v0.73.0
AiderSummary
This release introduces significant model flexibility with full support for o3-mini and R1 free on OpenRouter, alongside a new `--reasoning-effort` control. Key improvements include better context window handling and fixes to ensure correct turn ordering for R1 models.
New Features
- Enabled full support for the o3-mini model via the `aider --model o3-mini` command.
- Introduced the new `--reasoning-effort` argument with options: low, medium, and high.
- Added support for removing model-specific reasoning tags from responses using the `remove_reasoning: tagname` model setting.
- Enabled automatic creation of parent directories when creating new files.
- Added support for using the R1 free model on OpenRouter via `--model openrouter/deepseek/deepseek-r1:free`.
Bug Fixes
- Fixed model metadata for the `openrouter/deepseek/deepseek-r1` model.
- Fixed issues related to incorrect user/assistant turn order that caused errors when using R1 models.
Improvements
- Improved handling of context window size limits, providing better user messaging and specific guidance for Ollama users.
- Enforced correct user/assistant turn order to prevent errors on R1 models.
- Implemented case-insensitive matching for model names while retaining the original casing for display.