HKUDS/Vibe-Trading

English | 中文 | 日本語 | 한국어 | العربية | Español | Bahasa Indonesia

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

---

📰 News

⚠️ Security warning: The X account VibeTrading_HKU, Virtuals project 101845, and token contract 0x640BDBF77b6447E8b7DB7894cED84BD1c40571f4 are not official Vibe-Trading assets. We have never launched or endorsed any token or memecoin. Do not buy, connect a wallet, or sign anything. Details.

• 2026-10-30 🛠️ Channel reliability and A-share sizing (unreleased): Voice notes reach the agent as attachments in Telegram, Feishu, Matrix and Weixin; STAR and Beijing backtests follow their board-specific minimum sizes and one-share increments. Add path-containment regressions. (#2106, #2105, #2094). Follow-up: stream cancellation and retry/cache accounting, scoped background recovery, evidence-preserving research-goal edits, and Discord overflow fixes. A-share 5m paper steps now match bar by bar; saved accounts remain daily-only. Optional Parallel search is off by default. (#2099, #2109, #2111, #2113).
• 2026-10-29 🛠️ Research reuse and execution fixes (unreleased): Save versioned research artifacts and reuse manifest-checked prior backtests (#2079, #2074).

Fix document amounts/units and spot-crypto costs; restore Binance open orders and AKShare compatibility (#2050, #2088, #2090, #2083). Also add Codex model discovery, BYMA rules, background-owner isolation and shared tool policy. Paper strategies use private worker pipes; native Windows confirmation remains pending (#2089, CHANGELOG).

• 2026-10-28 🛠️ Paper trading, portfolio and market-routing fixes (unreleased): Add the phase-1 bar-agnostic paper-order lifecycle state machine with stable replay IDs, fail-closed cancellation, day settlement, optional partial fills and deterministic snapshots (#2066). Robinhood's read-only portfolio source now carries explicit account selection, quote mapping and cursor pagination (#2054; closes #1428). Fix Shadow Account cache invalidation and documented entry conditions (#2075, #2073); map US symbols for Futu and configure IBKR/Futu gateway endpoints (#2076, #1983). Also restore structured two-turn finals, Qlib factor semantics and numeric/grounding input boundaries (#2064, #2069, #2072, #2053). These fixes are on main for the next release.
• 2026-10-27 🛠️ Portfolio connections and research correctness (unreleased): Save connection-specific IBKR/Futu gateway addresses through Web or CLI, and use them for agent reads (#1983). Robinhood portfolio reads support account selection, pagination and equity quotes; follow-up checks bind quotes to the requested symbol, select the newer regular/extended-hours trade and show its as-of time (#2054, 011a555ed). Restore Qlib ROC/CORD formulas and enforce documented shadow-strategy entry bounds (#2069, #2073). Preserve financial units and numeric evidence, keep currency declarations within their own object, reject non-finite/boolean financial inputs, and accept ordinary two-turn claude-cli structured finals (#2072, #2053, #2064). These changes are on main for the next release.

Earlier news

• 2026-10-26 🛠️ Agent cancellation, grounding and market-correctness fixes (unreleased): Stopping a chat turn cancels in-flight Swarm runs and ignores late status events (#2059, #2060). Restore trailing OLS definitions for Qlib BETA/RESI, admit eligible document figures to the evidence ledger, and recover from refused native claude-cli tool attempts (#2062, #2058, #2048). Add field-level alpha-bench availability metadata; correct weight overflow, event-study rank scaling and attribution alignment (#2057, #2046, #2000, #2044). Also fix Moonshot reasoning-effort routing, journal/options input validation, Stooq class-share symbols, screener decimal fields and ST board limits (#2043, #2052, #2049, #2012, #1988, #1984). These changes are on main for the next release.
• 2026-10-25 🛠️ Session, market-data and calculation fixes (unreleased): Deleting a session also removes its search entries, and chat titles update correctly when the first message includes attachments or Swarm instructions (#1970, #1969). Fix prematurely truncated CCXT history, Nobitex daily dates and Tiingo class-share symbols (#1999, #1989, #2010). Preserve small trade/chart prices, correct GTJA factor formulas and VWAP units, and reject ambiguous boolean flags before changing state (fix). These fixes are on main for the next release.
• 2026-10-24 🛠️ MCP, backtest and search fixes (unreleased): MCP loads the runtime .env, while shell tools still require explicit opt-in at startup (#1974). Report assumed futures leverage (#1972), preserve fractional-day spans in annualization (#1971), and try enabled Sogou/Bing fallbacks when ddgs returns no results (fix).
• 2026-10-23 🛠️ Model, portfolio and futures fixes (unreleased): Direct MiniMax connections default to M3.1 Flash and retain reasoning across tool calls (#1936). Longbridge exposes cash by currency and financing limits across Agent, CLI, API and Web (#1940). Correct global futures routing, contract multipliers and micro-contract fees, with explicit warnings when pricing defaults are used (#1965). Also fix portfolio error redaction, audit rotation, IC statistics, numeric parsing and Weixin attachment collisions. Details in CHANGELOG.
• 2026-10-22 🚀 v0.1.18 released (Release notes, pip install -U vibe-trading-ai): a leaner agent runtime — tool schemas load on demand, oversized results stay readable in the run directory, Swarm keeps new observations, and usage accounting covers compaction and interrupted calls; automatic chat titles remain. On the 0.1.17 verification backtest it used 7 model calls instead of 12 and about a fifth of the input tokens. It also ships the post-0.1.17 security, grounding, paper-account and packaging fixes. Fixed on main today (next release): a retried provider error no longer halts live model decisions for the rest of the day, and a research goal's final answer is delivered even when it crosses the goal's token budget (CHANGELOG).
• 2026-10-21 🚀 v0.1.17 released (Release notes, pip install -U vibe-trading-ai): 638 commits and 228 merged pull requests since 0.1.16, plus 41 pull requests whose work landed through maintainer commits, from 33 contributors. The headline is daily paper trading: a paper_trade_step tool for the agent and MCP, plus saved paper accounts through vibe-trading paper, the REST API and a Web page, match orders or a strategy against completed daily bars without ever reaching a broker; saved accounts move forward only (#1939). Most of the rest is correctness, and much of it has one shape: a value that cannot be computed now says so instead of turning into a plausible number. A profit factor with no losing trade, an undefined correlation and an unbounded ratio come back as null, and a factor with too few IC observations is skipped with the reason; a missing price no longer bridges a return; a misspelled or engine-irrelevant backtest setting is reported in the run card. New: Brazil (B3), 478 Alpha Zoo factors (from 462), Slack and Discord in the guided channel setup, Email reports as HTML or a password-protectable PDF, token usage in Run Detail, chat and swarm, a claude-cli provider, and Persian and Turkish for 11 UI languages. Fixed today: the fund-flow fallback names its actual source and keeps total flow apart from main-order flow, and the Telegram setup steps are clarified. Shipped the same evening in v0.1.18: mcp>=1.30 closes CVE-2026-59951 for --transport http; custom model endpoints are re-checked on every connection and work behind fake-IP proxies; grounding reads run_dir/… refs and −$ amounts; Beijing 920xxx codes resolve to .BJ in correlation (CHANGELOG). Thanks @rudycelekli, @Shizoqua, @he-yufeng, @shadowinlife, @zeus229, @alexwan02, @Jackzigen, @cgycorey, @MetaAviator, @lorenzozanee, @Mikesad, @remote-controlled-man, @Romzhou, @sambazhu, @wavebyrd, @BHhhh-123, @Bortlesboat, @bygordon130-hub, @davidalmeida90, @DrDLyuan, @Emad211, @Frank-zhu2000, @goatyyc, @hunters1011-ctrl, @incorpore, @mdb1230, @mminkus, @passionbull, @rwxyx518-prog, @ThreeTima, @tomaszkubiak-courses and @xaritoku!
• 2026-10-20 🛠️ Backtest diagnostics and research correctness: Warn about unrecognized backtest config keys, show undefined correlations as unknown instead of zero, and reuse the saved annualisation factor when revalidating runs (#1935, #1933, #1915). Also improve factor sample checks, tool input validation, journal market classification, numeric formatting and WeCom streaming. All 14 fixes and remaining limits are in CHANGELOG.
• 2026-10-19 🛠️ Nine financial correctness fixes: Correct recency weights in factor decay, A-share board limits and Beijing symbol routing, SEC Q4 flow derivation, and event-study estimation windows. Preserve Futu holdings identity and tiny MACD/Bollinger values; reject negative specific variances and apply pair-specific fees to Yahoo forex symbols (#1912, #1920, #1930). See CHANGELOG for all nine fixes and limits.
• 2026-10-18 🛠️ Scheduling and research reliability: Live scheduling adopts the shared scheduler kernel (#1899), and figure checks preserve currency identity (#1905). Add factor neutralization and PCA (#1817); fix incomplete Swarm event tails and lost Matrix final replies. Details in CHANGELOG.
• 2026-10-17 🛠️ Token usage and research reliability: View LLM usage in Run Detail, chat and swarm (#1890). Shared scheduling now powers research and optional background jobs (#1893); live scheduling is unchanged. Fix journal date/time pairing, evidence paths, factor ties, memory roots, numeric error handling and channel progress. See CHANGELOG.
• 2026-10-16 🛠️ Credential safety and financial correctness: Scrub more channel/provider secrets (#1880), refresh cached local bars after source edits (#1879), and allocate reversal fees once (#1891). Correct European journal amounts, strict JSON, zero/negative comparisons, holding periods, weight floors, plateau detection and report paths. See CHANGELOG.
• 2026-10-15 🛠️ Model spending controls and research reliability: Live runners use independent decision sessions with configurable cadence and persistent daily usage budgets (#1854). Lightweight backtest previews preserve complete trade history (#1853, #1865). Fix percentage evidence arithmetic, copied-run history deduplication, swing-signal timing, crypto routing and credential redaction. See CHANGELOG for scope and limits.
• 2026-10-14 🛠️ Backtest, search and document fixes: Risk ratios and equity exports now include first-bar PnL (#1844). Session search returns distinct sessions with preserved titles and contextual snippets (#1827, #1834). Improve PDF/Office extraction, reject unresolved evidence references, and strengthen financial-input validation and credential redaction.
• 2026-10-13 🧩 Portfolio imports, strategy adaptation and research tools: Read-only extraETF holdings imports support dated EUR valuation and allocation proposals; adapted strategies get their own backtest evidence (#1170, #1149). Add tested custom model endpoints, a shared manual Pixel Office task board, Persian/Turkish UI, mStock read-only queries and Gildata research data.

Fix settlement-currency accounting, Futu market selection and cost basis, per-symbol HK board lots, saved validation settings and run progress. Complete declared grounding checks and the agent-loop split. mStock remains excluded from portfolio aggregation; Robinhood options execution remains unavailable. See CHANGELOG for scope and limits.

• 2026-10-12 🧮 Research and backtest updates: Correct opening fills, liquidation-time attribution, drawdown duration, valuation tolerances and SEC filing timing in factor IC (#1780–#1794). Add 13 fundamental/valuation factors, Brazil data and backtests, opt-in ZimaOS templates, and Feishu run progress. See CHANGELOG for scope and data limitations.
• 2026-10-11 🛠️ Five priority fixes: Derived figures require evidence for every data operand; unsupported live options stay blocked. Offline benchmarks retain their selected source, trade artifacts distinguish break-even exits, and Codex tools preserve optional arguments (#1622, #1779, #1781, #1785).
• 2026-10-10 🛠️ Slack/Discord setup and reproducible research: Localized channel forms verify bot credentials without saving changes (#1764, #1777). Portfolio research can reuse an immutable snapshot, and Web exports its sanitized JSON (#1769). Indicators report their date boundary and exact input fingerprint; corrupted session records recover without rewriting files. Memory recall, credential redaction and trade-journal detection are corrected. See CHANGELOG.
• 2026-10-09 🛠️ Channel updates and backtest correctness: Channel settings preserve embedded URL credentials and authenticated WeChat endpoints during in-place updates, with save/reset feedback in all nine languages (#1737, #1742, #1744). Cross-market option volatility uses only timestamps known at each bar; drawdown includes starting capital. Crypto/precious-metal routing, HK duplicate detection, cache recovery, scientific-notation amounts and missing-equity validation are corrected. mootdx leaves the default A-share chain. See CHANGELOG for all thirteen PRs.
• 2026-10-08 🔐 Protected PDF reports and clearer broker reads: Scheduled Email PDFs support optional AES-256 password protection across Web, CLI playbooks and agent confirmations; the password stays in private channel configuration (#1709). KIS queries all three venue buckets, refreshes an explicitly expired token once, and reports incomplete reads as errors (#1726). Derived formulas keep their arithmetic after descriptive labels while evidence checks remain enforced (#1728).
• 2026-10-07 🛠️ Research continuity and reliable risk metrics: Volatile workspace state now travels outside the system prompt, preserving its stable prefix (#1708). Cross-market dates align correctly, missing prices no longer bridge return observations, and options Sortino uses full-sample downside deviation (#1710, #1717, #1727). Loader fixtures share one OHLCV contract; credit valuation, style exposures, walk-forward folds and audit diagnostics are corrected.
• 2026-10-06 🛠️ Live controls and report corrections: Stopping a live runner cancels its current analysis and wa