Skip to content

Changelog

All significant changes to this project are documented in this release file.

Legend
Feature New feature
Enhancement Improvement in existing functionality
API Change Changes in the API
Fix Bug fix

0.2.0 Aug 3, 2026

Added

  • Feature ForecastingAssistant.compare() backtests several forecaster/estimator configurations with the same cross-validation strategy and returns a metric-ranked ComparisonResult leaderboard. Each successful candidate is available in candidates, a name-keyed mapping of BacktestResult ordered best to worst, and the winning configuration is exposed as best_name / best_candidate for direct reuse. A matching compare CLI command reports the leaderboard and supports --candidates, --metric, --from-profile, and --output-code.

Changed

  • API Change ForecastingAssistant.ask() now accepts a single result parameter in place of the previous forecast_result and backtest_result parameters. Update calls from ask(forecast_result=...) / ask(backtest_result=...) to ask(result=...). Any ExplainableResult is accepted, including ForecastResult, BacktestResult, and ComparisonResult.

Fixed

  • API Change ForecastingAssistant.ask() now treats a supplied result as the single source of truth. Previously an explicit profile or plan took precedence over the result's own while the context and code still came from the result, so the returned artifacts could describe different states. data, target, date_column, series_id_column, profile, plan, and steps are now ignored with an IgnoredArgumentWarning when result is provided.

0.1.0 Jul 13, 2026

First public release. skforecast-ai wraps the skforecast engine in a deterministic, rule-based assistant that profiles the data, selects a model, evaluates it, and returns the forecast together with the exact, runnable script that produced it. An optional LLM layer explains the decisions without ever changing them.

Maturity

The underlying forecasting engine (skforecast) is mature and production-grade. The skforecast-ai assistant layer is at 0.1.0, so its public API may still change.

Added

  • ForecastingAssistant: the main entry point, covering the full workflow: profile(), plan(), refine_plan(), forecast() / forecast_code(), create_cv(), backtest() / backtest_code(), and ask().
  • Typer-based CLI mirroring the programmatic API, with persistent configuration.