diff --git a/CHANGELOG.md b/CHANGELOG.md index 11e594a2c..291769b30 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,37 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html). Changes that need action when upgrading are listed under "Upgrading from" in their release. +## [0.7.1] — 2026-10-27 + +Decisions are scored only on final closes and settle across long market holidays, a model's unpadded date no longer reads filings made after the run date, and fixes to portfolios, prices, SEC statements, reports, Azure and Claude settings. + +### Upgrading from 0.7.0 + +- Docker images no longer include `.env.enterprise`. For Azure OpenAI in Docker, put its keys in `.env`. + +### Fixed + +- A date a model passes without zero padding, such as `2024-7-5`, is read as that date. It could compare as later than a filing made after the run date, and SEC EDGAR then served that filing. (#1488) +- A decision is no longer scored on the bar of a session still trading, and one made before a market closure longer than a week, such as a national holiday, settles once trading resumes instead of staying pending. (#1548, #1539) +- A backtest reports the failures of its last settlement pass, and two started in the same second no longer share one run. (#1557, #1549) +- A holding listed under a broker's spelling (`BTCUSDT`, `700.HK`) is matched to the instrument analyzed, and a portfolio number that is not finite is refused when the file loads. (#1556, #1509) +- Prices keep their significant digits: a sub-cent close no longer prints as 0.00, and a currency pair keeps its pips. (#1567) +- SEC EDGAR statements list one row per period, so a model no longer reads a figure against the wrong quarter across a long history, and a figure under one million no longer prints as 0. (#1517, #1589) +- Saving a report to a folder used before removes the earlier run's sections. (#1566) +- A date window that ends before it starts is sent back to the model instead of returning no data. (#1595) +- A statement frequency other than annual or quarterly is sent back to the model instead of being served annual figures under that word. (#1593) +- The memory's most recent lessons, and the entries rotation keeps, follow decision dates, so a backfill of older dates no longer displaces them. (#1603) +- Prediction-market odds near 0% or 100% show their distance from it to two significant digits. (#1598) +- Azure OpenAI receives `max_tokens` and a configured endpoint. (#1584, #1600) +- Claude's effort setting is decided correctly for dated model IDs such as `claude-sonnet-4-20250514`. (#1585) +- The CLI checks a ticker with the same rule as the run, so `XAUUSD+` is accepted and `..` is refused at the prompt. (#1604) +- Docker images no longer include `.env` files from any folder. +- Tests that failed on Windows and macOS for platform reasons are fixed. (#1506, #1485, #1541) + +### Contributors + +[@alanfate3](https://github.com/alanfate3), [@aranlucas](https://github.com/aranlucas), [@BichengWang](https://github.com/BichengWang), [@Bortlesboat](https://github.com/Bortlesboat), [@hoffman988](https://github.com/hoffman988), [@jhill-cmd](https://github.com/jhill-cmd), [@muhib-karim](https://github.com/muhib-karim), [@pei711](https://github.com/pei711), [@peiji1981](https://github.com/peiji1981), [@rudycelekli](https://github.com/rudycelekli), [@Shubham-Padkonde](https://github.com/Shubham-Padkonde), [@stevexyz2003](https://github.com/stevexyz2003), [@SuperMarioYL](https://github.com/SuperMarioYL), [@sytfly](https://github.com/sytfly), [@yuv009](https://github.com/yuv009). + ## [0.7.0] — 2026-10-16 Runs on your ChatGPT plan, backtests scored from the first close after each decision, a note at start-up when a newer release is out, and a wheel attached to each GitHub release. diff --git a/README.md b/README.md index 893424ff2..a9ddf10db 100644 --- a/README.md +++ b/README.md @@ -32,15 +32,16 @@ ## News +- [2026-10] **TradingAgents v0.7.1** released with decisions scored only on final closes and settled across long market holidays, a fix for model dates that could read filings made after the run date, and fixes to portfolios, prices, SEC statements and reports. - [2026-10] **TradingAgents v0.7.0** released with runs on your own ChatGPT Plus or Pro plan, backtests scored from the first close after each decision, a note at start-up when a newer release is out, and a wheel attached to each GitHub release. - [2026-10] **TradingAgents v0.6.0** released with reports saved as one HTML page, a provider per model tier so the managers and analysts can run on different models, past decisions settled for every ticker while the analysts work, and company news read from Yahoo search while Yahoo's news feed is down. -- [2026-09] **TradingAgents v0.5.2** released with parallel analysts for a faster analysis, a CLI that runs without prompts from flags such as `--ticker` and `--date`, the run's settings recorded in every report, and backtests that see only data published by each analysis date. Full release notes are in [CHANGELOG.md](CHANGELOG.md).
Earlier news +- [2026-09] **TradingAgents v0.5.2** released with parallel analysts for a faster analysis, a CLI that runs without prompts from flags such as `--ticker` and `--date`, the run's settings recorded in every report, and backtests that see only data published by each analysis date. - [2026-09] **TradingAgents v0.5.1** released with a package layout organised by what each module holds (import paths moved), optional Jev screening of social posts, GPT-6 Sol and Luna as the default models, and fixes to run isolation and SEC EDGAR statements. - [2026-09] **TradingAgents v0.5.0** released with point-in-time integrity across every dated path, SEC EDGAR fundamentals served as filed, backtesting over a ticker and date grid, portfolio-aware runs, and current model lineups across every provider. - [2026-08] **TradingAgents v0.4.0** released with look-ahead / point-in-time fixes across FRED macro, social sentiment, and the decision-log memory; clearer decision signals; working CLI checkpoint resume; Trader price grounding; and the GPT-5.6 and GLM-5.3 models. diff --git a/tradingagents/__init__.py b/tradingagents/__init__.py index 7926e149c..e1c420918 100644 --- a/tradingagents/__init__.py +++ b/tradingagents/__init__.py @@ -1,6 +1,6 @@ """TradingAgents: multi-agent LLM financial trading framework.""" -__version__ = "0.7.1.dev0" +__version__ = "0.7.1" from dotenv import find_dotenv, load_dotenv