Aider

• Aider works with LLM web chat UIs.

  • New --copy-paste mode.
  • New /copy-context command.

• Set API keys and other environment variables for all providers from command line or yaml conf file.

  • New --api-key provider=key setting.
  • New --set-env VAR=value setting.

• Added bash and zsh support to --watch-files.

• Better error messages when missing dependencies for Gemini and Bedrock models.

• Control-D now properly exits the program.

• Don't count token costs when API provider returns a hard error.

• Bugfix so watch files works with files that don't have tree-sitter support.

• Bugfix so o1 models can be used as weak model.

• Updated shell command prompt.

• Added docstrings for all Coders.

• Reorganized command line arguments with improved help messages and grouping.

• Use the exact sys.python for self-upgrades.

• Added experimental Gemini models.

• Aider wrote 71% of the code in this release.

https://github.com/user-attachments/assets/a8dca5f6-a1f8-4282-9cbd-e8219f4a23b6

• Use aider in your IDE or editor.

  • Run aider --watch-files and it will watch for instructions you add to your source files.

  • One-liner # ... or // ... comments that start or end with "AI" are instructions to aider.

  • When aider sees "AI!" it reads and follows all the instructions in AI comments.

• Support for new Amazon Bedrock Nova models.
• When /run or /test have non-zero exit codes, pre-fill "Fix that" into the next message prompt.
• /diff now invokes git diff to use your preferred diff tool.
• Added Ctrl-Z support for process suspension.
• Spinner now falls back to ASCII art if fancy symbols throw unicode errors.
• --read now expands ~ home dirs.
• Enabled exception capture in analytics.
• Aider wrote 61% of the code in this release.

https://github.com/user-attachments/assets/bea76d8b-5c31-4913-9536-97b7e6c632b5

• PDF support for Sonnet and Gemini models.
• Added --voice-input-device to select audio input device for voice recording, by @preynal.
• Added --timeout option to configure API call timeouts.
• Set cwd to repo root when running shell commands.
• Added Ctrl-Up/Down keyboard shortcuts for per-message history navigation.
• Improved error handling for failed .gitignore file operations.
• Improved error handling for input history file permissions.
• Improved error handling for analytics file access.
• Removed spurious warning about disabling pretty in VSCode.
• Removed broken support for Dart.
• Bugfix when scraping URLs found in chat messages.
• Better handling of version import errors.
• Improved /drop command to support substring matching for non-glob patterns.
• Bugfix to --alias.
• Aider wrote 82% of the code in this release.

https://github.com/user-attachments/assets/4d9b5187-45e5-47c2-a8ff-1e00542c8b06

• Added --alias config to define custom model aliases.
• Added --[no-]detect-urls flag to disable detecting and offering to scrape URLs found in the chat.
• Ollama models now default to an 8k context window.
• Added RepoMap support for Dart language by @malkoG.
• Ask 2.5% of users if they want to opt-in to analytics.
• Skip suggesting files that share names with files already in chat.
• /editor returns and prefill the file content into the prompt, so you can use /editor to compose messages that start with /commands, etc.
• Enhanced error handling for analytics.
• Improved handling of UnknownEditFormat exceptions with helpful documentation links.
• Bumped dependencies to pick up grep-ast 0.4.0 for Dart language support.
• Aider wrote 81% of the code in this release.

• 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.

• Full support for Claude 3.5 Haiku
  • Scored 75% on aider's code editing leaderboard.
  • Almost as good as Sonnet at much lower cost.
  • Launch with --haiku to use it.
• Easily apply file edits from ChatGPT, Claude or other web apps
  • Chat with ChatGPT or Claude via their web app.
  • Give it your source files and ask for the changes you want.
  • Use the web app's "copy response" button to copy the entire reply from the LLM.
  • Run aider --apply-clipboard-edits file-to-edit.js.
  • Aider will edit your file with the LLM's changes.
• Bugfix for creating new files.
• Aider wrote 84% of the code in this release. <img width="1003" alt="2024-11-04_12-11-03" src="https://github.com/user-attachments/assets/ceab2c15-848c-419c-bed6-38cd2347539e">

• Load and save aider slash-commands to files:
  • /save <fname> command will make a file of /add and /read-only commands that recreate the current file context in the chat.
  • /load <fname> will replay the commands in the file.
  • You can use /load to run any arbitrary set of slash-commands, not just /add and /read-only.
  • Use --load <fname> to run a list of commands on launch, before the interactive chat begins.
• Anonymous, opt-in analytics with no personal data sharing.
• Aider follows litellm's supports_vision attribute to enable image support for models.
• Bugfix for when diff mode flexibly handles the model using the wrong filename.
• Displays filenames in sorted order for /add and /read-only.
• New --no-fancy-input switch disables prompt toolkit input, now still available with --no-pretty.
• Override browser config with --no-browser or --no-gui.
• Offer to open documentation URLs when errors occur.
• Properly support all o1 models, regardless of provider.
• Improved layout of filenames above input prompt.
• Better handle corrupted repomap tags cache.

• Full support for Sonnet 10/22, the new SOTA model on aider's code editing benchmark.
  • Aider uses Sonnet 10/22 by default.
• Improved formatting of added and read-only files above chat prompt, by @jbellis.
• Improved support for o1 models by more flexibly parsing their nonconforming code edit replies.
• Corrected diff edit format prompt that only the first match is replaced.
• Stronger whole edit format prompt asking for clean file names.
• Now offers to add .env to the .gitignore file.
• Ships with a small model metadata json file to handle models not yet updated in litellm.
• Model settings for o1 models on azure.
• Bugfix to properly include URLs in /help RAG results.
• Aider wrote 49% of the code in this release.

• Improvements to /read-only:
  • Now supports shell-style auto-complete of the full file system.
  • Still auto-completes the full paths of the repo files like /add.
  • Now supports globs like src/**/*.py
• Renamed --yes to --yes-always.
  • Now uses AIDER_YES_ALWAYS env var and yes-always: yaml key.
  • Existing YAML and .env files will need to be updated.
  • Can still abbreviate to --yes on the command line.
• Config file now uses standard YAML list syntax with - list entries, one per line.
• /settings now includes the same announcement lines that would print at launch.
• Sanity checks the --editor-model on launch now, same as main and weak models.
• Added --skip-sanity-check-repo switch to speedup launch in large repos.
• Bugfix so architect mode handles Control-C properly.
• Repo-map is deterministic now, with improved caching logic.
• Improved commit message prompt.
• Aider wrote 77% of the code in this release.

• Use a pair of Architect/Editor models for improved coding
  • Use a strong reasoning model like o1-preview as your Architect.
  • Use a cheaper, faster model like gpt-4o as your Editor.
• New --o1-preview and --o1-mini shortcuts.
• Support for new Gemini 002 models.
• Better support for Qwen 2.5 models.
• Many confirmation questions can be skipped for the rest of the session with "(D)on't ask again" response.
• Autocomplete for /read-only supports the entire filesystem.
• New settings for completion menu colors.
• New /copy command to copy the last LLM response to the clipboard.
• Renamed /clipboard to /paste.
• Will now follow HTTP redirects when scraping urls.
• New --voice-format switch to send voice audio as wav/mp3/webm, by @mbailey.
• ModelSettings takes extra_params dict to specify any extras to pass to litellm.completion().
• Support for cursor shapes when in vim mode.
• Numerous bug fixes.
• Aider wrote 53% of the code in this release.

• Support for OpenAI o1 models:
  • o1-preview now works well with diff edit format.
  • o1-preview with diff now matches SOTA leaderboard result with whole edit format.
  • aider --model o1-mini
  • aider --model o1-preview
• On Windows, /run correctly uses PowerShell or cmd.exe.
• Support for new 08-2024 Cohere models, by @jalammar.
• Can now recursively add directories with /read-only.
• User input prompts now fall back to simple input() if --no-pretty or a Windows console is not available.
• Improved sanity check of git repo on startup.
• Improvements to prompt cache chunking strategy.
• Removed "No changes made to git tracked files".
• Numerous bug fixes for corner case crashes.
• Updated all dependency versions.
• Aider wrote 70% of the code in this release.