v0.84.0
AiderSummary
This release significantly expands model support by adding the latest Claude 4 series models and Gemini 2.5 Flash preview. Key fixes include correcting file ignoring behavior and improving OpenRouter cost accuracy, alongside several quality-of-life enhancements like better commit message context and improved shell completion.
New Features
- Added support for new Claude models including the Sonnet 4 and Opus 4 series across various providers.
- Added support for the Vertex AI Gemini 2.5 Flash preview model.
- Updated default OpenRouter models during onboarding to `deepseek/deepseek-r1:free` for the free tier and `anthropic/claude-sonnet-4` for paid tiers.
- Enabled automatic refreshing of GitHub Copilot tokens when used as OpenAI API keys.
Bug Fixes
- Fixed an issue where files explicitly added via the command line were not correctly ignored if listed in .gitignore.
- Fixed OpenRouter token cost calculation for improved accuracy.
Improvements
- Improved automatic commit messages by providing more context during their generation.
- Improved OpenRouter model metadata handling by introducing a local cache, increasing reliability and performance.
- Added shell tab completion for file path arguments and for --edit-format/--editor-edit-format options.
- The /settings command now displays detailed metadata for active main, editor, and weak models.
- Improved user language detection by correctly normalizing hyphenated language codes (e.g., en-US to en) and enhancing the validation of locale results.
- Prevented aider from instructing the LLM to reply in 'C' or 'POSIX' when these are detected as the system locale.
- Displayed a spinner with the model name when generating commit messages.