• Added /editor command to open system editor for writing prompts, by @thehunmonkgroup.
• Full support for gpt-4o-2024-11-20.
• Stream o1 models by default.
• /run and suggested shell commands are less mysterious and now confirm that they "Added XX lines of output to the chat."
• Ask 1% of users if they want to opt-in to analytics.
• Added support for optional multiline input tags with matching closing tags.
• Improved model settings configuration with support for global extra_params for litellm.completion().
• Architect mode now asks to add files suggested by the LLM.
• Fixed bug in fuzzy model name matching.
• Added Timeout exception to handle API provider timeouts.
• Added --show-release-notes to control release notes display on first run of new version.
• Save empty dict to cache file on model metadata download failure, to delay retry.
• Improved error handling and code formatting.
• Fixed bug in fuzzy model name matching when litellm provider info is missing.
• Modified model metadata file loading to allow override of resource file.
• Allow recursive loading of dirs using --read.
• Updated dependency versions to pick up litellm fix for ollama models.
• Added exponential backoff retry when writing files to handle editor file locks.
• Updated Qwen 2.5 Coder 32B model configuration.
• Fixed bug in git ignored file handling.
• Improved error handling for git operations.
• Aider wrote 74% of the code in this release.