Release notes
Aider v0.76.0
Improved support for thinking/reasoning models:
- Added
--thinking-tokensCLI option to control token budget for models that support thinking. - Display thinking/reasoning content from LLMs which return it.
- Enhanced handling of reasoning tags to better clean up model responses.
- Added deprecation warning for
remove_reasoningsetting, now replaced byreasoning_tag.
- Added
Aider will notify you when it's completed the last request and needs your input:
- Added notifications when LLM responses are ready with
--notificationsflag. - Specify desktop notification command with
--notifications-command.
- Added notifications when LLM responses are ready with
Added/improved support for many models/providers:
- Added support for QWQ 32B.
- Support for DeepSeek V3 free on OpenRouter:
--model openrouter/deepseek/deepseek-chat:free. - Added support for Claude 3.7 Sonnet models on OpenRouter, Bedrock and Vertex AI.
- Updated default model to Claude 3.7 Sonnet on OpenRouter.
- Added support for GPT-4.5-preview model.
- Added support for Claude 3.7 Sonnet:beta on OpenRouter.
- Added support for
openrouter/anthropic/claude-3.7-sonnet - Fixed weak_model_name patterns to match main model name patterns for some models.
Switch to
tree-sitter-language-packfor tree sitter support.Improved error handling for EOF (Ctrl+D) in user input prompts.
Added helper function to ensure hex color values have a # prefix.
Fixed handling of Git errors when reading staged files.
Improved SSL verification control for model information requests.
Improved empty LLM response handling with clearer warning messages.
Fixed Git identity retrieval to respect global configuration, by Akira Komamura.
Offer to install dependencies for Bedrock and Vertex AI models.
Deprecated model shortcut args (like --4o, --opus) in favor of the --model flag.
Aider wrote 85% of the code in this release.
https://aider.chat/HISTORY.html