market-data sources grow 10 → 18 (free Eastmoney / Sina / Stooq / Yahoo + key-gated Finnhub / Alpha Vantage / Tiingo / FMP, ban-risk fallback) plus 18 read-only data tools (fund flow, dragon-tiger, northbound, margin, block trades, SEC EDGAR + XBRL, financials, options chains, full-market screening…) across A-share / US / HK, all over MCP. Also bundles everything since 0.1.9 — 10 broker connectors, alpha compare, the provider-reliability…

2026-06-19 🚀 v0.1.10 — 全球数据层:市场数据源从 10 个增加到 18 个(免费的东方财富 / 新浪 / Stooq / Yahoo + 需要 Key 的 Finnhub / Alpha Vantage / Tiingo / FMP,具备封禁风险回退机制),外加 18 个只读数据工具(资金流向、龙虎榜、北向资金、融资融券、大宗交易、SEC EDGAR + XBRL、财务数据、期权链、全市场筛选等),覆盖 A 股 / 美股 / 港股,全部通过 MCP 实现。同时整合了自 0.1.9 以来的所有更新——10 个券商连接器、Alpha 对比、提供商可靠性…