dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-15 09:05:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'main' into mixpanel

Browse source
This commit is contained in:
Paul Gauthier 2024-10-30 09:40:01 -07:00
commit 068fb38a5d
181 changed files with 141428 additions and 1961 deletions
Download patch file Download diff file Expand all files Collapse all files

265
aider/website/HISTORY.md
View file

@ -6,20 +6,277 @@ highlight_image: /assets/blame.jpg
description: Release notes and stats on aider writing its own code.
---
# Release history
{% include blame.md %}
<!--[[[cog
# This page is a copy of HISTORY.md, adding the front matter above.
text = open("HISTORY.md").read()
text = text.replace("# Release history", "")
cog.out(text)
]]]-->
# Release history
### main branch
- 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.
- 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`.
- Properly support all o1 models, regardless of provider.
- Improved handling of API errors, especially when accessing the weak model.
### Aider v0.60.1
- Enable image support for Sonnet 10/22.
- Display filenames in sorted order.
### Aider v0.60.0
- 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.
### Aider v0.59.1
- Check for obsolete `yes: true` in yaml config, show helpful error.
- Model settings for openrouter/anthropic/claude-3.5-sonnet:beta
### Aider v0.59.0
- 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.
### Aider v0.58.1
- Fixed bug where cache warming pings caused subsequent user messages to trigger a tight loop of LLM requests.
### Aider v0.58.0
- [Use a pair of Architect/Editor models for improved coding](https://aider.chat/2024/09/26/architect.html)
- 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.
### Aider v0.57.1
- Fixed dependency conflict between aider-chat[help] and [playwright].
### Aider v0.57.0
- 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.
### Aider v0.56.0
- Enables prompt caching for Sonnet via OpenRouter by @fry69
- Enables 8k output tokens for Sonnet via VertexAI and DeepSeek V2.5.
- New `/report` command to open your browser with a pre-populated GitHub Issue.
- New `--chat-language` switch to set the spoken language.
- Now `--[no-]suggest-shell-commands` controls both prompting for and offering to execute shell commands.
- Check key imports on launch, provide helpful error message if dependencies aren't available.
- Renamed `--models` to `--list-models` by @fry69.
- Numerous bug fixes for corner case crashes.
- Aider wrote 56% of the code in this release.
### Aider v0.55.0
- Only print the pip command when self updating on Windows, without running it.
- Converted many error messages to warning messages.
- Added `--tool-warning-color` setting.
- Blanket catch and handle git errors in any `/command`.
- Catch and handle glob errors in `/add`, errors writing files.
- Disabled built in linter for typescript.
- Catch and handle terminals which don't support pretty output.
- Catch and handle playwright and pandoc errors.
- Catch `/voice` transcription exceptions, show the WAV file so the user can recover it.
- Aider wrote 53% of the code in this release.
### Aider v0.54.12
- Switched to `vX.Y.Z.dev` version naming.
### Aider v0.54.11
- Improved printed pip command output on Windows.
### Aider v0.54.10
- Bugfix to test command in platform info.
### Aider v0.54.9
- Include important devops files in the repomap.
- Print quoted pip install commands to the user.
- Adopt setuptools_scm to provide dev versions with git hashes.
- Share active test and lint commands with the LLM.
- Catch and handle most errors creating new files, reading existing files.
- Catch and handle most git errors.
- Added --verbose debug output for shell commands.
### Aider v0.54.8
- Startup QOL improvements:
- Sanity check the git repo and exit gracefully on problems.
- Pause for confirmation after model sanity check to allow user to review warnings.
- Bug fix for shell commands on Windows.
- Do not fuzzy match filenames when LLM is creating a new file, by @ozapinq
- Numerous corner case bug fixes submitted via new crash report -> GitHub Issue feature.
- Crash reports now include python version, OS, etc.
### Aider v0.54.7
- Offer to submit a GitHub issue pre-filled with uncaught exception info.
- Bugfix for infinite output.
### Aider v0.54.6
- New `/settings` command to show active settings.
- Only show cache warming status update if `--verbose`.
### Aider v0.54.5
- Bugfix for shell commands on Windows.
- Refuse to make git repo in $HOME, warn user.
- Don't ask again in current session about a file the user has said not to add to the chat.
- Added `--update` as an alias for `--upgrade`.
### Aider v0.54.4
- Bugfix to completions for `/model` command.
- Bugfix: revert home dir special case.
### Aider v0.54.3
- Dependency `watchdog<5` for docker image.
### Aider v0.54.2
- When users launch aider in their home dir, help them find/create a repo in a subdir.
- Added missing `pexpect` dependency.
### Aider v0.54.0
- Added model settings for `gemini/gemini-1.5-pro-exp-0827` and `gemini/gemini-1.5-flash-exp-0827`.
- Shell and `/run` commands can now be interactive in environments where a pty is available.
- Optionally share output of suggested shell commands back to the LLM.
- New `--[no-]suggest-shell-commands` switch to configure shell commands.
- Performance improvements for autocomplete in large/mono repos.
- New `--upgrade` switch to install latest version of aider from pypi.
- Bugfix to `--show-prompt`.
- Disabled automatic reply to the LLM on `/undo` for all models.
- Removed pager from `/web` output.
- Aider wrote 64% of the code in this release.
### Aider v0.53.0
- [Keep your prompt cache from expiring](https://aider.chat/docs/usage/caching.html#preventing-cache-expiration) with `--cache-keepalive-pings`.
- Pings the API every 5min to keep the cache warm.
- You can now bulk accept/reject a series of add url and run shell confirmations.
- Improved matching of filenames from S/R blocks with files in chat.
- Stronger prompting for Sonnet to make edits in code chat mode.
- Stronger prompting for the LLM to specify full file paths.
- Improved shell command prompting.
- Weak model now uses `extra_headers`, to support Anthropic beta features.
- New `--install-main-branch` to update to the latest dev version of aider.
- Improved error messages on attempt to add not-git subdir to chat.
- Show model metadata info on `--verbose`.
- Improved warnings when LLMs env variables aren't set.
- Bugfix to windows filenames which contain `\_`.
- Aider wrote 59% of the code in this release.
### Aider v0.52.1
- Bugfix for NameError when applying edits.
### Aider v0.52.0
- Aider now offers to run shell commands:
- Launch a browser to view updated html/css/js.
- Install new dependencies.
- Run DB migrations.
- Run the program to exercise changes.
- Run new test cases.
- `/read` and `/drop` now expand `~` to the home dir.
- Show the active chat mode at aider prompt.
- New `/reset` command to `/drop` files and `/clear` chat history.
- New `--map-multiplier-no-files` to control repo map size multiplier when no files are in the chat.
- Reduced default multiplier to 2.
- Bugfixes and improvements to auto commit sequencing.
- Improved formatting of token reports and confirmation dialogs.
- Default OpenAI model is now `gpt-4o-2024-08-06`.
- Bumped dependencies to pickup litellm bugfixes.
- Aider wrote 68% of the code in this release.
### Aider v0.51.0
- Prompt caching for Anthropic models with `--cache-prompts`.
- Caches the system prompt, repo map and `/read-only` files.
- Repo map recomputes less often in large/mono repos or when caching enabled.
- Use `--map-refresh <always|files|manual|auto>` to configure.
- Improved cost estimate logic for caching.
- Improved editing performance on Jupyter Notebook `.ipynb` files.
- Work around litellm tokenizer bug for images.
- Show which config yaml file is loaded with `--verbose`.
- Bumped dependency versions.
- Bugfix: properly load `.aider.models.metadata.json` data.
- Bugfix: Using `--msg /ask ...` caused an exception.
- Bugfix: litellm tokenizer bug for images.
- Aider wrote 56% of the code in this release.
### Aider v0.50.1
@ -507,7 +764,7 @@ cog.out(text)
### Aider v0.14.0
- [Support for Claude2 and other LLMs via OpenRouter](https://aider.chat/docs/faq.html#accessing-other-llms-with-openrouter) by @joshuavial
- Documentation for [running the aider benchmarking suite](https://github.com/paul-gauthier/aider/tree/main/benchmark)
- Documentation for [running the aider benchmarking suite](https://github.com/Aider-AI/aider/tree/main/benchmark)
- Aider now requires Python >= 3.9
@ -552,7 +809,7 @@ cog.out(text)
- Added `/git` command to run git from inside aider chats.
- Use Meta-ENTER (Esc+ENTER in some environments) to enter multiline chat messages.
- Create a `.gitignore` with `.aider*` to prevent users from accidentaly adding aider files to git.
- Create a `.gitignore` with `.aider*` to prevent users from accidentally adding aider files to git.
- Check pypi for newer versions and notify user.
- Updated keyboard interrupt logic so that 2 ^C in 2 seconds always forces aider to exit.
- Provide GPT with detailed error if it makes a bad edit block, ask for a retry.

12
aider/website/_config.yml
View file

@ -24,7 +24,7 @@ exclude:
aux_links:
"GitHub":
- "https://github.com/paul-gauthier/aider"
- "https://github.com/Aider-AI/aider"
"Discord":
- "https://discord.gg/Tv2uQnR88V"
"Blog":
@ -32,13 +32,17 @@ aux_links:
nav_external_links:
- title: "GitHub"
url: "https://github.com/paul-gauthier/aider"
url: "https://github.com/Aider-AI/aider"
- title: "Discord"
url: "https://discord.gg/Tv2uQnR88V"
repository: paul-gauthier/aider
repository: Aider-AI/aider
callouts:
tip:
title: Tip
color: green
color: green
note:
title: Note
color: yellow

492
aider/website/_data/architect.yml Normal file
View file

@ -0,0 +1,492 @@
- dirname: 2024-09-25-21-17-19--architect-sonnet-sonnet-diff
test_cases: 133
model: claude-3.5-sonnet
editor_model: claude-3.5-sonnet
editor_edit_format: diff
edit_format: architect
commit_hash: c18d6a8-dirty
pass_rate_1: 62.4
pass_rate_2: 80.5
percent_cases_well_formed: 100.0
error_outputs: 3
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 183
lazy_comments: 6
syntax_errors: 9
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 25.1
total_cost: 4.9502
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
test_cases: 133
model: claude-3.5-sonnet
edit_format: diff
commit_hash: 35f21b5
pass_rate_1: 57.1
pass_rate_2: 77.4
percent_cases_well_formed: 99.2
error_outputs: 23
released: 2024-06-20
num_malformed_responses: 4
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --sonnet
date: 2024-07-04
versions: 0.42.1-dev
seconds_per_case: 17.6
total_cost: 3.6346
- dirname: 2024-09-25-21-25-01--architect-o1mini-4o-jr-diff
test_cases: 133
model: o1-mini
editor_model: gpt-4o
editor_edit_format: diff
edit_format: architect
commit_hash: 3f682ed-dirty, 25e833b
pass_rate_1: 51.1
pass_rate_2: 70.7
percent_cases_well_formed: 100.0
error_outputs: 12
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 214
lazy_comments: 6
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 23.7
total_cost: 9.3158
- dirname: 2024-09-26-15-05-58--architect-o1mini-deep-jr-whole
test_cases: 133
model: o1-mini
edit_format: architect
commit_hash: 1676653-dirty
editor_model: deepseek
editor_edit_format: whole
pass_rate_1: 51.9
pass_rate_2: 71.4
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 199
lazy_comments: 11
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model o1-mini
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 48.2
total_cost: 5.6069
- dirname: 2024-09-25-21-33-40--architect-4o-4o-jr-diff
test_cases: 133
model: gpt-4o
editor_model: gpt-4o
editor_edit_format: diff
edit_format: architect
commit_hash: 9f3cd92
pass_rate_1: 56.4
pass_rate_2: 75.2
percent_cases_well_formed: 100.0
error_outputs: 13
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 207
lazy_comments: 8
syntax_errors: 1
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model gpt-4o
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 18.2
total_cost: 6.0918
- dirname: 2024-09-21-16-45-11--o1-preview-flex-sr-markers
test_cases: 133
model: o1-preview
edit_format: diff
commit_hash: 5493654-dirty
pass_rate_1: 57.9
pass_rate_2: 79.7
percent_cases_well_formed: 93.2
error_outputs: 11
num_malformed_responses: 11
num_with_malformed_responses: 9
user_asks: 3
lazy_comments: 0
syntax_errors: 10
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-preview
date: 2024-09-21
versions: 0.56.1.dev
seconds_per_case: 80.9
total_cost: 63.9190
- dirname: 2024-09-25-21-39-05--architect-o1preview-4o-jr-diff
test_cases: 133
model: o1-preview
editor_model: gpt-4o
editor_edit_format: diff
edit_format: architect
commit_hash: 9f3cd92
pass_rate_1: 63.2
pass_rate_2: 80.5
percent_cases_well_formed: 100.0
error_outputs: 23
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 191
lazy_comments: 2
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model o1-preview
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 42.3
total_cost: 39.3766
- dirname: 2024-09-25-21-52-42--architect-o1preview-sonnet-jr-diff
test_cases: 133
model: o1-preview
editor_model: claude-3.5-sonnet
editor_edit_format: diff
edit_format: architect
commit_hash: 9f3cd92
editor_model: claude-3-5-sonnet
pass_rate_1: 60.9
pass_rate_2: 82.7
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 180
lazy_comments: 3
syntax_errors: 9
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model o1-preview
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 44.9
total_cost: 37.6192
- dirname: 2024-09-21-16-40-56--o1-mini-flex-sr-markers
test_cases: 36
model: o1-mini
edit_format: diff
commit_hash: 5493654
pass_rate_1: 50.0
pass_rate_2: 61.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 3
lazy_comments: 0
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model o1-mini
date: 2024-09-21
versions: 0.56.1.dev
seconds_per_case: 26.7
total_cost: 2.4226
- dirname: 2024-09-25-23-12-14--architect-o1mini-deep-jr-diff
test_cases: 133
model: o1-mini
edit_format: architect
commit_hash: 9f3cd92-dirty
editor_model: deepseek
editor_edit_format: diff
pass_rate_1: 48.9
pass_rate_2: 69.2
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 202
lazy_comments: 12
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model o1-mini
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 52.2
total_cost: 5.7927
- dirname: 2024-09-25-23-18-16--architect-o1preview-deep-jr-diff
test_cases: 133
model: o1-preview
edit_format: architect
commit_hash: 9f3cd92-dirty
editor_model: deepseek
editor_edit_format: diff
pass_rate_1: 64.7
pass_rate_2: 80.5
percent_cases_well_formed: 100.0
error_outputs: 5
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 180
lazy_comments: 2
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-preview
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 73.2
total_cost: 35.7887
- dirname: 2024-09-25-23-30-36--architect-o1preview-deep-jr-whole
test_cases: 133
model: o1-preview
edit_format: architect
commit_hash: 9f3cd92-dirty
editor_model: deepseek
editor_edit_format: whole
pass_rate_1: 63.9
pass_rate_2: 85.0
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 181
lazy_comments: 12
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model o1-preview
date: 2024-09-25
versions: 0.57.2.dev
seconds_per_case: 67.4
total_cost: 35.3152
- dirname: 2024-09-26-15-15-17--architect-sonnet-deep-jr-whole
test_cases: 133
model: claude-3.5-sonnet
edit_format: architect
commit_hash: bc1559f-dirty
editor_model: deepseek
editor_edit_format: whole
pass_rate_1: 61.7
pass_rate_2: 78.9
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 184
lazy_comments: 5
syntax_errors: 9
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 37.2
total_cost: 2.1510
- dirname: 2024-09-26-15-33-28--costs-gpt4o-diff
test_cases: 133
model: gpt-4o
edit_format: diff
commit_hash: 89aa385-dirty
pass_rate_1: 55.6
pass_rate_2: 71.4
percent_cases_well_formed: 97.7
error_outputs: 5
num_malformed_responses: 5
num_with_malformed_responses: 3
user_asks: 10
lazy_comments: 0
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model gpt-4o
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 9.7
total_cost: 3.8088
- dirname: 2024-09-26-15-41-08--architect-4o-deep-jr-whole
test_cases: 133
model: gpt-4o
edit_format: architect
commit_hash: 89aa385-dirty
editor_model: deepseek
editor_edit_format: whole
pass_rate_1: 60.9
pass_rate_2: 73.7
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 187
lazy_comments: 12
syntax_errors: 5
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model gpt-4o
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 38.0
total_cost: 2.4737
- dirname: 2024-09-26-15-54-08--architect-4o-deep-jr-diff
test_cases: 133
model: gpt-4o
edit_format: architect
commit_hash: 89aa385-dirty
editor_model: deepseek
editor_edit_format: diff
pass_rate_1: 57.1
pass_rate_2: 74.4
percent_cases_well_formed: 100.0
error_outputs: 4
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 192
lazy_comments: 6
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model gpt-4o
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 44.0
total_cost: 2.5498
- dirname: 2024-09-26-16-06-39--architect-sonnet-deep-jr-diff
test_cases: 133
model: claude-3.5-sonnet
edit_format: architect
commit_hash: 89aa385-dirty
editor_model: deepseek
editor_edit_format: diff
pass_rate_1: 61.7
pass_rate_2: 78.9
percent_cases_well_formed: 100.0
error_outputs: 2
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 184
lazy_comments: 2
syntax_errors: 9
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-09-26
versions: 0.57.2.dev
seconds_per_case: 43.2
total_cost: 2.1488
- dirname: 2024-09-27-18-15-32--architect-4omini-4omini
test_cases: 133
model: gpt-4o-mini
edit_format: architect
commit_hash: 0bd8058-dirty
editor_model: gpt-4o-mini
editor_edit_format: whole
pass_rate_1: 43.6
pass_rate_2: 60.2
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 208
lazy_comments: 2
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model gpt-4o-mini
date: 2024-09-27
versions: 0.57.2.dev
seconds_per_case: 21.0
total_cost: 0.1527
- dirname: 2024-07-18-18-57-46--gpt-4o-mini-whole
test_cases: 133
model: gpt-4o-mini
edit_format: whole
commit_hash: d31eef3-dirty
pass_rate_1: 40.6
pass_rate_2: 55.6
released: 2024-07-18
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model gpt-4o-mini
date: 2024-07-18
versions: 0.44.1-dev
seconds_per_case: 7.8
total_cost: 0.0916
- dirname: 2024-09-29-22-35-36--architect-o1preview-o1mini-whole
test_cases: 133
model: o1-preview
edit_format: architect
commit_hash: 53ca83b
editor_model: o1-mini
editor_edit_format: whole
pass_rate_1: 65.4
pass_rate_2: 85.0
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 179
lazy_comments: 4
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-preview
date: 2024-09-29
versions: 0.58.1.dev
seconds_per_case: 39.7
total_cost: 36.2078

934
aider/website/_data/blame.yml
View file

File diff suppressed because it is too large Load diff

824
aider/website/_data/edit_leaderboard.yml
View file

@ -317,29 +317,6 @@
seconds_per_case: 22.9
total_cost: 2.7494
- dirname: 2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2
test_cases: 133
model: DeepSeek Chat V2 (original)
released: 2024-05-06
edit_format: diff
commit_hash: 80a3f6d
pass_rate_1: 44.4
pass_rate_2: 60.9
percent_cases_well_formed: 97.0
error_outputs: 14
num_malformed_responses: 4
user_asks: 2
lazy_comments: 0
syntax_errors: 13
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model deepseek/deepseek-chat
date: 2024-05-09
versions: 0.33.1-dev
seconds_per_case: 86.8
total_cost: 0.0941
- dirname: 2024-05-07-20-32-37--qwen1.5-110b-chat-whole
test_cases: 133
model: qwen1.5-110b-chat
@ -387,7 +364,7 @@
- dirname: 2024-05-13-17-39-05--gpt-4o-diff
test_cases: 133
model: gpt-4o
model: gpt-4o-2024-05-13
released: 2024-05-13
edit_format: diff
commit_hash: b6cd852
@ -407,7 +384,7 @@
versions: 0.34.1-dev
seconds_per_case: 6.0
total_cost: 0.0000
- dirname: 2024-04-12-22-18-20--gpt-4-turbo-2024-04-09-plain-diff
test_cases: 33
model: gpt-4-turbo-2024-04-09 (diff)
@ -570,7 +547,7 @@
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
test_cases: 133
model: claude-3.5-sonnet
model: claude-3.5-sonnet-20240620
edit_format: diff
commit_hash: 35f21b5
pass_rate_1: 57.1
@ -586,7 +563,7 @@
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --sonnet
command: aider --model claude-3.5-sonnet-20240620
date: 2024-07-04
versions: 0.42.1-dev
seconds_per_case: 17.6
@ -665,7 +642,7 @@
- dirname: 2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628
test_cases: 133
model: DeepSeek Chat V2 0628
model: DeepSeek Chat V2 0628 (deprecated)
edit_format: diff
commit_hash: 96ff06e-dirty
pass_rate_1: 60.9
@ -737,7 +714,7 @@
- dirname: 2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct
test_cases: 133
model: DeepSeek Coder V2 0724
model: DeepSeek Coder V2 0724 (deprecated)
edit_format: diff
commit_hash: 89965bf
pass_rate_1: 57.9
@ -855,27 +832,782 @@
seconds_per_case: 6.5
total_cost: 0.0000
- dirname: 2024-08-14-13-07-12--chatgpt-4o-latest-diff
- dirname: 2024-08-28-07-10-50--gemini-1.5-pro-exp-0827-diff-fenced
test_cases: 133
model: chatgpt-4o-latest
edit_format: diff
commit_hash: b1c3769
pass_rate_1: 53.4
pass_rate_2: 69.2
percent_cases_well_formed: 97.7
error_outputs: 27
num_malformed_responses: 5
num_with_malformed_responses: 3
user_asks: 7
model: gemini-1.5-pro-exp-0827
edit_format: diff-fenced
commit_hash: d8adc75
pass_rate_1: 54.9
pass_rate_2: 66.9
percent_cases_well_formed: 94.7
error_outputs: 112
num_malformed_responses: 26
num_with_malformed_responses: 7
user_asks: 38
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model gemini/gemini-1.5-pro-exp-0827
date: 2024-08-28
versions: 0.53.1-dev
seconds_per_case: 14.5
total_cost: 0.0000
- dirname: 2024-08-27-19-20-19--gemini-1.5-flash-exp-0827
test_cases: 133
model: gemini-1.5-flash-exp-0827
edit_format: whole
commit_hash: d8adc75
pass_rate_1: 40.6
pass_rate_2: 52.6
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 3
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model gemini/gemini-1.5-flash-exp-0827
date: 2024-08-27
versions: 0.53.1-dev
seconds_per_case: 6.3
total_cost: 0.0000
- dirname: 2024-08-27-19-42-05--gemini-1.5-flash-8b-exp-0827
test_cases: 133
model: gemini-1.5-flash-8b-exp-0827
edit_format: whole
commit_hash: d8adc75
pass_rate_1: 31.6
pass_rate_2: 38.3
percent_cases_well_formed: 100.0
error_outputs: 12
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 10
lazy_comments: 250
syntax_errors: 6
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model gemini/gemini-1.5-flash-8b-exp-0827
date: 2024-08-27
versions: 0.53.1-dev
seconds_per_case: 7.2
total_cost: 0.0000
- dirname: 2024-08-30-15-02-05--nous405b-whole
test_cases: 133
model: nousresearch/hermes-3-llama-3.1-405b
edit_format: whole
commit_hash: 2d9d605
pass_rate_1: 51.1
pass_rate_2: 63.9
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model openrouter/nousresearch/hermes-3-llama-3.1-405b
date: 2024-08-30
versions: 0.54.8-dev
seconds_per_case: 38.3
total_cost: 0.0000
- dirname: 2024-09-04-16-08-09--yi-coder-9b-whole
test_cases: 133
model: Yi Coder 9B Chat
edit_format: whole
commit_hash: c4e4967
pass_rate_1: 46.6
pass_rate_2: 54.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 9
lazy_comments: 0
syntax_errors: 14
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model openai/hf:01-ai/Yi-Coder-9B-Chat --openai-api-base https://glhf.chat/api/openai/v1
date: 2024-09-04
versions: 0.54.13.dev
seconds_per_case: 8.3
total_cost: 0.0000
released: 2024-09-04
- dirname: 2024-09-04-16-17-33--yi-coder-9b-chat-q4_0-whole
test_cases: 133
model: yi-coder:9b-chat-q4_0
edit_format: whole
commit_hash: c4e4967
pass_rate_1: 41.4
pass_rate_2: 45.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 48
lazy_comments: 1
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model ollama/yi-coder:9b-chat-q4_0
date: 2024-09-04
versions: 0.54.13.dev
seconds_per_case: 125.3
total_cost: 0.0000
- dirname: 2024-09-05-14-50-11--deepseek-sep5-no-shell
test_cases: 133
model: DeepSeek V2.5
edit_format: diff
commit_hash: 1279c86
pass_rate_1: 54.9
pass_rate_2: 72.2
percent_cases_well_formed: 96.2
error_outputs: 5
num_malformed_responses: 5
num_with_malformed_responses: 5
user_asks: 4
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --deepseek
date: 2024-09-05
versions: 0.55.1.dev
seconds_per_case: 49.6
total_cost: 0.0998
- dirname: 2024-09-06-19-55-17--reflection-hyperbolic-whole-output2
test_cases: 133
model: Reflection-70B
edit_format: whole
commit_hash: 74631ee-dirty, 2aef59e-dirty
pass_rate_1: 33.1
pass_rate_2: 42.1
percent_cases_well_formed: 100.0
error_outputs: 2
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 10
lazy_comments: 26
syntax_errors: 1
indentation_errors: 3
exhausted_context_windows: 0
test_timeouts: 3
command: (not currently supported)
date: 2024-09-06
versions: 0.55.1.dev
seconds_per_case: 61.6
total_cost: 0.0000
- dirname: 2024-09-11-15-42-17--command-r-plus-08-2024-whole
test_cases: 133
model: Command R+ (08-24)
edit_format: whole
commit_hash: b43ed20
pass_rate_1: 27.1
pass_rate_2: 38.3
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 7
lazy_comments: 10
syntax_errors: 0
indentation_errors: 3
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model command-r-plus-08-2024
date: 2024-09-11
versions: 0.56.1.dev
seconds_per_case: 20.3
total_cost: 0.0000
- dirname: 2024-09-11-15-47-02--command-r-08-2024-whole
test_cases: 133
model: Command R (08-24)
edit_format: whole
commit_hash: b43ed20-dirty
pass_rate_1: 30.1
pass_rate_2: 38.3
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 4
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model command-r-08-2024
date: 2024-09-11
versions: 0.56.1.dev
seconds_per_case: 7.6
total_cost: 0.0000
- dirname: 2024-09-12-19-57-35--o1-mini-whole
test_cases: 133
model: o1-mini (whole)
edit_format: whole
commit_hash: 36fa773-dirty, 291b456
pass_rate_1: 49.6
pass_rate_2: 70.7
percent_cases_well_formed: 90.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 17
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 103.0
total_cost: 5.3725
- dirname: 2024-09-21-16-40-56--o1-mini-flex-sr-markers
test_cases: 36
model: o1-mini
edit_format: diff
commit_hash: 5493654
pass_rate_1: 50.0
pass_rate_2: 61.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 3
lazy_comments: 0
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model o1-mini
date: 2024-09-21
versions: 0.56.1.dev
seconds_per_case: 26.7
total_cost: 2.4226
- dirname: 2024-09-21-16-45-11--o1-preview-flex-sr-markers
test_cases: 133
model: o1-preview
edit_format: diff
commit_hash: 5493654-dirty
pass_rate_1: 57.9
pass_rate_2: 79.7
percent_cases_well_formed: 93.2
error_outputs: 11
num_malformed_responses: 11
num_with_malformed_responses: 9
user_asks: 3
lazy_comments: 0
syntax_errors: 10
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-preview
date: 2024-09-21
versions: 0.56.1.dev
seconds_per_case: 80.9
total_cost: 63.9190
- dirname: 2024-09-19-16-58-29--qwen2.5-coder:7b-instruct-q8_0
test_cases: 133
model: qwen2.5-coder:7b-instruct-q8_0
edit_format: whole
commit_hash: 6f2b064-dirty
pass_rate_1: 45.1
pass_rate_2: 51.9
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 4
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model ollama/qwen2.5-coder:7b-instruct-q8_0
date: 2024-09-19
versions: 0.56.0
seconds_per_case: 9.3
total_cost: 0.0000
- dirname: 2024-09-20-20-20-19--qwen-2.5-72b-instruct-diff
test_cases: 133
model: qwen-2.5-72b-instruct (bf16)
edit_format: diff
commit_hash: 5139594
pass_rate_1: 53.4
pass_rate_2: 65.4
percent_cases_well_formed: 96.2
error_outputs: 9
num_malformed_responses: 9
num_with_malformed_responses: 5
user_asks: 3
lazy_comments: 0
syntax_errors: 2
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model openrouter/qwen/qwen-2.5-72b-instruct
date: 2024-09-20
versions: 0.56.1.dev
seconds_per_case: 39.8
total_cost: 0.0000
- dirname: 2024-09-21-11-56-43--Codestral-22B-v0.1-Q4_K_M.gguf_whole
test_cases: 133
model: Codestral-22B-v0.1-Q4_K_M
edit_format: whole
commit_hash: 2753ac6-dirty
pass_rate_1: 36.1
pass_rate_2: 48.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 8
lazy_comments: 6
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model Codestral-22B-v0.1-Q4_K_M
date: 2024-09-21
versions: 0.56.1.dev
seconds_per_case: 656.4
total_cost: 0.9108
- dirname: 2024-09-24-16-26-45--gemini-1.5-pro-002-diff-fenced
test_cases: 133
model: gemini-1.5-pro-002
edit_format: diff-fenced
commit_hash: 6b5fe9b, 3edcd71
pass_rate_1: 49.6
pass_rate_2: 65.4
percent_cases_well_formed: 96.2
error_outputs: 17
num_malformed_responses: 17
num_with_malformed_responses: 5
user_asks: 3
lazy_comments: 0
syntax_errors: 2
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model gemini/gemini-1.5-pro-002
date: 2024-09-24
versions: 0.57.2.dev
seconds_per_case: 11.6
total_cost: 2.8166
- dirname: 2024-09-24-16-33-23--gemini-1.5-flash-002-whole
test_cases: 133
model: gemini-1.5-flash-002
edit_format: whole
commit_hash: 3edcd71
pass_rate_1: 37.6
pass_rate_2: 51.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 3
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model gemini/gemini-1.5-flash-002
date: 2024-09-24
versions: 0.57.2.dev
seconds_per_case: 5.1
total_cost: 0.0515
- dirname: 2024-09-24-15-18-59--gemini-1.5-flash-8b-exp-0924-whole
test_cases: 133
model: gemini-1.5-flash-8b-exp-0924
edit_format: whole
commit_hash: 86faaa6
pass_rate_1: 33.1
pass_rate_2: 38.3
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 9
lazy_comments: 6
syntax_errors: 8
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model gemini/gemini-1.5-flash-8b-exp-0924
date: 2024-09-24
versions: 0.57.2.dev
seconds_per_case: 6.6
total_cost: 0.0000
- dirname: 2024-09-28-18-30-20--codestral-whole
test_cases: 133
model: ollama/codestral
edit_format: whole
commit_hash: 1971285-dirty
pass_rate_1: 33.8
pass_rate_2: 45.9
percent_cases_well_formed: 98.5
error_outputs: 8
num_malformed_responses: 8
num_with_malformed_responses: 2
user_asks: 12
lazy_comments: 6
syntax_errors: 5
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model ollama/codestral
date: 2024-09-28
versions: 0.57.2.dev
seconds_per_case: 67.2
total_cost: 0.0000
- dirname: 2024-09-29-17-51-11--codegeex4-whole-2
test_cases: 133
model: ollama/codegeex4
edit_format: whole
commit_hash: 228ae24
pass_rate_1: 28.6
pass_rate_2: 32.3
percent_cases_well_formed: 97.0
error_outputs: 20
num_malformed_responses: 20
num_with_malformed_responses: 4
user_asks: 56
lazy_comments: 5
syntax_errors: 5
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model ollama/codegeex4
date: 2024-09-29
versions: 0.57.2.dev
seconds_per_case: 128.1
total_cost: 0.0000
- dirname: 2024-09-30-00-09-00--wojtek-opencodeinterpreter-6.7b-whole-2
test_cases: 133
model: ollama/wojtek/opencodeinterpreter:6.7b
edit_format: whole
commit_hash: 6d586fd
pass_rate_1: 26.3
pass_rate_2: 30.1
percent_cases_well_formed: 91.0
error_outputs: 18
num_malformed_responses: 18
num_with_malformed_responses: 12
user_asks: 79
lazy_comments: 7
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 6
command: aider --model ollama/wojtek/opencodeinterpreter:6.7b
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 59.3
total_cost: 0.0000
- dirname: 2024-09-30-03-49-01--mistral-nemo-12b-instruct-2407-q4_K_M-whole-1
test_cases: 133
model: ollama/mistral-nemo:12b-instruct-2407-q4_K_M
edit_format: whole
commit_hash: ba4dec8
pass_rate_1: 22.6
pass_rate_2: 33.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 53
lazy_comments: 37
syntax_errors: 2
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model ollama/mistral-nemo:12b-instruct-2407-q4_K_M
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 34.7
total_cost: 0.0000
- dirname: 2024-09-30-14-09-43--qwen2.5-32b-whole-2
test_cases: 133
model: ollama/qwen2.5:32b
edit_format: whole
commit_hash: 765c4cb
pass_rate_1: 44.4
pass_rate_2: 54.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 9
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model ollama/qwen2.5:32b
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 134.9
total_cost: 0.0000
- dirname: 2024-09-30-19-35-40--llama3.2-3b-instruct-fp16-whole-1
test_cases: 133
model: ollama/llama3.2:3b-instruct-fp16
edit_format: whole
commit_hash: 3f12290
pass_rate_1: 20.3
pass_rate_2: 26.3
percent_cases_well_formed: 97.0
error_outputs: 21
num_malformed_responses: 21
num_with_malformed_responses: 4
user_asks: 73
lazy_comments: 11
syntax_errors: 1
indentation_errors: 3
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model ollama/llama3.2:3b-instruct-fp16
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 66.6
total_cost: 0.0000
- dirname: 2024-09-30-23-01-24--hermes3-8b-llama3.1-fp16-whole-2
test_cases: 133
model: ollama/hermes3:8b-llama3.1-fp16
edit_format: whole
commit_hash: c5ba4f7
pass_rate_1: 24.1
pass_rate_2: 30.1
percent_cases_well_formed: 98.5
syntax_errors: 0
exhausted_context_windows: 0
command: aider --model ollama/hermes3:8b-llama3.1-fp16
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 64.7
total_cost: 0.0000
- dirname: 2024-10-01-02-33-11--mistral-small-whole-1
test_cases: 133
model: ollama/mistral-small
edit_format: whole
commit_hash: 8a908fa
pass_rate_1: 30.1
pass_rate_2: 38.3
percent_cases_well_formed: 99.2
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
command: aider --model ollama/mistral-small
date: 2024-10-01
versions: 0.58.1.dev
seconds_per_case: 84.6
total_cost: 0.0000
- dirname: 2024-10-01-07-05-40--yi-coder-9b-chat-fp16-whole-1
test_cases: 133
model: ollama/yi-coder:9b-chat-fp16
edit_format: whole
commit_hash: 52c6632-dirty
pass_rate_1: 39.8
pass_rate_2: 43.6
percent_cases_well_formed: 99.2
lazy_comments: 0
indentation_errors: 0
exhausted_context_windows: 0
command: aider --model ollama/yi-coder:9b-chat-fp16
date: 2024-10-01
versions: 0.58.1.dev
seconds_per_case: 63.7
total_cost: 0.0000
- dirname: 2024-10-01-16-50-09--hermes3-whole-4
test_cases: 133
model: ollama/hermes3
edit_format: whole
commit_hash: 415e898
pass_rate_1: 21.1
pass_rate_2: 22.6
percent_cases_well_formed: 98.5
exhausted_context_windows: 0
command: aider --model ollama/hermes3
date: 2024-10-01
versions: 0.58.1.dev
seconds_per_case: 24.8
total_cost: 0.0000
- dirname: 2024-10-04-16-30-08--chatgpt-4o-latest-diff-oct4
test_cases: 133
model: openai/chatgpt-4o-latest
edit_format: diff
commit_hash: af10953
pass_rate_1: 56.4
pass_rate_2: 72.2
percent_cases_well_formed: 97.0
error_outputs: 4
num_malformed_responses: 4
num_with_malformed_responses: 4
user_asks: 21
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openai/chatgpt-4o-latest
date: 2024-08-14
released: 2024-08-08
versions: 0.50.2-dev
seconds_per_case: 26.3
total_cost: 3.6113
date: 2024-10-04
versions: 0.58.2.dev
seconds_per_case: 23.7
total_cost: 4.0641
- dirname: 2024-10-05-20-03-10--dracarys-glhf-whole
test_cases: 133
model: Dracarys2-72B-Instruct
edit_format: whole
commit_hash: 04a2cbb
pass_rate_1: 55.6
pass_rate_2: 66.9
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: (via glhf.chat)
date: 2024-10-05
versions: 0.59.2.dev
seconds_per_case: 46.7
total_cost: 0.0000
- dirname: 2024-10-13-21-33-42--grok2-whole
test_cases: 133
model: Grok-2
edit_format: whole
commit_hash: 0a497b7
pass_rate_1: 45.9
pass_rate_2: 58.6
percent_cases_well_formed: 98.5
error_outputs: 7
num_malformed_responses: 7
num_with_malformed_responses: 2
user_asks: 24
lazy_comments: 4
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/x-ai/grok-2
date: 2024-10-13
versions: 0.59.2.dev
seconds_per_case: 34.6
total_cost: 0.0000
- dirname: 2024-10-13-23-58-44--grok2mini-whole
test_cases: 133
model: Grok-2-mini
edit_format: whole
commit_hash: 0a497b7-dirty, 0a497b7
pass_rate_1: 40.6
pass_rate_2: 54.9
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 8
lazy_comments: 2
syntax_errors: 2
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model openrouter/x-ai/grok-2-mini
date: 2024-10-13
versions: 0.59.2.dev
seconds_per_case: 32.1
total_cost: 0.0000
- dirname: 2024-10-16-15-55-37--nemotron-glhf-whole3
test_cases: 133
model: Llama-3.1-Nemotron-70B-Instruct-HF
edit_format: whole
commit_hash: 6bb9b25-dirty
pass_rate_1: 36.8
pass_rate_2: 54.9
percent_cases_well_formed: 99.2
error_outputs: 17
num_malformed_responses: 1
num_with_malformed_responses: 1
user_asks: 53
lazy_comments: 17
syntax_errors: 1
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 3
command: (via glhf.chat)
date: 2024-10-16
versions: 0.59.2.dev
seconds_per_case: 64.9
total_cost: 0.0000
- dirname: 2024-10-22-17-45-28--sonnet-1022-diff-fixed-model-settings
test_cases: 133
model: claude-3-5-sonnet-20241022
edit_format: diff
commit_hash: 3b14eb9
pass_rate_1: 69.2
pass_rate_2: 84.2
percent_cases_well_formed: 99.2
error_outputs: 1
num_malformed_responses: 1
num_with_malformed_responses: 1
user_asks: 0
lazy_comments: 1
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model anthropic/claude-3-5-sonnet-20241022
date: 2024-10-22
versions: 0.59.2.dev
seconds_per_case: 18.6
total_cost: 0.0000

186
aider/website/_data/o1_results.yml Normal file
View file

@ -0,0 +1,186 @@
- dirname: 2024-07-18-18-57-46--gpt-4o-mini-whole
test_cases: 133
model: gpt-4o-mini (whole)
edit_format: whole
commit_hash: d31eef3-dirty
pass_rate_1: 40.6
pass_rate_2: 55.6
released: 2024-07-18
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model gpt-4o-mini
date: 2024-07-18
versions: 0.44.1-dev
seconds_per_case: 7.8
total_cost: 0.0916
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
test_cases: 133
model: claude-3.5-sonnet (diff)
edit_format: diff
commit_hash: 35f21b5
pass_rate_1: 57.1
pass_rate_2: 77.4
percent_cases_well_formed: 99.2
error_outputs: 23
released: 2024-06-20
num_malformed_responses: 4
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --sonnet
date: 2024-07-04
versions: 0.42.1-dev
seconds_per_case: 17.6
total_cost: 3.6346
- dirname: 2024-08-06-18-28-39--gpt-4o-2024-08-06-diff-again
test_cases: 133
model: gpt-4o-2024-08-06 (diff)
edit_format: diff
commit_hash: ed9ed89
pass_rate_1: 57.1
pass_rate_2: 71.4
percent_cases_well_formed: 98.5
error_outputs: 18
num_malformed_responses: 2
num_with_malformed_responses: 2
user_asks: 10
lazy_comments: 0
syntax_errors: 6
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 5
released: 2024-08-06
command: aider --model openai/gpt-4o-2024-08-06
date: 2024-08-06
versions: 0.48.1-dev
seconds_per_case: 6.5
total_cost: 0.0000
- dirname: 2024-09-12-19-57-35--o1-mini-whole
test_cases: 133
model: o1-mini (whole)
edit_format: whole
commit_hash: 36fa773-dirty, 291b456
pass_rate_1: 49.6
pass_rate_2: 70.7
percent_cases_well_formed: 90.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 17
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 103.0
total_cost: 5.3725
- dirname: 2024-09-12-20-56-22--o1-mini-diff
test_cases: 133
model: o1-mini (diff)
edit_format: diff
commit_hash: 4598a37-dirty, 291b456, 752e823-dirty
pass_rate_1: 45.1
pass_rate_2: 62.4
percent_cases_well_formed: 85.7
error_outputs: 26
num_malformed_responses: 26
num_with_malformed_responses: 19
user_asks: 2
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model o1-mini --edit-format diff
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 177.7
total_cost: 11.1071
- dirname: 2024-09-05-21-26-49--sonnet-whole-sep5
test_cases: 133
model: claude-3.5-sonnet (whole)
edit_format: whole
commit_hash: 8cfdcbd
pass_rate_1: 55.6
pass_rate_2: 75.2
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model openrouter/anthropic/claude-3.5-sonnet --edit-format whole
date: 2024-09-05
versions: 0.55.1.dev
seconds_per_case: 15.2
total_cost: 2.3502
- dirname: 2024-09-12-22-44-14--o1-preview-diff
test_cases: 133
model: o1-preview (diff)
edit_format: diff
commit_hash: 72f52bd
pass_rate_1: 56.4
pass_rate_2: 75.2
percent_cases_well_formed: 84.2
error_outputs: 27
num_malformed_responses: 27
num_with_malformed_responses: 21
user_asks: 8
lazy_comments: 0
syntax_errors: 7
indentation_errors: 3
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model o1-preview
date: 2024-09-12
versions: 0.56.1.dev
seconds_per_case: 95.8
total_cost: 71.7927
- dirname: 2024-09-13-02-13-59--o1-preview-whole
test_cases: 133
model: o1-preview (whole)
edit_format: whole
commit_hash: 72f52bd-dirty
pass_rate_1: 58.6
pass_rate_2: 79.7
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model o1-preview
date: 2024-09-13
versions: 0.56.1.dev
seconds_per_case: 47.4
total_cost: 38.0612

93
aider/website/_data/refactor_leaderboard.yml
View file

@ -145,7 +145,7 @@
- dirname: 2024-07-01-18-30-33--refac-claude-3.5-sonnet-diff-not-lazy
test_cases: 89
model: claude-3.5-sonnet (diff)
model: claude-3.5-sonnet-20240620
edit_format: diff
commit_hash: 7396e38-dirty
pass_rate_1: 64.0
@ -167,7 +167,7 @@
- dirname: 2024-07-24-07-49-39--refac-deepseek-coder-v2-0724
test_cases: 89
model: DeepSeek Coder V2 0724
model: DeepSeek Coder V2 0724 (deprecated)
edit_format: diff
commit_hash: bb6e597
pass_rate_1: 32.6
@ -208,4 +208,91 @@
versions: 0.48.1-dev
seconds_per_case: 16.9
total_cost: 4.0873
- dirname: 2024-09-05-15-19-05--refac-deepseek-v2.5-no-shell
test_cases: 89
model: DeepSeek Chat V2.5
edit_format: diff
commit_hash: 1279c86, 1279c86-dirty
pass_rate_1: 31.5
percent_cases_well_formed: 67.4
error_outputs: 90
num_malformed_responses: 88
num_with_malformed_responses: 29
user_asks: 8
lazy_comments: 7
syntax_errors: 0
indentation_errors: 6
exhausted_context_windows: 2
test_timeouts: 0
command: aider --deepseek
date: 2024-09-05
versions: 0.55.1.dev
seconds_per_case: 225.4
total_cost: 1.0338
- dirname: 2024-10-22-19-57-27--refac-openrouter-sonnet-1022
test_cases: 89
model: claude-3-5-sonnet-20241022
edit_format: diff
commit_hash: 4a3e6ef
pass_rate_1: 92.1
percent_cases_well_formed: 91.0
error_outputs: 13
num_malformed_responses: 12
num_with_malformed_responses: 8
user_asks: 14
lazy_comments: 2
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --sonnet
date: 2024-10-22
versions: 0.60.1.dev
seconds_per_case: 32.5
total_cost: 8.4644
- dirname: 2024-10-22-20-03-10--refac-o1mini
test_cases: 89
model: o1-mini
edit_format: diff
commit_hash: 4a3e6ef-dirty
pass_rate_1: 44.9
percent_cases_well_formed: 29.2
error_outputs: 151
num_malformed_responses: 150
num_with_malformed_responses: 63
user_asks: 28
lazy_comments: 2
syntax_errors: 5
indentation_errors: 4
exhausted_context_windows: 1
test_timeouts: 0
command: aider --model o1-mini
date: 2024-10-22
versions: 0.60.1.dev
seconds_per_case: 115.3
total_cost: 29.0492
- dirname: 2024-10-22-20-26-36--refac-o1preview
test_cases: 89
model: o1-preview
edit_format: diff
commit_hash: 4a3e6ef-dirty
pass_rate_1: 75.3
percent_cases_well_formed: 57.3
error_outputs: 75
num_malformed_responses: 74
num_with_malformed_responses: 38
user_asks: 19
lazy_comments: 2
syntax_errors: 2
indentation_errors: 3
exhausted_context_windows: 1
test_timeouts: 0
command: aider --model o1-preview
date: 2024-10-22
versions: 0.60.1.dev
seconds_per_case: 231.7
total_cost: 120.9850

459
aider/website/_data/sonnet-fine.yml Normal file
View file

@ -0,0 +1,459 @@
- dirname: 2024-06-20-15-16-41--claude-3.5-sonnet-diff
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 068609e-dirty
pass_rate_1: 57.9
pass_rate_2: 74.4
percent_cases_well_formed: 97.0
error_outputs: 48
num_malformed_responses: 11
num_with_malformed_responses: 4
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-20
versions: 0.38.1-dev
seconds_per_case: 21.6
total_cost: 0.0000
- dirname: 2024-06-24-12-48-43--claude-3.5-sonnet-udiff
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: udiff
commit_hash: 7be08c7
pass_rate_1: 62.4
pass_rate_2: 74.4
percent_cases_well_formed: 100.0
error_outputs: 10
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 10
lazy_comments: 0
syntax_errors: 1
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 14.3
total_cost: 0.0000
- dirname: 2024-06-24-17-44-31--claude-3.5-sonnet-diff-less-chatty
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 0d484e5
pass_rate_1: 57.9
pass_rate_2: 74.4
percent_cases_well_formed: 99.2
error_outputs: 14
num_malformed_responses: 3
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 16.0
total_cost: 0.0000
- dirname: 2024-06-24-17-50-46--claude-3.5-sonnet-diff-less-chatty2
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 3015495
pass_rate_1: 59.4
pass_rate_2: 76.7
percent_cases_well_formed: 99.2
error_outputs: 5
num_malformed_responses: 1
num_with_malformed_responses: 1
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 15.7
total_cost: 0.0000
- dirname: 2024-06-24-17-56-40--claude-3.5-sonnet-diff-less-chatty-sys-examples
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 3015495-dirty
pass_rate_1: 58.6
pass_rate_2: 75.9
percent_cases_well_formed: 100.0
error_outputs: 2
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 15.9
total_cost: 0.0000
- dirname: 2024-07-04-14-32-08--claude-3.5-sonnet-diff-continue
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 35f21b5
pass_rate_1: 57.1
pass_rate_2: 77.4
percent_cases_well_formed: 99.2
error_outputs: 23
num_malformed_responses: 4
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-07-04
versions: 0.42.1-dev
seconds_per_case: 17.6
total_cost: 3.6346
- dirname: 2024-07-06-19-39-59--claude-3.5-sonnet-diff-platform
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: e47c2a9-dirty
pass_rate_1: 57.9
pass_rate_2: 78.2
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-07-06
versions: 0.42.1-dev
seconds_per_case: 14.6
total_cost: 3.5616
- dirname: 2024-07-24-17-11-07--claude-3.5-sonnet-diff-july24
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 859a13e
pass_rate_1: 59.4
pass_rate_2: 78.2
percent_cases_well_formed: 99.2
error_outputs: 6
num_malformed_responses: 1
num_with_malformed_responses: 1
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-07-24
versions: 0.45.2-dev
seconds_per_case: 16.9
total_cost: 3.4981
- dirname: 2024-07-28-20-23-42--claude-3.5-sonnet-diff-no-reminder
test_cases: 94
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: e799e89-dirty
pass_rate_1: 59.6
pass_rate_2: 83.0
percent_cases_well_formed: 98.9
error_outputs: 12
num_malformed_responses: 2
num_with_malformed_responses: 1
user_asks: 2
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-07-28
versions: 0.45.2-dev
seconds_per_case: 15.7
total_cost: 2.4340
- dirname: 2024-08-14-00-46-09--claude-3.5-sonnet-diff-no-ipynb-again
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 139f799
pass_rate_1: 57.9
pass_rate_2: 75.9
percent_cases_well_formed: 98.5
error_outputs: 22
num_malformed_responses: 5
num_with_malformed_responses: 2
user_asks: 249
lazy_comments: 0
syntax_errors: 1
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-14
versions: 0.50.1-dev
seconds_per_case: 18.0
total_cost: 3.7058
- dirname: 2024-06-21-00-07-01--claude-3.5-sonnet-do-over
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: fb26174-dirty
pass_rate_1: 59.4
pass_rate_2: 80.5
percent_cases_well_formed: 99.2
error_outputs: 20
num_malformed_responses: 4
num_with_malformed_responses: 1
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-21
versions: 0.39.1-dev
seconds_per_case: 18.3
total_cost: 0.0000
- dirname: 2024-06-21-00-18-25--claude-3.5-sonnet-do-over2
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: fb26174-dirty
pass_rate_1: 58.6
pass_rate_2: 77.4
percent_cases_well_formed: 98.5
error_outputs: 22
num_malformed_responses: 4
num_with_malformed_responses: 2
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 0
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-21
versions: 0.39.1-dev
seconds_per_case: 17.3
total_cost: 0.0000
- dirname: 2024-06-24-00-09-40--claude-3.5-sonnet-chatty
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: b44c246-dirty
pass_rate_1: 59.4
pass_rate_2: 75.2
percent_cases_well_formed: 98.5
error_outputs: 21
num_malformed_responses: 5
num_with_malformed_responses: 2
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 15.7
total_cost: 0.0000
- dirname: 2024-06-24-00-33-35--claude-3.5-sonnet-chatty-do-over
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: bc1dfa3
pass_rate_1: 58.6
pass_rate_2: 76.7
percent_cases_well_formed: 97.7
error_outputs: 26
num_malformed_responses: 6
num_with_malformed_responses: 3
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-06-24
versions: 0.39.1-dev
seconds_per_case: 16.4
total_cost: 0.0000
- dirname: 2024-08-18-19-57-30--claude-3.5-sonnet-aug18
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 5099a5c
pass_rate_1: 54.9
pass_rate_2: 78.9
percent_cases_well_formed: 97.7
error_outputs: 47
num_malformed_responses: 11
num_with_malformed_responses: 3
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-18
versions: 0.50.2-dev
seconds_per_case: 22.3
total_cost: 3.9008
- dirname: 2024-08-18-20-23-50--claude-3.5-sonnet-aug18-cache-prompts
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 53db8cf-dirty
pass_rate_1: 56.4
pass_rate_2: 78.9
percent_cases_well_formed: 97.7
error_outputs: 16
num_malformed_responses: 4
num_with_malformed_responses: 3
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-18
versions: 0.50.2-dev
seconds_per_case: 21.1
total_cost: 3.6918
- dirname: 2024-08-18-23-11-04--claude-3.5-sonnet-aug18-cache-prompts-cold
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 53db8cf-dirty
pass_rate_1: 56.4
pass_rate_2: 78.2
percent_cases_well_formed: 97.0
error_outputs: 30
num_malformed_responses: 7
num_with_malformed_responses: 4
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-18
versions: 0.50.2-dev
seconds_per_case: 21.8
total_cost: 3.7858
- dirname: 2024-08-21-01-07-39--sonnet-diff-cache
test_cases: 133
model: claude-3-5-sonnet-20240620
edit_format: diff
commit_hash: e12157b-dirty
pass_rate_1: 57.1
pass_rate_2: 82.0
percent_cases_well_formed: 98.5
error_outputs: 12
num_malformed_responses: 2
num_with_malformed_responses: 2
user_asks: 0
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model claude-3-5-sonnet-20240620
date: 2024-08-21
versions: 0.51.2-dev
seconds_per_case: 14.5
total_cost: 3.1795
- dirname: 2024-08-21-00-50-49--shell-cmds-sonnet-user-remind
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 919ea05
pass_rate_1: 63.2
pass_rate_2: 79.7
percent_cases_well_formed: 98.5
error_outputs: 18
num_malformed_responses: 4
num_with_malformed_responses: 2
user_asks: 26
lazy_comments: 0
syntax_errors: 0
indentation_errors: 2
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-21
versions: 0.51.2-dev
seconds_per_case: 16.3
total_cost: 3.4738
- dirname: 2024-08-21-00-55-30--shell-cmds-sonnet-no-user-remind
test_cases: 133
model: openrouter/anthropic/claude-3.5-sonnet
edit_format: diff
commit_hash: 5c7707a
pass_rate_1: 63.9
pass_rate_2: 80.5
percent_cases_well_formed: 97.7
error_outputs: 51
num_malformed_responses: 12
num_with_malformed_responses: 3
user_asks: 24
lazy_comments: 0
syntax_errors: 0
indentation_errors: 1
exhausted_context_windows: 0
test_timeouts: 1
command: aider --model openrouter/anthropic/claude-3.5-sonnet
date: 2024-08-21
versions: 0.51.2-dev
seconds_per_case: 17.7
total_cost: 3.8990

2
aider/website/_includes/blame.md
View file

@ -1,5 +1,5 @@
<canvas id="blameChart" width="800" height="360" style="margin-top: 20px"></canvas>
<canvas id="linesChart" width="800" height="360" style="margin-top: 20px"></canvas>
<canvas id="blameChart" width="800" height="360" style="margin-top: 20px"></canvas>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://cdn.jsdelivr.net/npm/moment"></script>
<script src="https://cdn.jsdelivr.net/npm/chartjs-adapter-moment"></script>

2
aider/website/_includes/get-started.md
View file

@ -2,7 +2,7 @@
You can get started quickly like this:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
# Change directory into a git repo
cd /to/your/git/repo

2
aider/website/_includes/help.md
View file

@ -1,5 +1,5 @@
If you need more help, please check our
[GitHub issues](https://github.com/paul-gauthier/aider/issues)
[GitHub issues](https://github.com/Aider-AI/aider/issues)
and file a new issue if your problem isn't discussed.
Or drop into our
[Discord](https://discord.gg/Tv2uQnR88V)

170
aider/website/_includes/leaderboard_graph.html Normal file
View file

@ -0,0 +1,170 @@
<canvas id="{{ include.chart_id }}" width="800" height="450" style="margin-top: 20px"></canvas>
<script>
document.addEventListener('DOMContentLoaded', function () {
var ctx = document.getElementById('{{ include.chart_id }}').getContext('2d');
var leaderboardData = {
labels: [],
datasets: [{
label: 'Percent completed correctly',
data: [],
backgroundColor: [],
borderColor: [],
borderWidth: 1
}]
};
var allData = [];
{% for row in include.data %}
allData.push({
model: '{{ row.model }}',
pass_rate: {{ row[include.pass_rate_key] }},
percent_cases_well_formed: {{ row.percent_cases_well_formed }},
edit_format: '{{ row.edit_format }}'
});
{% endfor %}
function updateChart() {
var selectedRows = document.querySelectorAll('tr.selected');
var showAll = selectedRows.length === 0;
leaderboardData.labels = [];
leaderboardData.datasets[0].data = [];
leaderboardData.datasets[0].backgroundColor = [];
leaderboardData.datasets[0].borderColor = [];
allData.forEach(function(row, index) {
var rowElement = document.getElementById('{{ include.row_prefix }}-' + index);
if (showAll) {
rowElement.classList.remove('selected');
}
if (showAll || rowElement.classList.contains('selected')) {
leaderboardData.labels.push(row.model);
leaderboardData.datasets[0].data.push(row.pass_rate);
switch (row.edit_format) {
case 'whole':
leaderboardData.datasets[0].backgroundColor.push('rgba(255, 99, 132, 0.2)');
leaderboardData.datasets[0].borderColor.push('rgba(255, 99, 132, 1)');
break;
case 'diff':
leaderboardData.datasets[0].backgroundColor.push('rgba(54, 162, 235, 0.2)');
leaderboardData.datasets[0].borderColor.push('rgba(54, 162, 235, 1)');
break;
case 'udiff':
leaderboardData.datasets[0].backgroundColor.push('rgba(75, 192, 192, 0.2)');
leaderboardData.datasets[0].borderColor.push('rgba(75, 192, 192, 1)');
break;
case 'diff-fenced':
leaderboardData.datasets[0].backgroundColor.push('rgba(153, 102, 255, 0.2)');
leaderboardData.datasets[0].borderColor.push('rgba(153, 102, 255, 1)');
break;
default:
leaderboardData.datasets[0].backgroundColor.push('rgba(201, 203, 207, 0.2)');
leaderboardData.datasets[0].borderColor.push('rgba(201, 203, 207, 1)');
}
}
});
// Apply legend filtering
var meta = leaderboardChart.getDatasetMeta(0);
meta.data.forEach(function(bar, index) {
if (leaderboardData.labels.includes(allData[index].model)) {
bar.hidden = (allData[index].edit_format === 'whole' && meta.data[0].hidden) ||
(allData[index].edit_format !== 'whole' && meta.data[1].hidden);
} else {
bar.hidden = true;
}
});
leaderboardChart.update();
}
var tableBody = document.querySelector('table tbody');
allData.forEach(function(row, index) {
var tr = tableBody.children[index];
tr.id = '{{ include.row_prefix }}-' + index;
tr.style.cursor = 'pointer';
tr.onclick = function() {
this.classList.toggle('selected');
updateChart();
};
});
var leaderboardChart = new Chart(ctx, {
type: 'bar',
data: leaderboardData,
options: {
scales: {
y: {
beginAtZero: true,
title: {
display: true,
text: 'Correct Exercises (%)'
}
},
x: {
ticks: {
autoSkip: false,
maxRotation: 90,
minRotation: 0
}
}
},
plugins: {
legend: {
display: true,
position: 'top',
labels: {
generateLabels: function(chart) {
var uniqueFormats = [...new Set(allData.map(item => item.edit_format))];
return uniqueFormats.map(format => {
var color;
switch (format) {
case 'whole':
color = { fill: 'rgba(255, 99, 132, 0.2)', stroke: 'rgba(255, 99, 132, 1)' };
break;
case 'diff':
color = { fill: 'rgba(54, 162, 235, 0.2)', stroke: 'rgba(54, 162, 235, 1)' };
break;
case 'udiff':
color = { fill: 'rgba(75, 192, 192, 0.2)', stroke: 'rgba(75, 192, 192, 1)' };
break;
case 'diff-fenced':
color = { fill: 'rgba(153, 102, 255, 0.2)', stroke: 'rgba(153, 102, 255, 1)' };
break;
default:
color = { fill: 'rgba(201, 203, 207, 0.2)', stroke: 'rgba(201, 203, 207, 1)' };
}
return {
text: format,
fillStyle: color.fill,
strokeStyle: color.stroke,
lineWidth: 1,
hidden: false
};
});
}
},
onClick: function(e, legendItem, legend) {
var ci = legend.chart;
var clickedFormat = legendItem.text;
legendItem.hidden = !legendItem.hidden;
ci.data.datasets[0].data.forEach(function(dataPoint, i) {
var meta = ci.getDatasetMeta(0);
if (allData[i].edit_format === clickedFormat) {
meta.data[i].hidden = legendItem.hidden;
}
});
ci.update();
}
}
}
}
});
updateChart();
});
</script>

1
aider/website/_includes/multi-line.md
View file

@ -2,3 +2,4 @@ You can send long, multi-line messages in the chat in a few ways:
- Paste a multi-line message directly into the chat.
- Enter `{` alone on the first line to start a multiline message and `}` alone on the last line to end it.
- Use Meta-ENTER to start a new line without sending the message (Esc+ENTER in some environments).
- Use `/paste` to paste text from the clipboard into the chat.

2
aider/website/_includes/nav_footer_custom.html
View file

@ -1,7 +1,7 @@
<footer class="site-footer">
Aider is AI pair programming in your terminal.
Aider is on
<a href="https://github.com/paul-gauthier/aider">GitHub</a>
<a href="https://github.com/Aider-AI/aider">GitHub</a>
and
<a href="https://discord.gg/Tv2uQnR88V">Discord</a>.
</footer>

9
aider/website/_includes/replit-pipx.md Normal file
View file

@ -0,0 +1,9 @@
To use aider with pipx on replit, you can run these commands in the replit shell:
```
pip install pipx
pipx run aider-chat ...normal aider args...
```
If you install aider with pipx on replit and try and run it as just `aider` it will crash with a missing `libstdc++.so.6` library.

10
aider/website/_posts/2023-10-22-repomap.md
View file

@ -110,9 +110,9 @@ source code, by including the critical lines of code for each definition.
Here's a
sample of the map of the aider repo, just showing the maps of
[base_coder.py](https://github.com/paul-gauthier/aider/blob/main/aider/coders/base_coder.py)
[base_coder.py](https://github.com/Aider-AI/aider/blob/main/aider/coders/base_coder.py)
and
[commands.py](https://github.com/paul-gauthier/aider/blob/main/aider/commands.py)
[commands.py](https://github.com/Aider-AI/aider/blob/main/aider/commands.py)
:
```
@ -188,7 +188,7 @@ It specifically uses the
[py-tree-sitter-languages](https://github.com/grantjenks/py-tree-sitter-languages)
python module,
which provides simple, pip-installable binary wheels for
[most popular programming languages](https://github.com/paul-gauthier/grep-ast/blob/main/grep_ast/parsers.py).
[most popular programming languages](https://github.com/Aider-AI/grep-ast/blob/main/grep_ast/parsers.py).
Tree-sitter parses source code into an Abstract Syntax Tree (AST) based
on the syntax of the programming language.
@ -209,7 +209,7 @@ that aider originally used.
Switching from ctags to tree-sitter provides a bunch of benefits:
- The map is richer, showing full function call signatures and other details straight from the source files.
- Thanks to `py-tree-sitter-languages`, we get full support for many programming languages via a python package that's automatically installed as part of the normal `python -m pip install aider-chat`.
- Thanks to `py-tree-sitter-languages`, we get full support for many programming languages via a python package that's automatically installed as part of the normal `python -m pip install -U aider-chat`.
- We remove the requirement for users to manually install `universal-ctags` via some external tool or package manager (brew, apt, choco, etc).
- Tree-sitter integration is a key enabler for future work and capabilities for aider.
@ -245,7 +245,7 @@ just install [aider](https://aider.chat/docs/install.html).
## Credits
Aider uses
[modified versions of the tags.scm files](https://github.com/paul-gauthier/aider/tree/main/aider/queries)
[modified versions of the tags.scm files](https://github.com/Aider-AI/aider/tree/main/aider/queries)
from these
open source tree-sitter language implementations:

4
aider/website/_posts/2024-03-08-claude-3.md
View file

@ -23,14 +23,14 @@ making it the best available model for pair programming with AI.
To use Claude 3 Opus with aider:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export ANTHROPIC_API_KEY=sk-...
aider --opus
```
## Aider's code editing benchmark
[Aider](https://github.com/paul-gauthier/aider)
[Aider](https://github.com/Aider-AI/aider)
is an open source command line chat tool that lets you
pair program with AI on code in your local git repo.

2
aider/website/_posts/2024-04-09-gpt-4-turbo.md
View file

@ -52,7 +52,7 @@ def some_complex_method(foo, bar):
# ... implement method here ...
```
Aider uses a ["laziness" benchmark suite](https://github.com/paul-gauthier/refactor-benchmark)
Aider uses a ["laziness" benchmark suite](https://github.com/Aider-AI/refactor-benchmark)
which is designed to both provoke and quantify lazy coding.
It consists of
89 python refactoring tasks

2
aider/website/_posts/2024-05-02-browser.md
View file

@ -46,7 +46,7 @@ It also supports [connecting to almost any LLM](https://aider.chat/docs/llms.htm
Use the `--browser` switch to launch the browser version of aider:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export OPENAI_API_KEY=<key> # Mac/Linux
setx OPENAI_API_KEY <key> # Windows, restart shell after setx

2
aider/website/_posts/2024-05-13-models-over-time.md
View file

@ -15,7 +15,7 @@ nav_exclude: true
I recently wanted to draw a graph showing how LLM code editing skill has been
changing over time as new models have been released by OpenAI, Anthropic and others.
I have all the
[data in a yaml file](https://github.com/paul-gauthier/aider/blob/main/website/_data/edit_leaderboard.yml) that is used to render
[data in a yaml file](https://github.com/Aider-AI/aider/blob/main/website/_data/edit_leaderboard.yml) that is used to render
[aider's LLM leaderboards](https://aider.chat/docs/leaderboards/).
Below is the aider chat transcript, which shows:

2
aider/website/_posts/2024-05-22-linting.md
View file

@ -25,7 +25,7 @@ This increases the ability of the LLM to understand the problem and
make the correct changes to resolve it.
Aider ships with basic linters built with tree-sitter that support
[most popular programming languages](https://github.com/paul-gauthier/grep-ast/blob/main/grep_ast/parsers.py).
[most popular programming languages](https://github.com/Aider-AI/grep-ast/blob/main/grep_ast/parsers.py).
These built in linters will detect syntax errors and other fatal problems with the code.
You can also configure aider to use your preferred linters.

2
aider/website/_posts/2024-05-22-swe-bench-lite.md
View file

@ -76,7 +76,7 @@ The held out "acceptance tests" were *only* used
after benchmarking to compute statistics on which problems aider
correctly resolved.
The [full harness to run aider on SWE Bench Lite is available on GitHub](https://github.com/paul-gauthier/aider-swe-bench).
The [full harness to run aider on SWE Bench Lite is available on GitHub](https://github.com/Aider-AI/aider-swe-bench).
The benchmarking process was similar to how a developer might use aider to
resolve a GitHub issue:

2
aider/website/_posts/2024-05-24-self-assembly.md
View file

@ -13,7 +13,7 @@ nav_exclude: true
[![self assembly](/assets/self-assembly.jpg)](https://aider.chat/assets/self-assembly.jpg)
The
[aider git repo](https://github.com/paul-gauthier/aider)
[aider git repo](https://github.com/Aider-AI/aider)
currently contains about 4K commits and 14K lines of code.
Aider made 15% of the commits, inserting 4.8K and deleting 1.5K lines of code.

4
aider/website/_posts/2024-06-02-main-swe-bench.md
View file

@ -64,7 +64,7 @@ with the problem statement
submitted as the opening chat message from "the user".
- After that aider ran as normal, except all of aider's
suggestions were always accepted without user approval.
- A [simple harness](https://github.com/paul-gauthier/aider-swe-bench#the-aider-agent) was used to retry the SWE Bench problem if aider produced code that wasn't *plausibly correct*.
- A [simple harness](https://github.com/Aider-AI/aider-swe-bench#the-aider-agent) was used to retry the SWE Bench problem if aider produced code that wasn't *plausibly correct*.
Plausibly correct means that aider reported that it had successfully edited the repo
without causing syntax errors or breaking any *pre-existing* tests.
- If the solution from aider with GPT-4o wasn't plausible, the harness launched aider to try again from scratch using Claude 3 Opus.
@ -90,7 +90,7 @@ For a detailed discussion of the benchmark
methodology, see the
[article about aider's SWE Bench Lite results](https://aider.chat/2024/05/22/swe-bench-lite.html).
Also, the
[aider SWE Bench repository on GitHub](https://github.com/paul-gauthier/aider-swe-bench)
[aider SWE Bench repository on GitHub](https://github.com/Aider-AI/aider-swe-bench)
contains the harness and statistics code used for the benchmarks.
The benchmarking process was similar to how a developer might use aider to

6
aider/website/_posts/2024-07-01-sonnet-not-lazy.md
View file

@ -37,8 +37,8 @@ Users who tested Sonnet with a preview of
[aider's latest release](https://aider.chat/HISTORY.html#aider-v0410)
were thrilled:
- *Works like a charm. It is a monster. It refactors files of any size like it is nothing. The continue trick with Sonnet is truly the holy grail. Aider beats [other tools] hands down. I'm going to cancel both subscriptions.* -- [Emasoft](https://github.com/paul-gauthier/aider/issues/705#issuecomment-2200338971)
- *Thanks heaps for this feature - it's a real game changer. I can be more ambitious when asking Claude for larger features.* -- [cngarrison](https://github.com/paul-gauthier/aider/issues/705#issuecomment-2196026656)
- *Works like a charm. It is a monster. It refactors files of any size like it is nothing. The continue trick with Sonnet is truly the holy grail. Aider beats [other tools] hands down. I'm going to cancel both subscriptions.* -- [Emasoft](https://github.com/Aider-AI/aider/issues/705#issuecomment-2200338971)
- *Thanks heaps for this feature - it's a real game changer. I can be more ambitious when asking Claude for larger features.* -- [cngarrison](https://github.com/Aider-AI/aider/issues/705#issuecomment-2196026656)
- *Fantastic...! It's such an improvement not being constrained by output token length issues. [I refactored] a single JavaScript file into seven smaller files using a single Aider request.* -- [John Galt](https://discord.com/channels/1131200896827654144/1253492379336441907/1256250487934554143)
## Hitting the 4k token output limit
@ -116,7 +116,7 @@ for more details, but
you can get started quickly with aider and Sonnet like this:
```
$ python -m pip install aider-chat
$ python -m pip install -U aider-chat
$ export ANTHROPIC_API_KEY=<key> # Mac/Linux
$ setx ANTHROPIC_API_KEY <key> # Windows, restart shell after setx

2
aider/website/_posts/2024-07-25-new-models.md
View file

@ -30,7 +30,7 @@ included for scale.
You can code with all of these models using aider like this:
```
$ python -m pip install aider-chat
$ python -m pip install -U aider-chat
# Change directory into a git repo to work on
$ cd /to/your/git/repo

12
aider/website/_posts/2024-08-14-code-in-json.md
View file

@ -11,7 +11,8 @@ nav_exclude: true
# LLMs are bad at returning code in JSON
LLMs produce lower quality code if they’re asked to return it as part of a structured JSON response. This seems to be true for many top models, including those with specialized support for JSON. Benchmarks show that models struggle with syntactic issues related to quoting and escaping.
LLMs produce lower quality code if they’re asked to return it as part of a structured JSON response. This seems to be true for many top models, including those with specialized support for JSON. Benchmarks show that models struggle with syntax errors in the code
they write, related to quoting and escaping it into JSON.
The benchmark results also imply a decreased capacity for solving coding problems due to the burden of JSON formatting.
{% include code-in-json-benchmark.js %}
@ -150,7 +151,8 @@ to assess the impact of JSON-wrapping code:
- gpt-4o-2024-05-13
- gpt-4o-2024-08-06
Each combination of model and code wrapping strategy was benchmarked 5 times.
Each combination of model and code wrapping strategy was benchmarked 5 times
on all 133 problems.
### Overall coding skill
@ -172,7 +174,11 @@ Both JSON results were well below the markdown result.
### Syntax errors
Models tend to make more syntax errors when asked to wrap code in JSON.
Models tend to make more syntax errors *in the code they write*
when asked to wrap it in JSON.
The models can reliably
produce valid JSON, but code inside is more prone to syntax errors.
Figure 2 shows the number of syntax errors found in the code produced by each
model and code wrapping strategy.
It totals up the `SyntaxError` and `IndentationError` errors from all 5 runs,

145
aider/website/_posts/2024-08-26-sonnet-seems-fine.md Normal file
View file

@ -0,0 +1,145 @@
---
title: Sonnet seems as good as ever
excerpt: Sonnet's score on the aider code editing benchmark has been stable since it launched.
highlight_image: /assets/sonnet-seems-fine.jpg
---
{% if page.date %}
<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
{% endif %}
# Sonnet seems as good as ever
Recently there has been a lot of speculation that Sonnet has been
dumbed-down, nerfed or is otherwise performing worse.
Sonnet seems as good as ever, when performing the
[aider code editing benchmark](/docs/benchmarks.html#the-benchmark)
via the API.
Below is a graph showing the performance of Claude 3.5 Sonnet over time.
It shows every clean, comparable benchmark run performed since Sonnet launched.
Benchmarks were performed for various reasons, usually
to evaluate the effects of small changes to aider's system prompts.
The graph shows variance, but no indication of a noteworthy
degradation.
There is always some variance in benchmark results, typically +/- 2%
between runs with identical prompts.
It's worth noting that these results would not capture any changes
made to Anthropic web chat's use of Sonnet.
<div class="chart-container" style="position: relative; height:400px; width:100%">
<canvas id="sonnetPerformanceChart"></canvas>
</div>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://cdn.jsdelivr.net/npm/moment@2.29.4/moment.min.js"></script>
<script src="https://cdn.jsdelivr.net/npm/chartjs-adapter-moment@1.0.1/dist/chartjs-adapter-moment.min.js"></script>
<script>
document.addEventListener('DOMContentLoaded', function() {
var ctx = document.getElementById('sonnetPerformanceChart').getContext('2d');
var sonnetData = {{ site.data.sonnet-fine | jsonify }};
var chartData = sonnetData.map(item => ({
x: moment(item.date).toDate(),
y1: item.pass_rate_1,
y2: item.pass_rate_2
})).sort((a, b) => a.x - b.x);
new Chart(ctx, {
type: 'scatter',
data: {
datasets: [{
label: 'Pass Rate 1',
data: chartData.map(item => ({ x: item.x, y: item.y1 })),
backgroundColor: 'rgb(75, 192, 192)',
pointRadius: 5,
pointHoverRadius: 7
}, {
label: 'Pass Rate 2',
data: chartData.map(item => ({ x: item.x, y: item.y2 })),
backgroundColor: 'rgb(255, 99, 132)',
pointRadius: 5,
pointHoverRadius: 7
}]
},
options: {
responsive: true,
maintainAspectRatio: false,
scales: {
y: {
beginAtZero: true,
title: {
display: true,
text: 'Pass Rate (%)',
font: {
size: 14
}
},
ticks: {
font: {
size: 12
}
}
},
x: {
type: 'time',
time: {
unit: 'day'
},
title: {
display: true,
text: 'Date',
font: {
size: 14
}
},
ticks: {
font: {
size: 12
}
}
}
},
plugins: {
title: {
display: true,
text: 'Claude 3.5 Sonnet Performance Over Time',
font: {
size: 18
}
},
legend: {
labels: {
font: {
size: 14
}
}
},
tooltip: {
callbacks: {
label: function(context) {
let label = context.dataset.label || '';
if (label) {
label += ': ';
}
if (context.parsed.y !== null) {
label += context.parsed.y.toFixed(1) + '%';
}
return label;
}
}
}
}
}
});
});
</script>
> This graph shows the performance of Claude 3.5 Sonnet on
[aider's code editing benchmark](/docs/benchmarks.html#the-benchmark)
> over time. 'Pass Rate 1' represents the initial success rate, while 'Pass Rate 2' shows the success rate after a second attempt with a chance to fix testing errors.
> The
> [aider LLM code editing leaderboard](https://aider.chat/docs/leaderboards/)
> ranks models based on Pass Rate 2.

116
aider/website/_posts/2024-09-12-o1.md Normal file
View file

@ -0,0 +1,116 @@
---
title: o1-preview is SOTA on the aider leaderboard
excerpt: Preliminary benchmark results for the new OpenAI o1 models.
nav_exclude: true
---
{% if page.date %}
<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
{% endif %}
# OpenAI o1-preview is SOTA on the aider leaderboard
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
{% assign edit_sorted = site.data.o1_results | sort: 'pass_rate_2' | reverse %}
{% include leaderboard_graph.html
chart_id="editChart"
data=edit_sorted
row_prefix="edit-row"
pass_rate_key="pass_rate_2"
%}
## o1-preview
OpenAI o1-preview scored 79.7% on aider's code editing benchmark,
a state of the art result.
It achieved this result with the
["whole" edit format](/docs/leaderboards/#notes-on-the-edit-format),
where the LLM returns a full copy of the source code file with changes.
It is much more practical to use aider's
["diff" edit format](/docs/leaderboards/#notes-on-the-edit-format),
which allows the LLM to return search/replace blocks to
efficiently edit the source code.
This saves significant time and token costs.
Using the diff edit format the o1-preview model had a strong
benchmark score of 75.2%.
This likely places o1-preview between Sonnet and GPT-4o for practical use,
but at significantly higher cost.
## o1-mini
OpenAI o1-mini is priced similarly to GPT-4o and Claude 3.5 Sonnet,
but scored below those models.
It also works best with the whole edit format.
## Future work
The o1-preview model had trouble conforming to aider's diff edit format.
The o1-mini model had trouble conforming to both the whole and diff edit formats.
Aider is extremely permissive and tries hard to accept anything close
to the correct formats.
It is surprising that such strong models had trouble with
the syntactic requirements of simple text output formats.
It seems likely that aider could optimize its prompts and edit formats to
better harness the o1 models.
## Using aider with o1
OpenAI's new o1 models are supported in v0.57.0 of aider:
```
aider --model o1-mini
aider --model o1-preview
```
{: .note }
> These are initial benchmark results for the o1 models,
> based on aider v0.56.1-dev.
> See the [aider leaderboards](/docs/leaderboards/) for up-to-date results
> based on the latest aider releases.
<table style="width: 100%; max-width: 800px; margin: auto; border-collapse: collapse; box-shadow: 0 2px 4px rgba(0,0,0,0.1); font-size: 14px;">
<thead style="background-color: #f2f2f2;">
<tr>
<th style="padding: 8px; text-align: left;">Model</th>
<th style="padding: 8px; text-align: center;">Percent completed correctly</th>
<th style="padding: 8px; text-align: center;">Percent using correct edit format</th>
<th style="padding: 8px; text-align: left;">Command</th>
<th style="padding: 8px; text-align: center;">Edit format</th>
</tr>
</thead>
<tbody>
{% for row in edit_sorted %}
<tr style="border-bottom: 1px solid #ddd;">
<td style="padding: 8px;">{{ row.model }}</td>
<td style="padding: 8px; text-align: center;">{{ row.pass_rate_2 }}%</td>
<td style="padding: 8px; text-align: center;">{{ row.percent_cases_well_formed }}%</td>
<td style="padding: 8px;"><code>{{ row.command }}</code></td>
<td style="padding: 8px; text-align: center;">{{ row.edit_format }}</td>
</tr>
{% endfor %}
</tbody>
</table>
<style>
tr.selected {
color: #0056b3;
}
table {
table-layout: fixed;
}
td, th {
word-wrap: break-word;
overflow-wrap: break-word;
}
td:nth-child(3), td:nth-child(4) {
font-size: 12px;
}
</style>

418
aider/website/_posts/2024-09-26-architect.md Normal file
View file

@ -0,0 +1,418 @@
---
title: Separating code reasoning and editing
excerpt: An Architect model describes how to solve the coding problem, and an Editor model translates that into file edits. This Architect/Editor approach produces SOTA benchmark results.
highlight_image: /assets/architect.jpg
draft: false
nav_exclude: true
---
{% if page.date %}
<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
{% endif %}
# Separating code reasoning and editing
Aider now has experimental support for using two models to complete each coding task:
- An Architect model is asked to describe how to solve the coding problem.
- An Editor model is given the Architect's solution and asked to produce specific code editing instructions to apply those changes to existing source files.
Splitting up "code reasoning" and "code editing" in this manner
has produced SOTA results on
[aider's code editing benchmark](/docs/benchmarks.html#the-benchmark).
Using o1-preview as the Architect with either DeepSeek or o1-mini as the
Editor produced the SOTA score of 85%.
Using the Architect/Editor approach
also significantly improved the benchmark scores of many
models, compared to their previous "solo" baseline scores (striped bars).
<style>
.shaded td {
background-color: #f2f2f2;
border-top: 1px solid #ccc;
}
.table-container {
max-width: 100%;
overflow-x: auto;
}
.responsive-table {
border-collapse: separate;
border-spacing: 0;
width: 100%;
font-size: 16px;
border: 1px solid #ddd;
}
.responsive-table th, .responsive-table td {
padding: 8px;
text-align: left;
border-bottom: 1px solid #ddd;
word-break: break-word;
}
.responsive-table th {
background-color: #e2e2e2;
}
.responsive-table th:first-child,
.responsive-table td:first-child {
border-left: 1px solid #ddd;
}
.responsive-table th:last-child,
.responsive-table td:last-child {
border-right: 1px solid #ddd;
}
@media screen and (max-width: 600px) {
.responsive-table {
font-size: 12px;
}
.responsive-table th, .responsive-table td {
padding: 4px;
}
}
</style>
<style>
#passRateChart {
max-width: 100%;
height: auto !important;
}
</style>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script src="https://cdn.jsdelivr.net/npm/chartjs-plugin-annotation@1.0.2"></script>
{% assign sorted_data = site.data.architect | sort: "pass_rate_2" | reverse %}
<canvas id="passRateChart" width="400" height="250"></canvas>
<script>
document.addEventListener("DOMContentLoaded", function() {
var ctx = document.getElementById('passRateChart').getContext('2d');
// Function to determine aspect ratio and base font size based on screen width
function getChartSettings() {
if (window.innerWidth < 600) {
return { aspectRatio: 1, baseFontSize: 8 }; // Slightly taller for small screens
} else if (window.innerWidth < 800) {
return { aspectRatio: 1.2, baseFontSize: 10 }; // Slightly taller for small screens
} else {
return { aspectRatio: 1.4, baseFontSize: 12 }; // Slightly taller for larger screens
}
}
var chartSettings = getChartSettings();
var baseFontSize = chartSettings.baseFontSize;
var labels = [];
var data = [];
var colorMapping = {
"claude-3.5-sonnet": "rgba(75, 192, 192, 0.2)",
"gpt-4o": "rgba(255, 99, 132, 0.2)",
"o1-preview": "rgba(54, 162, 235, 0.2)",
"o1-mini": "rgba(255, 206, 86, 0.2)",
"gpt-4o-mini": "rgba(153, 102, 255, 0.2)"
};
var borderColorMapping = {
"claude-3.5-sonnet": "rgba(75, 192, 192, 1)",
"gpt-4o": "rgba(255, 99, 132, 1)",
"o1-preview": "rgba(54, 162, 235, 1)",
"o1-mini": "rgba(255, 206, 86, 1)",
"gpt-4o-mini": "rgba(153, 102, 255, 1)"
};
var backgroundColors = [];
var borderColors = [];
var patterns = {};
for (var key in colorMapping) {
patterns[key] = ctx.createPattern(createStripePattern(colorMapping[key]), 'repeat');
}
{% assign grouped_data = sorted_data | group_by: "model" %}
{% for group in grouped_data %}
{% for item in group.items %}
if ("{{ item.editor_model }}" == "") {
labels.push("Baseline");
} else {
labels.push("{{ item.editor_model }}/{{ item.editor_edit_format | default: item.edit_format }}");
}
data.push({{ item.pass_rate_2 }});
if ("{{ item.editor_model }}" == "") {
backgroundColors.push(patterns["{{ item.model }}"]);
} else {
backgroundColors.push(colorMapping["{{ item.model }}"]);
}
borderColors.push(borderColorMapping["{{ item.model }}"]);
{% endfor %}
{% endfor %}
labels.reverse();
data.reverse();
backgroundColors.reverse();
borderColors.reverse();
var chart = new Chart(ctx, {
type: 'bar',
data: {
labels: labels,
datasets: [{
label: 'Pass Rate',
data: data,
backgroundColor: backgroundColors,
borderColor: borderColors,
borderWidth: 1
}]
},
options: {
responsive: true,
maintainAspectRatio: true,
aspectRatio: chartSettings.aspectRatio,
scales: {
y: {
beginAtZero: true,
title: {
display: true,
text: 'Pass Rate (%)',
font: {
size: baseFontSize + 6
}
},
ticks: {
font: {
size: baseFontSize
}
}
},
x: {
title: {
display: true,
text: 'Editor model and edit format',
font: {
size: baseFontSize + 6
}
},
ticks: {
font: {
size: baseFontSize + 4
},
maxRotation: 90, // Allow full rotation if needed
minRotation: 45 // Start rotating at 45 degrees to fit more labels
}
}
},
plugins: {
annotation: {
annotations: {
line1: {
type: 'line',
yMin: 79.7,
yMax: 79.7,
borderColor: 'rgba(255, 99, 132, 0.8)',
borderWidth: 2,
borderDash: [6, 6],
label: {
content: 'Previous SOTA',
enabled: true,
position: 'start',
xAdjust: 10,
font: {
size: baseFontSize
}
}
}
}
},
legend: {
display: true,
title: {
display: true,
text: 'Architect model',
font: {
size: baseFontSize + 2,
weight: 'bold'
}
},
labels: {
font: {
size: baseFontSize + 4
},
generateLabels: function(chart) {
var colorMapping = {
"o1-preview": "rgba(54, 162, 235, 0.2)",
"claude-3.5-sonnet": "rgba(75, 192, 192, 0.2)",
"gpt-4o": "rgba(255, 99, 132, 0.2)",
"o1-mini": "rgba(255, 206, 86, 0.2)",
"gpt-4o-mini": "rgba(153, 102, 255, 0.2)"
};
return Object.keys(colorMapping).reverse().map(function(key) {
return {
text: key,
fillStyle: colorMapping[key],
strokeStyle: colorMapping[key].replace('0.2', '1'),
lineWidth: 1
};
});
}
}
}
}
}
});
// Update aspect ratio and font sizes on window resize
window.addEventListener('resize', function() {
var newSettings = getChartSettings();
chart.options.aspectRatio = newSettings.aspectRatio;
baseFontSize = newSettings.baseFontSize;
// Update font sizes
chart.options.scales.y.title.font.size = baseFontSize + 6;
chart.options.scales.y.ticks.font.size = baseFontSize;
chart.options.scales.x.title.font.size = baseFontSize + 6;
chart.options.scales.x.ticks.font.size = baseFontSize + 4;
chart.options.plugins.annotation.annotations.line1.label.font.size = baseFontSize;
chart.options.plugins.legend.title.font.size = baseFontSize + 4;
chart.options.plugins.legend.labels.font.size = baseFontSize + 4;
chart.update();
});
});
function createStripePattern(baseColor) {
var canvas = document.createElement('canvas');
canvas.width = 10;
canvas.height = 10;
var ctx = canvas.getContext('2d');
ctx.fillStyle = baseColor;
ctx.fillRect(0, 0, canvas.width, canvas.height);
ctx.strokeStyle = 'rgba(0, 0, 0, 0.1)';
ctx.lineWidth = 2;
ctx.beginPath();
ctx.moveTo(0, 0);
ctx.lineTo(10, 10);
ctx.stroke();
return canvas;
}
</script>
## Motivation
This approach was motivated by the release of OpenAI's o1 models.
They are strong at reasoning, but often fail to output properly formatted
code editing instructions.
It helps to instead let them describe the solution
however they prefer and then pass that output to a more traditional LLM.
This second Editor LLM can then interpret the solution description and
produce the code editing instructions needed to update
the existing source code.
This approach has recently become attractive for aider due to
rapid improvements in the speed and costs of frontier models.
In particular, chaining older LLMs would have been quite slow and
incompatible with aider's goal of providing an interactive,
pair programming AI coding experience.
## Code reasoning and code editing
Normally aider asks the model to solve a coding problem in one prompt,
asking the LLM to explain the solution and return
a well formatted series of file edits.
All of [aider's editing formats](/docs/more/edit-formats.html)
require the LLM to return source code edits in a specific text
format, so that aider can process the edits and apply them to the local source files.
Because this all happens in a single prompt/response round trip to the LLM,
the model has to split its attention between
solving the coding problem and conforming to the edit format.
The Architect/Editor approach splits this into two inference steps, possibly
using two different LLMs:
1. Solve the coding problem (Architect).
2. Turn the proposed solution into a series of well formed code edits (Editor).
The Architect/Editor approach allows the Architect to focus on solving the coding problem
and *describe the solution however comes naturally to it*.
Similarly, the Editor can focus all of its attention on properly formatting the edits
without needing to reason much about how to solve the coding problem.
We can assign the Architect and Editor roles to LLMs which are well suited to their needs.
Strong reasoning model like o1-preview make excellent Architects, while
the Editor role can be assigned to an appropriate model based on cost, speed
and code editing skill.
## Results
The graph above and the table below show the
[aider's code editing benchmark](/docs/benchmarks.html#the-benchmark)
score for various combinations of Architect and Editor models.
Some noteworthy observations:
- Pairing o1-preview as Architect with either Deepseek or o1-mini as Editor sets a SOTA significantly above the previous best score. This result is obtained with the "whole" editing format, requiring the Editor to output a full update copy of each edited source file. Both of these steps are therefore quite slow, so probably not practical for interactive use with aider.
- Pairing OpenAI's o1-preview with Anthropic's Sonnet as the Editor produces the second best result. This is an entirely practical configuration for users able to work with both providers.
- Pairing many models with themselves in the Architect/Editor configuration can provide
significant benefits.
Sonnet, GPT-4o and GPT-4o-mini all scored higher when used as an Architect/Editor pair.
- Deepseek is surprisingly effective as an Editor model. It seems remarkably capable at turning proposed coding solutions into new, updated versions of the source files. Using the efficient "diff" editing format, Deepseek helps all the Architect models except for Sonnet.
## Try it!
The development version of aider
has built in defaults to support Architect/Editor coding with
o1-preview, o1-mini, GPT-4o and Claude 3.5 Sonnet.
Run aider with `--architect` or get started quickly like this:
```
pip install -U aider-chat
# Change directory into a git repo
cd /to/your/git/repo
# Work with Claude 3.5 Sonnet as the Architect and Editor
export ANTHROPIC_API_KEY=your-key-goes-here
aider --sonnet --architect
# Work with OpenAI models, using gpt-4o as the Editor
export OPENAI_API_KEY=your-key-goes-here
aider --4o --architect
aider --o1-mini --architect
aider --o1-preview --architect
```
## More info
Aider has a number of "chat modes", and "architect" is available as a new chat mode.
The `--architect` switch is a shortcut for `--chat-mode architect`.
For more details, see documentation on
[aider's chat modes](/docs/usage/modes.html).
## Full results
Below are the benchmark results using various models as the Architect, paired with
various models as the Editor.
Each section includes a "baseline" result,
where the model works
by itself in aider's normal "code" editing mode
(not as part of an Architect/Editor configuration).
This "solo" baseline represents the performance previously available when using
this model with aider.
<div class="table-container">
<table class="responsive-table">
<thead>
<tr>
<th>Architect</th>
<th>Editor</th>
<th>Edit Format</th>
<th>Pass Rate</th>
</tr>
</thead>
<tbody>
{% for group in grouped_data %}
{% assign group_class = forloop.index | modulo: 2 | plus: 1 %}
{% for item in group.items %}
<tr class="{% if group_class == 1 %}shaded{% endif %}">
<td>{{ item.model }}</td>
<td>{% if item.editor_model %}{{ item.editor_model }}{% else %}<b>Baseline</b>{% endif %}</td>
<td style="text-align: center;">{{ item.editor_edit_format | default: item.edit_format }}</td>
<td style="text-align: right;">{{ item.pass_rate_2 }}%</td>
</tr>
{% endfor %}
{% endfor %}
</tbody>
</table>
</div>

BIN
aider/website/assets/architect.jpg Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 337 KiB

BIN
aider/website/assets/prompt-caching.jpg Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 307 KiB

154
aider/website/assets/sample.aider.conf.yml
View file

@ -12,30 +12,30 @@
# options:
## show this help message and exit
#help:
#help: xxx
#######
# Main:
## Specify the OpenAI API key
#openai-api-key:
#openai-api-key: xxx
## Specify the Anthropic API key
#anthropic-api-key:
#anthropic-api-key: xxx
## Specify the model to use for the main chat
#model:
#model: xxx
## Use claude-3-opus-20240229 model for the main chat
#opus: false
## Use claude-3-5-sonnet-20240620 model for the main chat
## Use claude-3-5-sonnet-20241022 model for the main chat
#sonnet: false
## Use gpt-4-0613 model for the main chat
#4: false
## Use gpt-4o model for the main chat
## Use gpt-4o-2024-08-06 model for the main chat
#4o: false
## Use gpt-4o-mini model for the main chat
@ -50,26 +50,32 @@
## Use deepseek/deepseek-coder model for the main chat
#deepseek: false
## Use o1-mini model for the main chat
#o1-mini: false
## Use o1-preview model for the main chat
#o1-preview: false
#################
# Model Settings:
## List known models which match the (partial) MODEL name
#models:
#list-models: xxx
## Specify the api base url
#openai-api-base:
#openai-api-base: xxx
## Specify the api_type
#openai-api-type:
#openai-api-type: xxx
## Specify the api_version
#openai-api-version:
#openai-api-version: xxx
## Specify the deployment_id
#openai-api-deployment-id:
#openai-api-deployment-id: xxx
## Specify the OpenAI organization ID
#openai-organization-id:
#openai-organization-id: xxx
## Specify a file with aider model settings for unknown models
#model-settings-file: .aider.model.settings.yml
@ -81,23 +87,50 @@
#verify-ssl: true
## Specify what edit format the LLM should use (default depends on model)
#edit-format:
#edit-format: xxx
## Use architect edit format for the main chat
#architect: false
## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#weak-model:
#weak-model: xxx
## Specify the model to use for editor tasks (default depends on --model)
#editor-model: xxx
## Specify the edit format for the editor model (default: depends on editor model)
#editor-edit-format: xxx
## Only work with models that have meta-data available (default: True)
#show-model-warnings: true
## Max number of tokens to use for repo map, use 0 to disable (default: 1024)
#map-tokens:
## Maximum number of tokens to use for chat history. If not specified, uses the model's max_chat_history_tokens.
#max-chat-history-tokens:
## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#max-chat-history-tokens: xxx
## Specify the .env file to load (default: .env in git root)
#env-file: .env
#################
# Cache Settings:
## Enable caching of prompts (default: False)
#cache-prompts: false
## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#cache-keepalive-pings: false
###################
# Repomap Settings:
## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
#map-tokens: xxx
## Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
#map-refresh: auto
## Multiplier for map tokens when no files are specified (default: 2)
#map-multiplier-no-files: true
################
# History Files:
@ -111,7 +144,7 @@
#restore-chat-history: false
## Log the conversation with the LLM to this file (for example, .aider.llm.history)
#llm-history-file:
#llm-history-file: xxx
##################
# Output Settings:
@ -132,14 +165,29 @@
#user-input-color: #00cc00
## Set the color for tool output (default: None)
#tool-output-color:
#tool-output-color: xxx
## Set the color for tool error messages (default: red)
## Set the color for tool error messages (default: #FF2222)
#tool-error-color: #FF2222
## Set the color for tool warning messages (default: #FFA500)
#tool-warning-color: #FFA500
## Set the color for assistant output (default: #0088ff)
#assistant-output-color: #0088ff
## Set the color for the completion menu (default: terminal's default text color)
#completion-menu-color: xxx
## Set the background color for the completion menu (default: terminal's default background color)
#completion-menu-bg-color: xxx
## Set the color for the current item in the completion menu (default: terminal's default background color)
#completion-menu-current-color: xxx
## Set the background color for the current item in the completion menu (default: terminal's default text color)
#completion-menu-current-bg-color: xxx
## Set the markdown code theme (default: default, other options include monokai, solarized-dark, solarized-light)
#code-theme: default
@ -183,11 +231,14 @@
#commit: false
## Specify a custom prompt for generating commit messages
#commit-prompt:
#commit-prompt: xxx
## Perform a dry run without modifying files (default: False)
#dry-run: false
## Skip the sanity check for the git repository (default: False)
#skip-sanity-check-repo: false
########################
# Fixing and committing:
@ -195,13 +246,18 @@
#lint: false
## Specify lint commands to run for different languages, eg: "python: flake8 --select=..." (can be used multiple times)
#lint-cmd: xxx
## Specify multiple values like this:
#lint-cmd:
# - xxx
# - yyy
# - zzz
## Enable/disable automatic linting after changes (default: True)
#auto-lint: true
## Specify command to run tests
#test-cmd:
#test-cmd: xxx
## Enable/disable automatic testing after changes (default: False)
#auto-test: false
@ -225,19 +281,29 @@
# Other Settings:
## specify a file to edit (can be used multiple times)
#file: xxx
## Specify multiple values like this:
#file:
# - xxx
# - yyy
# - zzz
## specify a read-only file (can be used multiple times)
#read: xxx
## Specify multiple values like this:
#read:
# - xxx
# - yyy
# - zzz
## Use VI editing mode in the terminal (default: False)
#vim: false
## Specify the language for voice using ISO 639-1 code (default: auto)
#voice-language: en
## Specify the language to use in the chat (default: None, uses system settings)
#chat-language: xxx
## Show the version number and exit
#version:
#version: xxx
## Check for updates and return status in the exit code
#just-check-update: false
@ -245,11 +311,17 @@
## Check for new aider versions on launch
#check-update: true
## Install the latest version from the main branch
#install-main-branch: false
## Upgrade aider to the latest version from PyPI
#upgrade: false
## Apply the changes from the given file instead of running the chat (debug)
#apply:
#apply: xxx
## Always say yes to every confirmation
#yes: false
#yes-always: false
## Enable verbose output
#verbose: false
@ -264,16 +336,34 @@
#exit: false
## Specify a single message to send the LLM, process reply then exit (disables chat mode)
#message:
#message: xxx
## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
#message-file:
#message-file: xxx
## Load and execute /commands from a file on launch
#load: xxx
## Specify the encoding for input and output (default: utf-8)
#encoding: utf-8
## Specify the config file (default: search for .aider.conf.yml in git root, cwd or home directory)
#config:
#config: xxx
## Run aider in your browser
#gui: false
## Enable/disable suggesting shell commands (default: True)
#suggest-shell-commands: true
## Enable/disable fancy input with history and completion (default: True)
#fancy-input: true
#################
# Voice Settings:
## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
#voice-format: wav
## Specify the language for voice using ISO 639-1 code (default: auto)
#voice-language: en

97
aider/website/assets/sample.env
View file

@ -33,13 +33,13 @@
## Use claude-3-opus-20240229 model for the main chat
#AIDER_OPUS=
## Use claude-3-5-sonnet-20240620 model for the main chat
## Use claude-3-5-sonnet-20241022 model for the main chat
#AIDER_SONNET=
## Use gpt-4-0613 model for the main chat
#AIDER_4=
## Use gpt-4o model for the main chat
## Use gpt-4o-2024-08-06 model for the main chat
#AIDER_4O=
## Use gpt-4o-mini model for the main chat
@ -54,11 +54,17 @@
## Use deepseek/deepseek-coder model for the main chat
#AIDER_DEEPSEEK=
## Use o1-mini model for the main chat
#AIDER_O1_MINI=
## Use o1-preview model for the main chat
#AIDER_O1_PREVIEW=
#################
# Model Settings:
## List known models which match the (partial) MODEL name
#AIDER_MODELS=
#AIDER_LIST_MODELS=
## Specify the api base url
#OPENAI_API_BASE=
@ -87,21 +93,48 @@
## Specify what edit format the LLM should use (default depends on model)
#AIDER_EDIT_FORMAT=
## Use architect edit format for the main chat
#AIDER_ARCHITECT=
## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#AIDER_WEAK_MODEL=
## Specify the model to use for editor tasks (default depends on --model)
#AIDER_EDITOR_MODEL=
## Specify the edit format for the editor model (default: depends on editor model)
#AIDER_EDITOR_EDIT_FORMAT=
## Only work with models that have meta-data available (default: True)
#AIDER_SHOW_MODEL_WARNINGS=true
## Max number of tokens to use for repo map, use 0 to disable (default: 1024)
#AIDER_MAP_TOKENS=
## Maximum number of tokens to use for chat history. If not specified, uses the model's max_chat_history_tokens.
## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#AIDER_MAX_CHAT_HISTORY_TOKENS=
## Specify the .env file to load (default: .env in git root)
#AIDER_ENV_FILE=.env
#################
# Cache Settings:
## Enable caching of prompts (default: False)
#AIDER_CACHE_PROMPTS=false
## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#AIDER_CACHE_KEEPALIVE_PINGS=false
###################
# Repomap Settings:
## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
#AIDER_MAP_TOKENS=
## Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
#AIDER_MAP_REFRESH=auto
## Multiplier for map tokens when no files are specified (default: 2)
#AIDER_MAP_MULTIPLIER_NO_FILES=true
################
# History Files:
@ -138,12 +171,27 @@
## Set the color for tool output (default: None)
#AIDER_TOOL_OUTPUT_COLOR=
## Set the color for tool error messages (default: red)
## Set the color for tool error messages (default: #FF2222)
#AIDER_TOOL_ERROR_COLOR=#FF2222
## Set the color for tool warning messages (default: #FFA500)
#AIDER_TOOL_WARNING_COLOR=#FFA500
## Set the color for assistant output (default: #0088ff)
#AIDER_ASSISTANT_OUTPUT_COLOR=#0088ff
## Set the color for the completion menu (default: terminal's default text color)
#AIDER_COMPLETION_MENU_COLOR=
## Set the background color for the completion menu (default: terminal's default background color)
#AIDER_COMPLETION_MENU_BG_COLOR=
## Set the color for the current item in the completion menu (default: terminal's default background color)
#AIDER_COMPLETION_MENU_CURRENT_COLOR=
## Set the background color for the current item in the completion menu (default: terminal's default text color)
#AIDER_COMPLETION_MENU_CURRENT_BG_COLOR=
## Set the markdown code theme (default: default, other options include monokai, solarized-dark, solarized-light)
#AIDER_CODE_THEME=default
@ -192,6 +240,9 @@
## Perform a dry run without modifying files (default: False)
#AIDER_DRY_RUN=false
## Skip the sanity check for the git repository (default: False)
#AIDER_SKIP_SANITY_CHECK_REPO=false
########################
# Fixing and committing:
@ -237,8 +288,8 @@
## Use VI editing mode in the terminal (default: False)
#AIDER_VIM=false
## Specify the language for voice using ISO 639-1 code (default: auto)
#AIDER_VOICE_LANGUAGE=en
## Specify the language to use in the chat (default: None, uses system settings)
#AIDER_CHAT_LANGUAGE=
## Check for updates and return status in the exit code
#AIDER_JUST_CHECK_UPDATE=false
@ -246,11 +297,17 @@
## Check for new aider versions on launch
#AIDER_CHECK_UPDATE=true
## Install the latest version from the main branch
#AIDER_INSTALL_MAIN_BRANCH=false
## Upgrade aider to the latest version from PyPI
#AIDER_UPGRADE=false
## Apply the changes from the given file instead of running the chat (debug)
#AIDER_APPLY=
## Always say yes to every confirmation
#AIDER_YES=
#AIDER_YES_ALWAYS=
## Enable verbose output
#AIDER_VERBOSE=false
@ -270,8 +327,26 @@
## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
#AIDER_MESSAGE_FILE=
## Load and execute /commands from a file on launch
#AIDER_LOAD=
## Specify the encoding for input and output (default: utf-8)
#AIDER_ENCODING=utf-8
## Run aider in your browser
#AIDER_GUI=false
## Enable/disable suggesting shell commands (default: True)
#AIDER_SUGGEST_SHELL_COMMANDS=true
## Enable/disable fancy input with history and completion (default: True)
#AIDER_FANCY_INPUT=true
#################
# Voice Settings:
## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
#AIDER_VOICE_FORMAT=wav
## Specify the language for voice using ISO 639-1 code (default: auto)
#AIDER_VOICE_LANGUAGE=en

BIN
aider/website/assets/shell-cmds-small.mp4 Normal file
View file

Binary file not shown.

BIN
aider/website/assets/shell-cmds.jpg Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 519 KiB

BIN
aider/website/assets/sonnet-seems-fine.jpg Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 147 KiB

2
aider/website/docs/benchmarks-1106.md
View file

@ -19,7 +19,7 @@ and there's a lot
of interest about their ability to code compared to the previous versions.
With that in mind, I've been benchmarking the new models.
[Aider](https://github.com/paul-gauthier/aider)
[Aider](https://github.com/Aider-AI/aider)
is an open source command line chat tool that lets you work with GPT to edit
code in your local git repo.
To do this, aider needs to be able to reliably recognize when GPT wants to edit

2
aider/website/docs/benchmarks-speed-1106.md
View file

@ -20,7 +20,7 @@ and there's a lot
of interest about their capabilities and performance.
With that in mind, I've been benchmarking the new models.
[Aider](https://github.com/paul-gauthier/aider)
[Aider](https://github.com/Aider-AI/aider)
is an open source command line chat tool that lets you work with GPT to edit
code in your local git repo.
Aider relies on a

10
aider/website/docs/benchmarks.md
View file

@ -55,7 +55,7 @@ about prompting GPT for complex tasks like coding. It's beneficial to
minimize the "cognitive overhead" of formatting the response, allowing
GPT to concentrate on the coding task at hand.
As a thought experiment, imagine a slack conversation with a junior developer where
As a thought experiment, imagine a slack conversation with a editor developer where
you ask them to write the code to add some new feature to your app.
They're going to type the response back to you by hand in the chat.
Should they type out the
@ -168,7 +168,7 @@ requests:
### whole
The
[whole](https://github.com/paul-gauthier/aider/blob/main/aider/coders/wholefile_prompts.py)
[whole](https://github.com/Aider-AI/aider/blob/main/aider/coders/wholefile_prompts.py)
format asks GPT to return an updated copy of the entire file, including any changes.
The file should be
formatted with normal markdown triple-backtick fences, inlined with the rest of its response text.
@ -187,7 +187,7 @@ def main():
### diff
The [diff](https://github.com/paul-gauthier/aider/blob/main/aider/coders/editblock_prompts.py)
The [diff](https://github.com/Aider-AI/aider/blob/main/aider/coders/editblock_prompts.py)
format also asks GPT to return edits as part of the normal response text,
in a simple diff format.
Each edit is a fenced code block that
@ -209,7 +209,7 @@ demo.py
### whole-func
The [whole-func](https://github.com/paul-gauthier/aider/blob/main/aider/coders/wholefile_func_coder.py)
The [whole-func](https://github.com/Aider-AI/aider/blob/main/aider/coders/wholefile_func_coder.py)
format requests updated copies of whole files to be returned using the function call API.
@ -227,7 +227,7 @@ format requests updated copies of whole files to be returned using the function
### diff-func
The
[diff-func](https://github.com/paul-gauthier/aider/blob/main/aider/coders/editblock_func_coder.py)
[diff-func](https://github.com/Aider-AI/aider/blob/main/aider/coders/editblock_func_coder.py)
format requests a list of
original/updated style edits to be returned using the function call API.

996
aider/website/docs/config/adv-model-settings.md
View file

File diff suppressed because it is too large Load diff

173
aider/website/docs/config/aider_conf.md
View file

@ -21,11 +21,28 @@ load whichever is found first.
{% include env-keys-tip.md %}
## A note on lists
Lists of values can be specified either as a bulleted list:
```
read:
- CONVENTIONS.md
- anotherfile.txt
- thirdfile.py
```
Or lists can be specified using commas and square brackets:
```
read: [CONVENTIONS.md, anotherfile.txt, thirdfile.py]
```
## Sample YAML config file
Below is a sample of the YAML config file, which you
can also
[download from GitHub](https://github.com/paul-gauthier/aider/blob/main/aider/website/assets/sample.aider.conf.yml).
[download from GitHub](https://github.com/Aider-AI/aider/blob/main/aider/website/assets/sample.aider.conf.yml).
<!--[[[cog
from aider.args import get_sample_yaml
@ -51,30 +68,30 @@ cog.outl("```")
# options:
## show this help message and exit
#help:
#help: xxx
#######
# Main:
## Specify the OpenAI API key
#openai-api-key:
#openai-api-key: xxx
## Specify the Anthropic API key
#anthropic-api-key:
#anthropic-api-key: xxx
## Specify the model to use for the main chat
#model:
#model: xxx
## Use claude-3-opus-20240229 model for the main chat
#opus: false
## Use claude-3-5-sonnet-20240620 model for the main chat
## Use claude-3-5-sonnet-20241022 model for the main chat
#sonnet: false
## Use gpt-4-0613 model for the main chat
#4: false
## Use gpt-4o model for the main chat
## Use gpt-4o-2024-08-06 model for the main chat
#4o: false
## Use gpt-4o-mini model for the main chat
@ -89,26 +106,32 @@ cog.outl("```")
## Use deepseek/deepseek-coder model for the main chat
#deepseek: false
## Use o1-mini model for the main chat
#o1-mini: false
## Use o1-preview model for the main chat
#o1-preview: false
#################
# Model Settings:
## List known models which match the (partial) MODEL name
#models:
#list-models: xxx
## Specify the api base url
#openai-api-base:
#openai-api-base: xxx
## Specify the api_type
#openai-api-type:
#openai-api-type: xxx
## Specify the api_version
#openai-api-version:
#openai-api-version: xxx
## Specify the deployment_id
#openai-api-deployment-id:
#openai-api-deployment-id: xxx
## Specify the OpenAI organization ID
#openai-organization-id:
#openai-organization-id: xxx
## Specify a file with aider model settings for unknown models
#model-settings-file: .aider.model.settings.yml
@ -120,23 +143,50 @@ cog.outl("```")
#verify-ssl: true
## Specify what edit format the LLM should use (default depends on model)
#edit-format:
#edit-format: xxx
## Use architect edit format for the main chat
#architect: false
## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#weak-model:
#weak-model: xxx
## Specify the model to use for editor tasks (default depends on --model)
#editor-model: xxx
## Specify the edit format for the editor model (default: depends on editor model)
#editor-edit-format: xxx
## Only work with models that have meta-data available (default: True)
#show-model-warnings: true
## Max number of tokens to use for repo map, use 0 to disable (default: 1024)
#map-tokens:
## Maximum number of tokens to use for chat history. If not specified, uses the model's max_chat_history_tokens.
#max-chat-history-tokens:
## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#max-chat-history-tokens: xxx
## Specify the .env file to load (default: .env in git root)
#env-file: .env
#################
# Cache Settings:
## Enable caching of prompts (default: False)
#cache-prompts: false
## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#cache-keepalive-pings: false
###################
# Repomap Settings:
## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
#map-tokens: xxx
## Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
#map-refresh: auto
## Multiplier for map tokens when no files are specified (default: 2)
#map-multiplier-no-files: true
################
# History Files:
@ -150,7 +200,7 @@ cog.outl("```")
#restore-chat-history: false
## Log the conversation with the LLM to this file (for example, .aider.llm.history)
#llm-history-file:
#llm-history-file: xxx
##################
# Output Settings:
@ -171,14 +221,29 @@ cog.outl("```")
#user-input-color: #00cc00
## Set the color for tool output (default: None)
#tool-output-color:
#tool-output-color: xxx
## Set the color for tool error messages (default: red)
## Set the color for tool error messages (default: #FF2222)
#tool-error-color: #FF2222
## Set the color for tool warning messages (default: #FFA500)
#tool-warning-color: #FFA500
## Set the color for assistant output (default: #0088ff)
#assistant-output-color: #0088ff
## Set the color for the completion menu (default: terminal's default text color)
#completion-menu-color: xxx
## Set the background color for the completion menu (default: terminal's default background color)
#completion-menu-bg-color: xxx
## Set the color for the current item in the completion menu (default: terminal's default background color)
#completion-menu-current-color: xxx
## Set the background color for the current item in the completion menu (default: terminal's default text color)
#completion-menu-current-bg-color: xxx
## Set the markdown code theme (default: default, other options include monokai, solarized-dark, solarized-light)
#code-theme: default
@ -222,11 +287,14 @@ cog.outl("```")
#commit: false
## Specify a custom prompt for generating commit messages
#commit-prompt:
#commit-prompt: xxx
## Perform a dry run without modifying files (default: False)
#dry-run: false
## Skip the sanity check for the git repository (default: False)
#skip-sanity-check-repo: false
########################
# Fixing and committing:
@ -234,13 +302,18 @@ cog.outl("```")
#lint: false
## Specify lint commands to run for different languages, eg: "python: flake8 --select=..." (can be used multiple times)
#lint-cmd: xxx
## Specify multiple values like this:
#lint-cmd:
# - xxx
# - yyy
# - zzz
## Enable/disable automatic linting after changes (default: True)
#auto-lint: true
## Specify command to run tests
#test-cmd:
#test-cmd: xxx
## Enable/disable automatic testing after changes (default: False)
#auto-test: false
@ -264,19 +337,29 @@ cog.outl("```")
# Other Settings:
## specify a file to edit (can be used multiple times)
#file: xxx
## Specify multiple values like this:
#file:
# - xxx
# - yyy
# - zzz
## specify a read-only file (can be used multiple times)
#read: xxx
## Specify multiple values like this:
#read:
# - xxx
# - yyy
# - zzz
## Use VI editing mode in the terminal (default: False)
#vim: false
## Specify the language for voice using ISO 639-1 code (default: auto)
#voice-language: en
## Specify the language to use in the chat (default: None, uses system settings)
#chat-language: xxx
## Show the version number and exit
#version:
#version: xxx
## Check for updates and return status in the exit code
#just-check-update: false
@ -284,11 +367,17 @@ cog.outl("```")
## Check for new aider versions on launch
#check-update: true
## Install the latest version from the main branch
#install-main-branch: false
## Upgrade aider to the latest version from PyPI
#upgrade: false
## Apply the changes from the given file instead of running the chat (debug)
#apply:
#apply: xxx
## Always say yes to every confirmation
#yes: false
#yes-always: false
## Enable verbose output
#verbose: false
@ -303,18 +392,36 @@ cog.outl("```")
#exit: false
## Specify a single message to send the LLM, process reply then exit (disables chat mode)
#message:
#message: xxx
## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
#message-file:
#message-file: xxx
## Load and execute /commands from a file on launch
#load: xxx
## Specify the encoding for input and output (default: utf-8)
#encoding: utf-8
## Specify the config file (default: search for .aider.conf.yml in git root, cwd or home directory)
#config:
#config: xxx
## Run aider in your browser
#gui: false
## Enable/disable suggesting shell commands (default: True)
#suggest-shell-commands: true
## Enable/disable fancy input with history and completion (default: True)
#fancy-input: true
#################
# Voice Settings:
## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
#voice-format: wav
## Specify the language for voice using ISO 639-1 code (default: auto)
#voice-language: en
```
<!--[[[end]]]-->

99
aider/website/docs/config/dotenv.md
View file

@ -28,7 +28,7 @@ If the files above exist, they will be loaded in that order. Files loaded last w
Below is a sample `.env` file, which you
can also
[download from GitHub](https://github.com/paul-gauthier/aider/blob/main/aider/website/assets/sample.env).
[download from GitHub](https://github.com/Aider-AI/aider/blob/main/aider/website/assets/sample.env).
<!--[[[cog
from aider.args import get_sample_dotenv
@ -75,13 +75,13 @@ cog.outl("```")
## Use claude-3-opus-20240229 model for the main chat
#AIDER_OPUS=
## Use claude-3-5-sonnet-20240620 model for the main chat
## Use claude-3-5-sonnet-20241022 model for the main chat
#AIDER_SONNET=
## Use gpt-4-0613 model for the main chat
#AIDER_4=
## Use gpt-4o model for the main chat
## Use gpt-4o-2024-08-06 model for the main chat
#AIDER_4O=
## Use gpt-4o-mini model for the main chat
@ -96,11 +96,17 @@ cog.outl("```")
## Use deepseek/deepseek-coder model for the main chat
#AIDER_DEEPSEEK=
## Use o1-mini model for the main chat
#AIDER_O1_MINI=
## Use o1-preview model for the main chat
#AIDER_O1_PREVIEW=
#################
# Model Settings:
## List known models which match the (partial) MODEL name
#AIDER_MODELS=
#AIDER_LIST_MODELS=
## Specify the api base url
#OPENAI_API_BASE=
@ -129,21 +135,48 @@ cog.outl("```")
## Specify what edit format the LLM should use (default depends on model)
#AIDER_EDIT_FORMAT=
## Use architect edit format for the main chat
#AIDER_ARCHITECT=
## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#AIDER_WEAK_MODEL=
## Specify the model to use for editor tasks (default depends on --model)
#AIDER_EDITOR_MODEL=
## Specify the edit format for the editor model (default: depends on editor model)
#AIDER_EDITOR_EDIT_FORMAT=
## Only work with models that have meta-data available (default: True)
#AIDER_SHOW_MODEL_WARNINGS=true
## Max number of tokens to use for repo map, use 0 to disable (default: 1024)
#AIDER_MAP_TOKENS=
## Maximum number of tokens to use for chat history. If not specified, uses the model's max_chat_history_tokens.
## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#AIDER_MAX_CHAT_HISTORY_TOKENS=
## Specify the .env file to load (default: .env in git root)
#AIDER_ENV_FILE=.env
#################
# Cache Settings:
## Enable caching of prompts (default: False)
#AIDER_CACHE_PROMPTS=false
## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#AIDER_CACHE_KEEPALIVE_PINGS=false
###################
# Repomap Settings:
## Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
#AIDER_MAP_TOKENS=
## Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
#AIDER_MAP_REFRESH=auto
## Multiplier for map tokens when no files are specified (default: 2)
#AIDER_MAP_MULTIPLIER_NO_FILES=true
################
# History Files:
@ -180,12 +213,27 @@ cog.outl("```")
## Set the color for tool output (default: None)
#AIDER_TOOL_OUTPUT_COLOR=
## Set the color for tool error messages (default: red)
## Set the color for tool error messages (default: #FF2222)
#AIDER_TOOL_ERROR_COLOR=#FF2222
## Set the color for tool warning messages (default: #FFA500)
#AIDER_TOOL_WARNING_COLOR=#FFA500
## Set the color for assistant output (default: #0088ff)
#AIDER_ASSISTANT_OUTPUT_COLOR=#0088ff
## Set the color for the completion menu (default: terminal's default text color)
#AIDER_COMPLETION_MENU_COLOR=
## Set the background color for the completion menu (default: terminal's default background color)
#AIDER_COMPLETION_MENU_BG_COLOR=
## Set the color for the current item in the completion menu (default: terminal's default background color)
#AIDER_COMPLETION_MENU_CURRENT_COLOR=
## Set the background color for the current item in the completion menu (default: terminal's default text color)
#AIDER_COMPLETION_MENU_CURRENT_BG_COLOR=
## Set the markdown code theme (default: default, other options include monokai, solarized-dark, solarized-light)
#AIDER_CODE_THEME=default
@ -234,6 +282,9 @@ cog.outl("```")
## Perform a dry run without modifying files (default: False)
#AIDER_DRY_RUN=false
## Skip the sanity check for the git repository (default: False)
#AIDER_SKIP_SANITY_CHECK_REPO=false
########################
# Fixing and committing:
@ -279,8 +330,8 @@ cog.outl("```")
## Use VI editing mode in the terminal (default: False)
#AIDER_VIM=false
## Specify the language for voice using ISO 639-1 code (default: auto)
#AIDER_VOICE_LANGUAGE=en
## Specify the language to use in the chat (default: None, uses system settings)
#AIDER_CHAT_LANGUAGE=
## Check for updates and return status in the exit code
#AIDER_JUST_CHECK_UPDATE=false
@ -288,11 +339,17 @@ cog.outl("```")
## Check for new aider versions on launch
#AIDER_CHECK_UPDATE=true
## Install the latest version from the main branch
#AIDER_INSTALL_MAIN_BRANCH=false
## Upgrade aider to the latest version from PyPI
#AIDER_UPGRADE=false
## Apply the changes from the given file instead of running the chat (debug)
#AIDER_APPLY=
## Always say yes to every confirmation
#AIDER_YES=
#AIDER_YES_ALWAYS=
## Enable verbose output
#AIDER_VERBOSE=false
@ -312,11 +369,29 @@ cog.outl("```")
## Specify a file containing the message to send the LLM, process reply, then exit (disables chat mode)
#AIDER_MESSAGE_FILE=
## Load and execute /commands from a file on launch
#AIDER_LOAD=
## Specify the encoding for input and output (default: utf-8)
#AIDER_ENCODING=utf-8
## Run aider in your browser
#AIDER_GUI=false
## Enable/disable suggesting shell commands (default: True)
#AIDER_SUGGEST_SHELL_COMMANDS=true
## Enable/disable fancy input with history and completion (default: True)
#AIDER_FANCY_INPUT=true
#################
# Voice Settings:
## Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
#AIDER_VOICE_FORMAT=wav
## Specify the language for voice using ISO 639-1 code (default: auto)
#AIDER_VOICE_LANGUAGE=en
```
<!--[[[end]]]-->

197
aider/website/docs/config/options.md
View file

@ -27,21 +27,30 @@ cog.out(get_md_help())
```
usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
[--opus] [--sonnet] [--4] [--4o] [--mini] [--4-turbo]
[--35turbo] [--deepseek] [--models] [--openai-api-base]
[--openai-api-type] [--openai-api-version]
[--openai-api-deployment-id] [--openai-organization-id]
[--model-settings-file] [--model-metadata-file]
[--35turbo] [--deepseek] [--o1-mini] [--o1-preview]
[--list-models] [--openai-api-base] [--openai-api-type]
[--openai-api-version] [--openai-api-deployment-id]
[--openai-organization-id] [--model-settings-file]
[--model-metadata-file]
[--verify-ssl | --no-verify-ssl] [--edit-format]
[--weak-model]
[--architect] [--weak-model] [--editor-model]
[--editor-edit-format]
[--show-model-warnings | --no-show-model-warnings]
[--map-tokens] [--max-chat-history-tokens] [--env-file]
[--max-chat-history-tokens] [--env-file]
[--cache-prompts | --no-cache-prompts]
[--cache-keepalive-pings] [--map-tokens]
[--map-refresh] [--map-multiplier-no-files]
[--input-history-file] [--chat-history-file]
[--restore-chat-history | --no-restore-chat-history]
[--llm-history-file] [--dark-mode] [--light-mode]
[--pretty | --no-pretty] [--stream | --no-stream]
[--user-input-color] [--tool-output-color]
[--tool-error-color] [--assistant-output-color]
[--code-theme] [--show-diffs] [--git | --no-git]
[--tool-error-color] [--tool-warning-color]
[--assistant-output-color] [--completion-menu-color]
[--completion-menu-bg-color]
[--completion-menu-current-color]
[--completion-menu-current-bg-color] [--code-theme]
[--show-diffs] [--git | --no-git]
[--gitignore | --no-gitignore] [--aiderignore]
[--subtree-only] [--auto-commits | --no-auto-commits]
[--dirty-commits | --no-dirty-commits]
@ -50,14 +59,20 @@ usage: aider [-h] [--openai-api-key] [--anthropic-api-key] [--model]
[--attribute-commit-message-author | --no-attribute-commit-message-author]
[--attribute-commit-message-committer | --no-attribute-commit-message-committer]
[--commit] [--commit-prompt] [--dry-run | --no-dry-run]
[--lint] [--lint-cmd] [--auto-lint | --no-auto-lint]
[--test-cmd] [--auto-test | --no-auto-test] [--test]
[--skip-sanity-check-repo] [--lint] [--lint-cmd]
[--auto-lint | --no-auto-lint] [--test-cmd]
[--auto-test | --no-auto-test] [--test]
[--analytics | --no-analytics] [--analytics-log]
[--analytics-disable] [--file] [--read] [--vim]
[--voice-language] [--version] [--just-check-update]
[--check-update | --no-check-update] [--apply] [--yes]
[-v] [--show-repo-map] [--show-prompts] [--exit]
[--message] [--message-file] [--encoding] [-c] [--gui]
[--chat-language] [--version] [--just-check-update]
[--check-update | --no-check-update]
[--install-main-branch] [--upgrade] [--apply]
[--yes-always] [-v] [--show-repo-map] [--show-prompts]
[--exit] [--message] [--message-file] [--load]
[--encoding] [-c] [--gui]
[--suggest-shell-commands | --no-suggest-shell-commands]
[--fancy-input | --no-fancy-input] [--voice-format]
[--voice-language]
```
@ -88,7 +103,7 @@ Use claude-3-opus-20240229 model for the main chat
Environment variable: `AIDER_OPUS`
### `--sonnet`
Use claude-3-5-sonnet-20240620 model for the main chat
Use claude-3-5-sonnet-20241022 model for the main chat
Environment variable: `AIDER_SONNET`
### `--4`
@ -99,7 +114,7 @@ Aliases:
- `-4`
### `--4o`
Use gpt-4o model for the main chat
Use gpt-4o-2024-08-06 model for the main chat
Environment variable: `AIDER_4O`
### `--mini`
@ -123,11 +138,22 @@ Aliases:
Use deepseek/deepseek-coder model for the main chat
Environment variable: `AIDER_DEEPSEEK`
### `--o1-mini`
Use o1-mini model for the main chat
Environment variable: `AIDER_O1_MINI`
### `--o1-preview`
Use o1-preview model for the main chat
Environment variable: `AIDER_O1_PREVIEW`
## Model Settings:
### `--models MODEL`
### `--list-models MODEL`
List known models which match the (partial) MODEL name
Environment variable: `AIDER_MODELS`
Environment variable: `AIDER_LIST_MODELS`
Aliases:
- `--list-models MODEL`
- `--models MODEL`
### `--openai-api-base OPENAI_API_BASE`
Specify the api base url
@ -174,10 +200,22 @@ Aliases:
- `--edit-format EDIT_FORMAT`
- `--chat-mode EDIT_FORMAT`
### `--architect`
Use architect edit format for the main chat
Environment variable: `AIDER_ARCHITECT`
### `--weak-model WEAK_MODEL`
Specify the model to use for commit messages and chat history summarization (default depends on --model)
Environment variable: `AIDER_WEAK_MODEL`
### `--editor-model EDITOR_MODEL`
Specify the model to use for editor tasks (default depends on --model)
Environment variable: `AIDER_EDITOR_MODEL`
### `--editor-edit-format EDITOR_EDIT_FORMAT`
Specify the edit format for the editor model (default: depends on editor model)
Environment variable: `AIDER_EDITOR_EDIT_FORMAT`
### `--show-model-warnings`
Only work with models that have meta-data available (default: True)
Default: True
@ -186,12 +224,8 @@ Aliases:
- `--show-model-warnings`
- `--no-show-model-warnings`
### `--map-tokens VALUE`
Max number of tokens to use for repo map, use 0 to disable (default: 1024)
Environment variable: `AIDER_MAP_TOKENS`
### `--max-chat-history-tokens VALUE`
Maximum number of tokens to use for chat history. If not specified, uses the model's max_chat_history_tokens.
Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
Environment variable: `AIDER_MAX_CHAT_HISTORY_TOKENS`
### `--env-file ENV_FILE`
@ -199,6 +233,37 @@ Specify the .env file to load (default: .env in git root)
Default: .env
Environment variable: `AIDER_ENV_FILE`
## Cache Settings:
### `--cache-prompts`
Enable caching of prompts (default: False)
Default: False
Environment variable: `AIDER_CACHE_PROMPTS`
Aliases:
- `--cache-prompts`
- `--no-cache-prompts`
### `--cache-keepalive-pings VALUE`
Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
Default: 0
Environment variable: `AIDER_CACHE_KEEPALIVE_PINGS`
## Repomap Settings:
### `--map-tokens VALUE`
Suggested number of tokens to use for repo map, use 0 to disable (default: 1024)
Environment variable: `AIDER_MAP_TOKENS`
### `--map-refresh VALUE`
Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
Default: auto
Environment variable: `AIDER_MAP_REFRESH`
### `--map-multiplier-no-files VALUE`
Multiplier for map tokens when no files are specified (default: 2)
Default: 2
Environment variable: `AIDER_MAP_MULTIPLIER_NO_FILES`
## History Files:
### `--input-history-file INPUT_HISTORY_FILE`
@ -261,15 +326,36 @@ Set the color for tool output (default: None)
Environment variable: `AIDER_TOOL_OUTPUT_COLOR`
### `--tool-error-color VALUE`
Set the color for tool error messages (default: red)
Set the color for tool error messages (default: #FF2222)
Default: #FF2222
Environment variable: `AIDER_TOOL_ERROR_COLOR`
### `--tool-warning-color VALUE`
Set the color for tool warning messages (default: #FFA500)
Default: #FFA500
Environment variable: `AIDER_TOOL_WARNING_COLOR`
### `--assistant-output-color VALUE`
Set the color for assistant output (default: #0088ff)
Default: #0088ff
Environment variable: `AIDER_ASSISTANT_OUTPUT_COLOR`
### `--completion-menu-color COLOR`
Set the color for the completion menu (default: terminal's default text color)
Environment variable: `AIDER_COMPLETION_MENU_COLOR`
### `--completion-menu-bg-color COLOR`
Set the background color for the completion menu (default: terminal's default background color)
Environment variable: `AIDER_COMPLETION_MENU_BG_COLOR`
### `--completion-menu-current-color COLOR`
Set the color for the current item in the completion menu (default: terminal's default background color)
Environment variable: `AIDER_COMPLETION_MENU_CURRENT_COLOR`
### `--completion-menu-current-bg-color COLOR`
Set the background color for the current item in the completion menu (default: terminal's default text color)
Environment variable: `AIDER_COMPLETION_MENU_CURRENT_BG_COLOR`
### `--code-theme VALUE`
Set the markdown code theme (default: default, other options include monokai, solarized-dark, solarized-light)
Default: default
@ -373,6 +459,11 @@ Aliases:
- `--dry-run`
- `--no-dry-run`
### `--skip-sanity-check-repo`
Skip the sanity check for the git repository (default: False)
Default: False
Environment variable: `AIDER_SKIP_SANITY_CHECK_REPO`
## Fixing and committing:
### `--lint`
@ -426,7 +517,7 @@ Specify a file to log analytics events
Environment variable: `AIDER_ANALYTICS_LOG`
### `--analytics-disable`
Disable analytics forever
Permanently disable analytics
Default: False
Environment variable: `AIDER_ANALYTICS_DISABLE`
@ -445,10 +536,9 @@ Use VI editing mode in the terminal (default: False)
Default: False
Environment variable: `AIDER_VIM`
### `--voice-language VOICE_LANGUAGE`
Specify the language for voice using ISO 639-1 code (default: auto)
Default: en
Environment variable: `AIDER_VOICE_LANGUAGE`
### `--chat-language CHAT_LANGUAGE`
Specify the language to use in the chat (default: None, uses system settings)
Environment variable: `AIDER_CHAT_LANGUAGE`
### `--version`
Show the version number and exit
@ -466,13 +556,26 @@ Aliases:
- `--check-update`
- `--no-check-update`
### `--install-main-branch`
Install the latest version from the main branch
Default: False
Environment variable: `AIDER_INSTALL_MAIN_BRANCH`
### `--upgrade`
Upgrade aider to the latest version from PyPI
Default: False
Environment variable: `AIDER_UPGRADE`
Aliases:
- `--upgrade`
- `--update`
### `--apply FILE`
Apply the changes from the given file instead of running the chat (debug)
Environment variable: `AIDER_APPLY`
### `--yes`
### `--yes-always`
Always say yes to every confirmation
Environment variable: `AIDER_YES`
Environment variable: `AIDER_YES_ALWAYS`
### `--verbose`
Enable verbose output
@ -512,6 +615,10 @@ Aliases:
- `--message-file MESSAGE_FILE`
- `-f MESSAGE_FILE`
### `--load LOAD_FILE`
Load and execute /commands from a file on launch
Environment variable: `AIDER_LOAD`
### `--encoding VALUE`
Specify the encoding for input and output (default: utf-8)
Default: utf-8
@ -530,4 +637,32 @@ Environment variable: `AIDER_GUI`
Aliases:
- `--gui`
- `--browser`
### `--suggest-shell-commands`
Enable/disable suggesting shell commands (default: True)
Default: True
Environment variable: `AIDER_SUGGEST_SHELL_COMMANDS`
Aliases:
- `--suggest-shell-commands`
- `--no-suggest-shell-commands`
### `--fancy-input`
Enable/disable fancy input with history and completion (default: True)
Default: True
Environment variable: `AIDER_FANCY_INPUT`
Aliases:
- `--fancy-input`
- `--no-fancy-input`
## Voice Settings:
### `--voice-format VOICE_FORMAT`
Audio format for voice recording (default: wav). webm and mp3 require ffmpeg
Default: wav
Environment variable: `AIDER_VOICE_FORMAT`
### `--voice-language VOICE_LANGUAGE`
Specify the language for voice using ISO 639-1 code (default: auto)
Default: en
Environment variable: `AIDER_VOICE_LANGUAGE`
<!--[[[end]]]-->

7
aider/website/docs/ctags.md
View file

@ -12,6 +12,7 @@ nav_exclude: true
![robot flowchat](/assets/robot-flowchart.png)
## Updated
Aider no longer uses ctags to build a repo map.
@ -111,9 +112,9 @@ like functions and methods also include their signatures.
Here's a
sample of the map of the aider repo, just showing the maps of
[main.py](https://github.com/paul-gauthier/aider/blob/main/aider/main.py)
[main.py](https://github.com/Aider-AI/aider/blob/main/aider/main.py)
and
[io.py](https://github.com/paul-gauthier/aider/blob/main/aider/io.py)
[io.py](https://github.com/Aider-AI/aider/blob/main/aider/io.py)
:
```
@ -228,7 +229,7 @@ Some possible approaches to reducing the amount of map data are:
- Distill the global map, to prioritize important symbols and discard "internal" or otherwise less globally relevant identifiers. Possibly enlist `gpt-3.5-turbo` to perform this distillation in a flexible and language agnostic way.
- Provide a mechanism for GPT to start with a distilled subset of the global map, and let it ask to see more detail about subtrees or keywords that it feels are relevant to the current coding task.
- Attempt to analyize the natural language coding task given by the user and predict which subset of the repo map is relevant. Possibly by analysis of prior coding chats within the specific repo. Work on certain files or types of features may require certain somewhat predictable context from elsewhere in the repo. Vector and keyword search against the chat history, repo map or codebase may help here.
- Attempt to analyze the natural language coding task given by the user and predict which subset of the repo map is relevant. Possibly by analysis of prior coding chats within the specific repo. Work on certain files or types of features may require certain somewhat predictable context from elsewhere in the repo. Vector and keyword search against the chat history, repo map or codebase may help here.
One key goal is to prefer solutions which are language agnostic or
which can be easily deployed against most popular code languages.

112
aider/website/docs/faq.md
View file

@ -37,7 +37,7 @@ If you still wish to add lots of files to the chat, you can:
- Use a wildcard when you launch aider: `aider src/*.py`
- Use a wildcard with the in-chat `/add` command: `/add src/*.py`
- Give the `/add` command a directory name and it will recurisvely add every file under that dir: `/add src`
- Give the `/add` command a directory name and it will recursively add every file under that dir: `/add src`
## Can I use aider in a large (mono) repo?
@ -45,7 +45,14 @@ Aider will work in any size repo, but is not optimized for quick
performance and response time in very large repos.
There are some things you can do to improve performance.
Change into a sub directory of your repo that contains the
Be sure to check the
[general usage tips](/docs/usage/tips.html)
before considering this large-repo specific advice.
To get the best results from aider you want to
be thoughtful about how you add files to the chat,
regardless of your repo size.
You can change into a sub directory of your repo that contains the
code you want to work on and use the `--subtree-only` switch.
This will tell aider to ignore the repo outside of the
directory you start in.
@ -59,23 +66,85 @@ to use for ignore patterns.
You might have a few of these handy for when you want to work on
frontend, backend, etc portions of your repo.
## Can I use aider with multiple git repos at once?
Currently aider can only work with one repo at a time.
There are some things you can try if you need to work with
multiple interrelated repos:
- You can run aider in repo-A where you need to make a change
and use `/read` to add some files read-only from another repo-B.
This can let aider see key functions or docs from the other repo.
- You can run `aider --show-repo-map > map.md` within each
repo to create repo maps.
You could then run aider in repo-A and
use `/read ../path/to/repo-B/map.md` to share
a high level map of the other repo.
- You can use aider to write documentation about a repo.
Inside each repo, you could run `aider docs.md`
and work with aider to write some markdown docs.
Then while using aider to edit repo-A
you can `/read ../path/to/repo-B/docs.md` to
read in those docs from the other repo.
- In repo A, ask aider to write a small script that demonstrates
the functionality you want to use in repo B.
Then when you're using aider in repo B, you can
`/read` in that script.
## How do I turn on the repository map?
Depending on the LLM you are using, aider may launch with the repo map disabled by default:
```
Repo-map: disabled
```
This is because weaker models get easily overwhelmed and confused by the content of the
repo map. They sometimes mistakenly try to edit the code in the repo map.
The repo map is usually disabled for a good reason.
If you would like to force it on, you can run aider with `--map-tokens 1024`.
## How do I include the git history in the context?
When starting a fresh aider session, you can include recent git history in the chat context. This can be useful for providing the LLM with information about recent changes. To do this:
1. Use the `/run` command with `git diff` to show recent changes:
```
/run git diff HEAD~1
```
This will include the diff of the last commit in the chat history.
2. To include diffs from multiple commits, increase the number after the tilde:
```
/run git diff HEAD~3
```
This will show changes from the last three commits.
Remember, the chat history already includes recent changes made during the current session, so this tip is most useful when starting a new aider session and you want to provide context about recent work.
{: .tip }
The `/git` command will not work for this purpose, as its output is not included in the chat.
## How can I run aider locally from source code?
To run the project locally, follow these steps:
```
# Clone the repository:
git clone git@github.com:paul-gauthier/aider.git
# Clone the repository
git clone git@github.com:Aider-AI/aider.git
# Navigate to the project directory:
# Navigate to the project directory
cd aider
# It's recommended to make a virtual environment
# Install the dependencies listed in the `requirements.txt` file:
# Install aider in editable/development mode,
# so it runs from the latest copy of these source files
python -m pip install -e .
# Run the local version of Aider:
# Run the local version of aider
python -m aider
```
@ -122,3 +191,32 @@ You can also refer to the
[instructions for installing a development version of aider](https://aider.chat/docs/install/optional.html#install-the-development-version-of-aider).
## Can I share my aider chat transcript?
Yes, you can now share aider chat logs in a pretty way.
1. Copy the markdown logs you want to share from `.aider.chat.history.md` and make a github gist. Or publish the raw markdown logs on the web any way you'd like.
```
https://gist.github.com/Aider-AI/2087ab8b64034a078c0a209440ac8be0
```
2. Take the gist URL and append it to:
```
https://aider.chat/share/?mdurl=
```
This will give you a URL like this, which shows the chat history like you'd see in a terminal:
```
https://aider.chat/share/?mdurl=https://gist.github.com/Aider-AI/2087ab8b64034a078c0a209440ac8be0
```
## What is Aider AI LLC?
Aider AI LLC is the company behind the aider AI coding tool.
Aider is
[open source and available on GitHub](https://github.com/Aider-AI/aider)
under an
[Apache 2.0 license](https://github.com/Aider-AI/aider/blob/main/LICENSE.txt).

18
aider/website/docs/git.md
View file

@ -22,9 +22,16 @@ This keeps your edits separate from aider's edits, and makes sure you never lose
## In-chat commands
Aider also allows you to use in-chat commands to `/diff` or `/undo` the last change.
To do more complex management of your git history, you cat use raw `git` commands,
either by using `/git` within the chat, or with standard git tools outside of aider.
Aider also allows you to use
[in-chat commands](/docs/usage/commands.html)
to perform git operations:
- `/diff` will show all the file changes since the last message you sent.
- `/undo` will undo and discard the last change.
- `/commit` to commit all dirty changes with a sensible commit message.
- `/git` will let you run raw git commands to do more complex management of your git history.
You can also manage your git history outside of aider with your preferred git tools.
## Disabling git integration
@ -36,15 +43,18 @@ While it is not recommended, you can disable aider's use of git in a few ways:
## Commit messages
Aider sends the `--weak-model` a copy of the diffs and the chat history
and asks it to produce a commit message.
By default, aider creates commit messages which follow
[Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/).
You can customize the
[commit prompt](https://github.com/paul-gauthier/aider/blob/main/aider/prompts.py#L5)
[commit prompt](https://github.com/Aider-AI/aider/blob/main/aider/prompts.py#L5)
with the `--commit-prompt` option.
You can place that on the command line, or
[configure it via a config file or environment variables](https://aider.chat/docs/config.html).
## Commit attribution
Aider marks commits that it either authored or committed.

4
aider/website/docs/install/install.md
View file

@ -31,7 +31,7 @@ To work with Anthropic's models like Claude 3.5 Sonnet you need a paid
```
# Install aider
python -m pip install aider-chat
python -m pip install -U --upgrade-strategy only-if-needed aider-chat
# To work with GPT-4o:
$ aider --4o --openai-api-key sk-xxx...
@ -44,7 +44,7 @@ $ aider --sonnet --anthropic-api-key sk-xxx...
```
# Install aider
python -m pip install aider-chat
python -m pip install -U --upgrade-strategy only-if-needed aider-chat
# To work with GPT-4o:
$ aider --4o --openai-api-key sk-xxx...

8
aider/website/docs/install/optional.md
View file

@ -74,15 +74,11 @@ joshuavial also confirmed that aider works inside a VS Code terminal window.
Aider detects if it is running inside VSCode and turns off pretty/color output,
since the VSCode terminal doesn't seem to support it well.
[MattFlower](https://github.com/MattFlower) provided a VSCode plugin for aider:
[https://marketplace.visualstudio.com/items?itemName=MattFlower.aider](https://marketplace.visualstudio.com/items?itemName=MattFlower.aider)
### Other editors
If you are interested in creating an aider plugin for your favorite editor,
please let me know by opening a
[GitHub issue](https://github.com/paul-gauthier/aider/issues).
[GitHub issue](https://github.com/Aider-AI/aider/issues).
## Install the development version of aider
@ -91,7 +87,7 @@ If you want the very latest development version of aider
you can install directly from GitHub:
```
python -m pip install --upgrade git+https://github.com/paul-gauthier/aider.git
python -m pip install --upgrade git+https://github.com/Aider-AI/aider.git
```
If you've git cloned the aider repository already, you can install "live" from your local copy. This is mostly useful if you are developing aider and want your current modifications to take effect immediately.

6
aider/website/docs/install/pipx.md
View file

@ -25,3 +25,9 @@ Install [pipx](https://pipx.pypa.io/stable/) then just do:
```
pipx install aider-chat
```
## pipx on replit
{% include replit-pipx.md %}

53
aider/website/docs/languages.md
View file

@ -21,6 +21,33 @@ Aider can currently produce repository maps for many popular
mainstream languages, listed below.
## How to add support for another language
Aider should work quite well for other languages, even those
without repo map or linter support.
You should really try coding with aider before
assuming it needs better support for your language.
That said, if aider already has support for linting your language,
then it should be possible to add repo map support.
To build a repo map, aider needs the `tags.scm` file
from the given language's tree-sitter grammar.
If you can find and share that file in a
[GitHub issue](https://github.com/Aider-AI/aider/issues),
then it may be possible to add repo map support.
If aider doesn't support linting, it will be complicated to
add linting and repo map support.
That is because aider relies on
[py-tree-sitter-languages](https://github.com/grantjenks/py-tree-sitter-languages)
to provide pre-packaged versions of tree-sitter
parsers for many languages.
Aider needs to be easy for users to install in many environments,
and it is probably too complex to add dependencies on
additional individual tree-sitter parsers.
<!--[[[cog
from aider.repomap import get_supported_languages_md
cog.out(get_supported_languages_md())
@ -81,29 +108,3 @@ cog.out(get_supported_languages_md())
<!--[[[end]]]-->
## How to add support for another language
Aider should work quite well for other languages, even those
without repo map or linter support.
You should really try coding with aider before
assuming it needs better support for your language.
That said, if aider already has support for linting your language,
then it should be possible to add repo map support.
To build a repo map, aider needs the `tags.scm` file
from the given language's tree-sitter grammar.
If you can find and share that file in a
[GitHub issue](https://github.com/paul-gauthier/aider/issues),
then it may be possible to add repo map support.
If aider doesn't support linting, it will be complicated to
add linting and repo map support.
That is because aider relies on
[py-tree-sitter-languages](https://github.com/grantjenks/py-tree-sitter-languages)
to provide pre-packaged versions of tree-sitter
parsers for many languages.
Aider needs to be easy for users to install in many environments,
and it is probably too complex to add dependencies on
additional individual tree-sitter parsers.

8
aider/website/docs/leaderboards/index.md
View file

@ -150,7 +150,7 @@ The model also has to successfully apply all its changes to the source file with
## Code refactoring leaderboard
[Aider's refactoring benchmark](https://github.com/paul-gauthier/refactor-benchmark) asks the LLM to refactor 89 large methods from large python classes. This is a more challenging benchmark, which tests the model's ability to output long chunks of code without skipping sections or making mistakes. It was developed to provoke and measure [GPT-4 Turbo's "lazy coding" habit](/2023/12/21/unified-diffs.html).
[Aider's refactoring benchmark](https://github.com/Aider-AI/refactor-benchmark) asks the LLM to refactor 89 large methods from large python classes. This is a more challenging benchmark, which tests the model's ability to output long chunks of code without skipping sections or making mistakes. It was developed to provoke and measure [GPT-4 Turbo's "lazy coding" habit](/2023/12/21/unified-diffs.html).
The refactoring benchmark requires a large context window to
work with large source files.
@ -291,10 +291,10 @@ since it is the easiest format for an LLM to use.
Contributions of benchmark results are welcome!
See the
[benchmark README](https://github.com/paul-gauthier/aider/blob/main/benchmark/README.md)
[benchmark README](https://github.com/Aider-AI/aider/blob/main/benchmark/README.md)
for information on running aider's code editing benchmarks.
Submit results by opening a PR with edits to the
[benchmark results data files](https://github.com/paul-gauthier/aider/blob/main/website/_data/).
[benchmark results data files](https://github.com/Aider-AI/aider/blob/main/aider/website/_data/).
<p class="post-date">
@ -321,6 +321,6 @@ mod_dates = [get_last_modified_date(file) for file in files]
latest_mod_date = max(mod_dates)
cog.out(f"{latest_mod_date.strftime('%B %d, %Y.')}")
]]]-->
August 14, 2024.
October 22, 2024.
<!--[[[end]]]-->
</p>

111
aider/website/docs/legal/contributor-agreement.md Normal file
View file

@ -0,0 +1,111 @@
Individual Contributor License Agreement
Thank you for your interest in Aider AI LLC ("Aider AI").
To clarify the intellectual property license
granted with Contributions from any person or entity, Aider AI
must have on file a signed Contributor License Agreement ("CLA")
from each Contributor, indicating agreement with the license
terms below. This agreement is for your protection as a Contributor
as well as the protection of Aider AI and its users. It does not
change your rights to use your own Contributions for any other purpose.
Please complete and sign this Agreement. Read this document carefully
before signing and keep a copy for your records.
You accept and agree to the following terms and conditions for Your
Contributions (present and future) that you submit to Aider AI.
Except for the license granted herein to Aider AI and recipients
of software distributed by Aider AI, You reserve all right, title,
and interest in and to Your Contributions.
1. Definitions.
"You" (or "Your") shall mean the copyright owner or legal entity
authorized by the copyright owner that is making this Agreement
with Aider AI. For legal entities, the entity making a
Contribution and all other entities that control, are controlled
by, or are under common control with that entity are considered to
be a single Contributor. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"Contribution" shall mean any original work of authorship,
including any modifications or additions to an existing work, that
is intentionally submitted by You to Aider AI for inclusion
in, or documentation of, any of the products owned or managed by
Aider AI (the "Work"). For the purposes of this definition,
"submitted" means any form of electronic, verbal, or written
communication sent to Aider AI or its representatives,
including but not limited to communication on electronic mailing
lists, source code control systems, and issue tracking systems that
are managed by, or on behalf of, Aider AI for the purpose of
discussing and improving the Work, but excluding communication that
is conspicuously marked or otherwise designated in writing by You
as "Not a Contribution."
2. Grant of Copyright License. Subject to the terms and conditions of
this Agreement, You hereby grant to Aider AI and to
recipients of software distributed by Aider AI a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare derivative works of,
publicly display, publicly perform, sublicense, and distribute Your
Contributions and such derivative works.
3. Grant of Patent License. Subject to the terms and conditions of
this Agreement, You hereby grant to Aider AI and to
recipients of software distributed by Aider AI a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have
made, use, offer to sell, sell, import, and otherwise transfer the
Work, where such license applies only to those patent claims
licensable by You that are necessarily infringed by Your
Contribution(s) alone or by combination of Your Contribution(s)
with the Work to which such Contribution(s) was submitted. If any
entity institutes patent litigation against You or any other entity
(including a cross-claim or counterclaim in a lawsuit) alleging
that your Contribution, or the Work to which you have contributed,
constitutes direct or contributory patent infringement, then any
patent licenses granted to that entity under this Agreement for
that Contribution or Work shall terminate as of the date such
litigation is filed.
4. You represent that you are legally entitled to grant the above
license. If your employer(s) has rights to intellectual property
that you create that includes your Contributions, you represent
that you have received permission to make Contributions on behalf
of that employer, that your employer has waived such rights for
your Contributions to Aider AI, or that your employer has
executed a separate Corporate CLA with Aider AI.
5. You represent that each of Your Contributions is Your original
creation (see section 7 for submissions on behalf of others). You
represent that Your Contribution submissions include complete
details of any third-party license or other restriction (including,
but not limited to, related patents and trademarks) of which you
are personally aware and which are associated with any part of Your
Contributions.
6. You are not expected to provide support for Your Contributions,
except to the extent You desire to provide support. You may provide
support for free, for a fee, or not at all. Unless required by
applicable law or agreed to in writing, You provide Your
Contributions on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
OF ANY KIND, either express or implied, including, without
limitation, any warranties or conditions of TITLE, NON-
INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE.
7. Should You wish to submit work that is not Your original creation,
You may submit it to Aider AI separately from any
Contribution, identifying the complete details of its source and of
any license or other restriction (including, but not limited to,
related patents, trademarks, and license agreements) of which you
are personally aware, and conspicuously marking the work as
"Submitted on behalf of a third-party: [named here]".
8. You agree to notify Aider AI of any facts or circumstances of
which you become aware that would make these representations
inaccurate in any respect.

4
aider/website/docs/llms/anthropic.md
View file

@ -14,7 +14,7 @@ Aider has some built in shortcuts for the most popular Anthropic models and
has been tested and benchmarked to work well with them:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export ANTHROPIC_API_KEY=<key> # Mac/Linux
setx ANTHROPIC_API_KEY <key> # Windows, restart shell after setx
@ -26,7 +26,7 @@ aider
aider --opus
# List models available from Anthropic
aider --models anthropic/
aider --list-models anthropic/
```
{: .tip }

4
aider/website/docs/llms/azure.md
View file

@ -8,7 +8,7 @@ nav_order: 500
Aider can connect to the OpenAI models on Azure.
```
python -m pip install aider-chat
python -m pip install -U aider-chat
# Mac/Linux:
export AZURE_API_KEY=<key>
@ -24,7 +24,7 @@ setx AZURE_API_BASE https://myendpt.openai.azure.com
aider --model azure/<your_deployment_name>
# List models available from Azure
aider --models azure/
aider --list-models azure/
```
Note that aider will also use environment variables

75
aider/website/docs/llms/bedrock.md Normal file
View file

@ -0,0 +1,75 @@
---
parent: Connecting to LLMs
nav_order: 560
---
# Amazon Bedrock
Aider can connect to models provided by Amazon Bedrock.
You will need to have an AWS account with access to the Bedrock service.
To configure Aider to use the Amazon Bedrock API, you need to set up your AWS credentials.
This can be done using the AWS CLI or by setting environment variables.
## AWS CLI Configuration
If you haven't already, install the [AWS CLI](https://aws.amazon.com/cli/) and configure it with your credentials:
```bash
aws configure
```
This will prompt you to enter your AWS Access Key ID, Secret Access Key, and default region.
## Environment Variables
Alternatively, you can set the following environment variables:
```bash
export AWS_REGION=your_preferred_region
# For user authentication
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
# For profile authentication
export AWS_PROFILE=your-profile
```
You can add these to your
[.env file](/docs/config/dotenv.html).
## Bedrock with `pipx` installation
The AWS Bedrock provider requires the `boto3` package in order to function correctly. To use aider installed via `pipx` with AWS Bedrock, you must add the `boto3` dependency to aider's virtual environment by running
```
pipx inject aider boto3
```
## Running Aider with Bedrock
Once your AWS credentials are set up, you can run Aider with the `--model` command line switch, specifying the Bedrock model you want to use:
```bash
aider --model bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
```
## Available Models
To see some models available via Bedrock, run:
```
aider --list-models bedrock/
```
Make sure you have access to these models in your AWS account before attempting to use them with Aider.
# More info
For more information on Amazon Bedrock and its models, refer to the [official AWS documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).
Also, see the
[litellm docs on Bedrock](https://litellm.vercel.app/docs/providers/bedrock).

6
aider/website/docs/llms/cohere.md
View file

@ -13,13 +13,13 @@ You'll need a [Cohere API key](https://dashboard.cohere.com/welcome/login).
To use **Command-R+**:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export COHERE_API_KEY=<key> # Mac/Linux
setx COHERE_API_KEY <key> # Windows, restart shell after setx
aider --model command-r-plus
aider --model command-r-plus-08-2024
# List models available from Cohere
aider --models cohere_chat/
aider --list-models cohere_chat/
```

2
aider/website/docs/llms/deepseek.md
View file

@ -9,7 +9,7 @@ Aider can connect to the DeepSeek.com API.
The DeepSeek Coder V2 model has a top score on aider's code editing benchmark.
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export DEEPSEEK_API_KEY=<key> # Mac/Linux
setx DEEPSEEK_API_KEY <key> # Windows, restart shell after setx

4
aider/website/docs/llms/gemini.md
View file

@ -12,7 +12,7 @@ with code editing capability that's comparable to GPT-3.5.
You'll need a [Gemini API key](https://aistudio.google.com/app/u/2/apikey).
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export GEMINI_API_KEY=<key> # Mac/Linux
setx GEMINI_API_KEY <key> # Windows, restart shell after setx
@ -20,6 +20,6 @@ setx GEMINI_API_KEY <key> # Windows, restart shell after setx
aider --model gemini/gemini-1.5-pro-latest
# List models available from Gemini
aider --models gemini/
aider --list-models gemini/
```

4
aider/website/docs/llms/groq.md
View file

@ -13,7 +13,7 @@ You'll need a [Groq API key](https://console.groq.com/keys).
To use **Llama3 70B**:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export GROQ_API_KEY=<key> # Mac/Linux
setx GROQ_API_KEY <key> # Windows, restart shell after setx
@ -21,7 +21,7 @@ setx GROQ_API_KEY <key> # Windows, restart shell after setx
aider --model groq/llama3-70b-8192
# List models available from Groq
aider --models groq/
aider --list-models groq/
```

2
aider/website/docs/llms/ollama.md
View file

@ -15,7 +15,7 @@ ollama pull <model>
ollama serve
# In another terminal window...
python -m pip install aider-chat
python -m pip install -U aider-chat
export OLLAMA_API_BASE=http://127.0.0.1:11434 # Mac/Linux
setx OLLAMA_API_BASE http://127.0.0.1:11434 # Windows, restart shell after setx

2
aider/website/docs/llms/openai-compat.md
View file

@ -8,7 +8,7 @@ nav_order: 500
Aider can connect to any LLM which is accessible via an OpenAI compatible API endpoint.
```
python -m pip install aider-chat
python -m pip install -U aider-chat
# Mac/Linux:
export OPENAI_API_BASE=<endpoint>

14
aider/website/docs/llms/openai.md
View file

@ -14,7 +14,7 @@ Aider has some built in shortcuts for the most popular OpenAI models and
has been tested and benchmarked to work well with them:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export OPENAI_API_KEY=<key> # Mac/Linux
setx OPENAI_API_KEY <key> # Windows, restart shell after setx
@ -22,14 +22,20 @@ setx OPENAI_API_KEY <key> # Windows, restart shell after setx
# Aider uses gpt-4o by default (or use --4o)
aider
# GPT-4 Turbo (1106)
aider --4-turbo
# GPT-4o
aider --4o
# GPT-3.5 Turbo
aider --35-turbo
# o1-mini
aider --model o1-mini
# o1-preview
aider --model o1-preview
# List models available from OpenAI
aider --models openai/
aider --list-models openai/
```
You can use `aider --model <model-name>` to use any other OpenAI model.

6
aider/website/docs/llms/openrouter.md
View file

@ -9,7 +9,7 @@ Aider can connect to [models provided by OpenRouter](https://openrouter.ai/model
You'll need an [OpenRouter API key](https://openrouter.ai/keys).
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export OPENROUTER_API_KEY=<key> # Mac/Linux
setx OPENROUTER_API_KEY <key> # Windows, restart shell after setx
@ -18,13 +18,13 @@ setx OPENROUTER_API_KEY <key> # Windows, restart shell after setx
aider --model openrouter/<provider>/<model>
# List models available from OpenRouter
aider --models openrouter/
aider --list-models openrouter/
```
In particular, many aider users access Sonnet via OpenRouter:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export OPENROUTER_API_KEY=<key> # Mac/Linux
setx OPENROUTER_API_KEY <key> # Windows, restart shell after setx

12
aider/website/docs/llms/other.md
View file

@ -9,14 +9,14 @@ Aider uses the [litellm](https://docs.litellm.ai/docs/providers) package
to connect to hundreds of other models.
You can use `aider --model <model-name>` to use any supported model.
To explore the list of supported models you can run `aider --models <model-name>`
To explore the list of supported models you can run `aider --list-models <model-name>`
with a partial model name.
If the supplied name is not an exact match for a known model, aider will
return a list of possible matching models.
For example:
```
$ aider --models turbo
$ aider --list-models turbo
Aider v0.29.3-dev
Models which match "turbo":
@ -63,6 +63,7 @@ cog.out(''.join(lines))
- AZURE_API_KEY
- AZURE_OPENAI_API_KEY
- BASETEN_API_KEY
- CEREBRAS_API_KEY
- CLARIFAI_API_KEY
- CLOUDFLARE_API_KEY
- CODESTRAL_API_KEY
@ -71,22 +72,19 @@ cog.out(''.join(lines))
- DATABRICKS_API_KEY
- DEEPINFRA_API_KEY
- DEEPSEEK_API_KEY
- EMPOWER_API_KEY
- FIREWORKSAI_API_KEY
- FIREWORKS_AI_API_KEY
- FIREWORKS_API_KEY
- FRIENDLIAI_API_KEY
- GEMINI_API_KEY
- GITHUB_API_KEY
- GROQ_API_KEY
- HUGGINGFACE_API_KEY
- MARITALK_API_KEY
- MISTRAL_API_KEY
- MISTRAL_AZURE_API_KEY
- NLP_CLOUD_API_KEY
- NVIDIA_NIM_API_KEY
- OLLAMA_API_KEY
- OPENAI_API_KEY
- OPENAI_LIKE_API_KEY
- OPENROUTER_API_KEY
- OR_API_KEY
- PALM_API_KEY
@ -95,8 +93,6 @@ cog.out(''.join(lines))
- PROVIDER_API_KEY
- REPLICATE_API_KEY
- TOGETHERAI_API_KEY
- TOGETHER_AI_API_KEY
- TOGETHER_API_KEY
- VOLCENGINE_API_KEY
- VOYAGE_API_KEY
- XINFERENCE_API_KEY

106
aider/website/docs/more/edit-formats.md Normal file
View file

@ -0,0 +1,106 @@
---
parent: More info
nav_order: 960
description: Aider uses various "edit formats" to let LLMs edit source files.
---
# Edit formats
Aider uses various "edit formats" to let LLMs edit source files.
Different models work better or worse with different edit formats.
Aider is configured to use the optimal format for most popular, common models.
You can always force use of a specific edit format with
the `--edit-format` switch.
## whole
The "whole" edit format is the simplest possible editing format.
The LLM is instructed to return a full, updated
copy of each source file that needs changes.
While simple, it can be slow and costly because the LLM has to return
the *entire file* even if just a few lines are edited.
The format expects the file path just before the fenced file content:
````
show_greeting.py
```
import sys
def greeting(name):
print(f"Hey {{name}}")
if __name__ == '__main__':
greeting(sys.argv[1])
```
````
## diff
The "diff" edit format asks the LLM to specify file edits as a series of search/replace blocks.
This is an efficient format, because the model only needs to return parts of the file
which have changes.
They are formatted using a syntax similar to the git merge conflict resolution markings,
with the file path right before a fenced block:
````
mathweb/flask/app.py
```
<<<<<<< SEARCH
from flask import Flask
=======
import math
from flask import Flask
>>>>>>> REPLACE
```
````
## diff-fenced
The "diff-fenced" edit format is based on the diff format, but
the file path is placed inside the fence.
It is primarily used with the Gemini family of models,
which often fail to conform to fencing approach specified in the diff format.
````
```
mathweb/flask/app.py
<<<<<<< SEARCH
from flask import Flask
=======
import math
from flask import Flask
>>>>>>> REPLACE
```
````
## udiff
The "udiff" edit format is based on the widely used unified diff format,
but [modified and simplified](/2023/12/21/unified-diffs.html).
This is an efficient format, because the model only needs to return parts of the file
which have changes.
It was mainly used to the GPT-4 Turbo family of models,
to reduce their "lazy coding" tendencies with other edit formats.
````
```diff
--- mathweb/flask/app.py
+++ mathweb/flask/app.py
@@ ... @@
-class MathWeb:
+import sympy
+
+class MathWeb:
```
````
## editor-diff and editor-whole
These are streamlined versions of the diff and whole formats, intended to be used
with `--editor-edit-format` when using
[architect mode](/docs/usage/modes.html).

98
aider/website/docs/more/infinite-output.md Normal file
View file

@ -0,0 +1,98 @@
---
parent: More info
nav_order: 920
description: Aider can handle "infinite output" from models that support prefill.
---
# Infinite output
LLM providers limit how much output a model can generate from a single request.
This is usually called the output token limit.
Aider is able to work around this limit with models that support
"prefilling" the assistant response.
When you use aider with a model that supports prefill, you will see
"infinite output" noted in the announcement lines displayed at launch:
```
Aider v0.58.0
Main model: claude-3-5-sonnet-20240620 with diff edit format, prompt cache, infinite output
```
Models that support prefill can be primed to think they started their response
with a specific piece of text.
You can put words in their mouth, and they will continue generating
text from that point forward.
When aider is collecting code edits from a model and
it hits the output token limit,
aider simply initiates another LLM request with the partial
response prefilled.
This prompts the model to continue where it left off,
generating more of the desired response.
This prefilling of the partially completed response can be repeated,
allowing for very long outputs.
Joining the text across these output limit boundaries
requires some heuristics, but is typically fairly reliable.
Aider supports "infinite output" for models that support "prefill",
such as:
<!--[[[cog
import requests
import json
# Fetch the JSON data
url = "https://raw.githubusercontent.com/BerriAI/litellm/refs/heads/main/model_prices_and_context_window.json"
response = requests.get(url)
data = json.loads(response.text)
# Process the JSON to find models with supports_assistant_prefill=true
prefill_models = [model for model, info in data.items() if info.get('supports_assistant_prefill') == True]
# Generate the list of models
model_list = "\n".join(f"- {model}" for model in sorted(prefill_models))
cog.out(model_list)
]]]-->
- anthropic.claude-3-5-sonnet-20241022-v2:0
- anthropic/claude-3-5-sonnet-20241022
- claude-3-5-sonnet-20240620
- claude-3-5-sonnet-20241022
- claude-3-haiku-20240307
- claude-3-opus-20240229
- claude-3-sonnet-20240229
- codestral/codestral-2405
- codestral/codestral-latest
- deepseek-chat
- deepseek-coder
- eu.anthropic.claude-3-5-sonnet-20241022-v2:0
- mistral/codestral-2405
- mistral/codestral-latest
- mistral/codestral-mamba-latest
- mistral/mistral-large-2402
- mistral/mistral-large-2407
- mistral/mistral-large-latest
- mistral/mistral-medium
- mistral/mistral-medium-2312
- mistral/mistral-medium-latest
- mistral/mistral-small
- mistral/mistral-small-latest
- mistral/mistral-tiny
- mistral/open-codestral-mamba
- mistral/open-mistral-7b
- mistral/open-mistral-nemo
- mistral/open-mistral-nemo-2407
- mistral/open-mixtral-8x22b
- mistral/open-mixtral-8x7b
- mistral/pixtral-12b-2409
- openrouter/anthropic/claude-3.5-sonnet
- us.anthropic.claude-3-5-sonnet-20241022-v2:0
- vertex_ai/claude-3-5-sonnet-v2@20241022
- vertex_ai/claude-3-5-sonnet@20240620
- vertex_ai/claude-3-haiku@20240307
- vertex_ai/claude-3-opus@20240229
- vertex_ai/claude-3-sonnet@20240229
<!--[[[end]]]-->

4
aider/website/docs/repomap.md
View file

@ -29,9 +29,9 @@ It shows how each of these symbols are defined, by including the critical lines
Here's a part of
the repo map of aider's repo, for
[base_coder.py](https://github.com/paul-gauthier/aider/blob/main/aider/coders/base_coder.py)
[base_coder.py](https://github.com/Aider-AI/aider/blob/main/aider/coders/base_coder.py)
and
[commands.py](https://github.com/paul-gauthier/aider/blob/main/aider/commands.py)
[commands.py](https://github.com/Aider-AI/aider/blob/main/aider/commands.py)
:
```

6
aider/website/docs/scripting.md
View file

@ -26,7 +26,9 @@ for FILE in *.py ; do
done
```
User `aider --help` to see all the command line options, but these are useful for scripting:
Use `aider --help` to see all the
[command line options](/docs/config/options.html),
but these are useful for scripting:
```
--stream, --no-stream
@ -81,7 +83,7 @@ coder.run("/tokens")
```
See the
[Coder.create() and Coder.__init__() methods](https://github.com/paul-gauthier/aider/blob/main/aider/coders/base_coder.py)
[Coder.create() and Coder.__init__() methods](https://github.com/Aider-AI/aider/blob/main/aider/coders/base_coder.py)
for all the supported arguments.
It can also be helpful to set the equivalent of `--yes` by doing this:

2
aider/website/docs/troubleshooting/aider-not-found.md
View file

@ -17,7 +17,7 @@ You may see an error message like this:
Below is the most fail safe way to install and run aider in these situations:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
python -m aider
```

24
aider/website/docs/troubleshooting/edit-errors.md
View file

@ -14,7 +14,7 @@ This usually happens because the LLM is disobeying the system prompts
and trying to make edits in a format that aider doesn't expect.
Aider makes every effort to get the LLM
to conform, and works hard to deal with
LLMM edits that are "almost" correctly formatted.
LLM edits that are "almost" correctly formatted.
But sometimes the LLM just won't cooperate.
In these cases, here are some things you might try.
@ -30,16 +30,30 @@ disobeying the system prompt instructions.
Most local models are just barely capable of working with aider,
so editing errors are probably unavoidable.
Local models which have been quantized are even more likely to have problems
because they are not capable enough to follow aider's system prompts.
## Try the whole format
Run aider with `--edit-format whole` if the model is using a different edit format.
You can see which edit format it is using in the announce lines:
```
Aider v0.50.2-dev
Models: claude-3-5-sonnet-20240620 with ♾️ diff edit format
```
## Reduce distractions
Many LLM now have very large context windows,
Many LLMs now have very large context windows,
but filling them with irrelevant code or conversation
can cofuse the model.
can confuse the model.
- Don't add too many files to the chat, *just* add the files you think need to be edited.
Aider also sends the LLM a [map of your entire git repo](https://aider.chat/docs/repomap.html), so other relevant code will be included automatically.
- Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help GPT produce properly formatted edits.
- Use `/clear` to remove the conversation history, again to help GPT focus.
- Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help the LLM produce properly formatted edits.
- Use `/clear` to remove the conversation history, again to help the LLM focus.
- Use `/tokens` to see how many tokens you are using for each message.
## More help

72
aider/website/docs/troubleshooting/imports.md Normal file
View file

@ -0,0 +1,72 @@
---
parent: Troubleshooting
nav_order: 28
---
# Dependency versions
Aider expects to be installed via `pip` or `pipx`, which will install
correct versions of all of its required dependencies.
If you've been linked to this doc from a GitHub issue,
or if aider is reporting `ImportErrors`
it is likely that your
aider install is using incorrect dependencies.
## Install with pipx
If you are having dependency problems you should consider
[installing aider using pipx](/docs/install/pipx.html).
This will ensure that aider is installed in its own python environment,
with the correct set of dependencies.
Try re-installing cleanly:
```
pipx uninstall aider-chat
pipx install aider-chat
```
## Package managers like Homebrew, AUR, ports
Package managers often install aider with the wrong dependencies, leading
to import errors and other problems.
The recommended way to
install aider is with
[pip](/docs/install/install.html).
Be sure to use the `--upgrade-strategy only-if-needed` switch so that the correct
versions of dependencies will be installed.
```
python -m pip install -U --upgrade-strategy only-if-needed aider-chat
```
A very safe way is to
[install aider using pipx](/docs/install/pipx.html),
which will ensure it is installed in a stand alone virtual environment.
## Dependency versions matter
Aider pins its dependencies and is tested to work with those specific versions.
If you are installing aider with pip (rather than pipx),
you should be careful about upgrading or downgrading the python packages that
aider uses.
In particular, be careful with the packages with pinned versions
noted at the end of
[aider's requirements.in file](https://github.com/Aider-AI/aider/blob/main/requirements/requirements.in).
These versions are pinned because aider is known not to work with the
latest versions of these libraries.
Also be wary of upgrading `litellm`, as it changes versions frequently
and sometimes introduces bugs or backwards incompatible changes.
## Replit
You can `pip install -U aider-chat` on replit.
Or you can install aider with
pipx as follows:
{% include replit-pipx.md %}

2
aider/website/docs/troubleshooting/token-limits.md
View file

@ -68,7 +68,7 @@ To avoid hitting output token limits:
- Ask for smaller changes in each request.
- Break your code into smaller source files.
- Use a strong model like gpt-4o, sonnet or opus that can return diffs.
- Use a model that supports [infinite output](/docs/more/infinite-output.html).
## Other causes

6
aider/website/docs/unified-diffs.md
View file

@ -317,7 +317,7 @@ the ones with the most code and which involve refactoring.
Based on this observation, I set out to build a benchmark based on refactoring
a non-trivial amount of code found in fairly large files.
To do this, I used python's `ast` module to analyze
[9 popular open source python repositories](https://github.com/paul-gauthier/refactor-benchmark)
[9 popular open source python repositories](https://github.com/Aider-AI/refactor-benchmark)
to identify challenging refactoring tasks.
The goal was to find:
@ -332,7 +332,7 @@ where we ask GPT to do something like:
> Name the new function `_set_csrf_cookie`, exactly the same name as the existing method.
> Update any existing `self._set_csrf_cookie` calls to work with the new `_set_csrf_cookie` function.
A [simple python AST scanning script](https://github.com/paul-gauthier/aider/blob/main/benchmark/refactor_tools.py)
A [simple python AST scanning script](https://github.com/Aider-AI/aider/blob/main/benchmark/refactor_tools.py)
found 89 suitable files
and packaged them up as benchmark tasks.
Each task has a test
@ -351,7 +351,7 @@ gathered during benchmarking like the
introduction of new comments that contain "...".
The result is a pragmatic
[benchmark suite that provokes, detects and quantifies GPT coding laziness](https://github.com/paul-gauthier/refactor-benchmark).
[benchmark suite that provokes, detects and quantifies GPT coding laziness](https://github.com/Aider-AI/refactor-benchmark).

2
aider/website/docs/usage/browser.md
View file

@ -48,7 +48,7 @@ It also supports [connecting to almost any LLM](https://aider.chat/docs/llms.htm
Use the `--browser` switch to launch the browser version of aider:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
export OPENAI_API_KEY=<key> # Mac/Linux
setx OPENAI_API_KEY <key> # Windows, restart shell after setx

51
aider/website/docs/usage/caching.md Normal file
View file

@ -0,0 +1,51 @@
---
title: Prompt caching
highlight_image: /assets/prompt-caching.jpg
parent: Usage
nav_order: 750
description: Aider supports prompt caching for cost savings and faster coding.
---
# Prompt caching
Aider supports prompt caching for cost savings and faster coding.
Currently Anthropic provides caching for Sonnet and Haiku,
and DeepSeek provides caching for Coder.
Aider organizes the chat history to try and cache:
- The system prompt.
- Read only files added with `--read` or `/read-only`.
- The repository map.
- The editable files that have been added to the chat.
![Prompt caching](/assets/prompt-caching.jpg)
## Usage
Run aider with `--cache-prompts` or add that setting to your
[configuration files](/docs/config.html).
Due to limitations in the provider APIs, caching statistics and costs
are not available when streaming responses.
To turn off streaming, use `--no-stream`.
When caching is enabled, it will be noted for the main model when aider launches:
```
Main model: claude-3-5-sonnet-20240620 with diff edit format, prompt cache, infinite output
```
## Preventing cache expiration
Aider can ping the provider to keep your prompt cache warm and prevent
it from expiring.
By default, Anthropic keeps your cache for 5 minutes.
Use `--cache-keepalive-pings N` to tell aider to ping
every 5 minutes to keep the cache warm.
Aider will ping up to `N` times over a period of `N*5` minutes
after each message you send.

20
aider/website/docs/usage/commands.md
View file

@ -14,31 +14,39 @@ cog.out(get_help_md())
|Command|Description|
|:------|:----------|
| **/add** | Add files to the chat so GPT can edit them or review them in detail |
| **/add** | Add files to the chat so aider can edit them or review them in detail |
| **/architect** | Enter architect mode to discuss high-level design and architecture |
| **/ask** | Ask questions about the code base without editing any files |
| **/chat-mode** | Switch to a new chat mode |
| **/clear** | Clear the chat history |
| **/clipboard** | Add image/text from the clipboard to the chat (optionally provide a name for the image) |
| **/code** | Ask for changes to your code |
| **/commit** | Commit edits to the repo made outside the chat (commit message optional) |
| **/copy** | Copy the last assistant message to the clipboard |
| **/diff** | Display the diff of changes since the last message |
| **/drop** | Remove files from the chat session to free up context space |
| **/exit** | Exit the application |
| **/git** | Run a git command |
| **/git** | Run a git command (output excluded from chat) |
| **/help** | Ask questions about aider |
| **/lint** | Lint and fix provided files or in-chat files if none provided |
| **/lint** | Lint and fix in-chat files or all dirty files if none in chat |
| **/load** | Load and execute commands from a file |
| **/ls** | List all known files and indicate which are included in the chat session |
| **/map** | Print out the current repository map |
| **/map-refresh** | Force a refresh of the repository map |
| **/model** | Switch to a new LLM |
| **/models** | Search the list of available models |
| **/paste** | Paste image/text from the clipboard into the chat. Optionally provide a name for the image. |
| **/quit** | Exit the application |
| **/read** | Add a file to the chat that is for reference, not to be edited |
| **/read-only** | Add files to the chat that are for reference, not to be edited |
| **/report** | Report a problem by opening a GitHub Issue |
| **/reset** | Drop all files and clear the chat history |
| **/run** | Run a shell command and optionally add the output to the chat (alias: !) |
| **/save** | Save commands to a file that can reconstruct the current chat session's files |
| **/settings** | Print out the current settings |
| **/test** | Run a shell command and add the output to the chat on non-zero exit code |
| **/tokens** | Report on the number of tokens used by the current chat context |
| **/undo** | Undo the last git commit if it was done by aider |
| **/voice** | Record and transcribe voice input |
| **/web** | Scrape a webpage, convert to markdown and add to the chat |
| **/web** | Scrape a webpage, convert to markdown and send in a message |
<!--[[[end]]]-->

31
aider/website/docs/usage/conventions.md
View file

@ -21,10 +21,35 @@ For example, say we want our python code to:
We would simply create a file like `CONVENTIONS.md` with those lines
and then we can add it to the aider chat, along with the file(s)
that we want to edit:
that we want to edit.
It's best to load the conventions file with `/read CONVENTIONS.md`
or `aider --read CONVENTIONS.md`.
This way it is marked as read-only, and cached if prompt caching
is enabled.
## Always load conventions
You can also configure aider to always load your conventions file
in the [`.aider.conf.yml` config file](https://aider.chat/docs/config/aider_conf.html):
```yaml
# alone
read: CONVENTIONS.md
# multiple files
read: [CONVENTIONS.md, anotherfile.txt]
```
## Example
See below for an example of how the conventions can affect the code
that aider writes.
<div class="chat-transcript" markdown="1">
> $ aider CONVENTIONS.md useragent.py
> $ aider --read CONVENTIONS.md useragent.py
>
> Aider v0.24.2-dev
> Added CONVENTIONS.md to the chat.
@ -85,3 +110,5 @@ which is perhaps more typical in small python scripts.
> Applied edit to useragent.py
</div>

7
aider/website/docs/usage/images-urls.md
View file

@ -23,7 +23,7 @@ You can add images to the chat just like you would
add any other file:
- Use `/add <image-filename>` from within the chat
- Use `/clipboard` to paste an image from your clipboard into the chat.
- Use `/paste` to paste an image from your clipboard into the chat.
- Launch aider with image filenames on the command line: `aider <image-filename>` along with any other command line arguments you need.
## Web pages
@ -40,4 +40,9 @@ To add URLs to the chat:
- Use `/web <url>`
- Just paste the URL into the chat and aider will ask if you want to add it.
You can also scrape web pages from the command line to see the markdown version that aider produces:
```
python -m aider.scrape https://aider.chat/docs/usage/tips.html
```

17
aider/website/docs/usage/lint-test.md
View file

@ -31,18 +31,21 @@ You can disable this with the `--no-auto-lint` switch.
## Testing
You can configure aider to run your test suite
after each time the AI edits your code
using the `--test-cmd <cmd>` switch.
You can run tests with `/test <test-command>`.
Aider will run the test command without any arguments.
If there are test errors, aider expects the
command to print them on stdout/stderr
and return a non-zero exit code.
This is how most test tools normally operate.
To have aider automatically run the test command,
use the `--auto-test` switch.
Aider will try and fix any errors
if the command returns a non-zero exit code.
You can configure aider to run your test suite
after each time the AI edits your code
using the `--test-cmd <test-command>` and
`--auto-test` switch.
## Compiled languages

71
aider/website/docs/usage/modes.md
View file

@ -6,15 +6,17 @@ description: Using the chat, ask and help chat modes.
# Chat modes
Aider has 3 different chat modes:
Aider has a few different chat modes:
- `code` - Aider will make changes to your code to satisfy your requests.
- `architect` - Aider will first propose a solution, then ask if you want it to turn that proposal into edits to your files.
- `ask` - Aider will answer questions about your code, but never edit it.
- `help` - Aider will answer questions about using aider, configuring, troubleshooting, etc.
By default, aider starts in "code" mode. As you are talking, you can
send individual messages in a specific mode using `/code`, `/ask`, and `/help` commands:
Using `/code`, `/ask`, and `/help` applies just to that particular message.
send individual messages in a specific mode using
`/code`, `/architect`, `/ask`, and `/help` commands:
Using these `/`-commands applies just to that particular message.
Your next message will go back to the active mode (usually "code" mode by default).
You can switch the active mode in a sticky way
@ -22,11 +24,53 @@ with the `/chat-mode <mode>` command:
```
/chat-mode code
/chat-mode architect
/chat-mode ask
/chat-mode help
```
Or you can launch aider in one of the modes with the `--chat-mode <mode>` switch.
There is also a special shortcut `--architect` to launch in `--chat-mode architect`.
## Architect mode and the editor model
When you are in architect mode, aider sends your request to two models:
1. First, it sends your request to the main active model.
The main model is configured with `/model`, `--model` or the shortcut switches like `--sonnet`.
After the main model replies, aider will offer to edit the files based on the response.
2. To edit the files, aider sends a second LLM request asking for specific code editing instructions.
This request goes to the "editor" model.
Aider has built in defaults to select an editor model based on your main model.
Or, you can choose an editor model yourself with `--editor-model <model>`.
Architect mode produces better results than code mode, but uses two LLM requests.
This probably makes it slower and more expensive than using code mode.
Architect mode is especially useful with OpenAI's o1 models, which are strong at
reasoning but less capable at editing files.
Pairing an o1 architect with an editor model like GPT-4o or Sonnet will
give the best results.
But architect mode is also quite helpful when you use GPT-4o or Sonnet
at both the architect and the editor.
Allowing the model two requests to solve the problem and edit the files
usually provides a better result.
The editor model uses one of aider's edit formats to let the LLM
edit source files.
Aider will pick a suitable edit format by default,
but you can customize it with `--editor-edit-format <format>`.
The
["editor-diff" and "editor-whole" edit formats](/docs/more/edit-formats.html#editor-diff-and-editor-whole)
are the recommended edit formats when using architect mode.
See this article on
[aider's architect/editor mode](/2024/09/26/architect.html)
for more details.
## Examples
<div class="chat-transcript" markdown="1">
@ -63,5 +107,26 @@ print(factorial(5)) # Output: 120
This function uses recursion to calculate the factorial. It's been added to your code.
#### /architect Can we make this simpler?
Yes, you could replace the `factorial()` function with a call to the `math.factorial()`
builtin.
This way you don't have to maintain a custom factorial implementation,
and the builtin function is well optimized.
> Edit the files? (Y)es/(N)o [Yes]: Yes
```python
<<<<<<< SEARCH
def factorial(n):
if n == 0 or n == 1:
return 1
else:
return n * factorial(n - 1)
=======
from math import factorial
>>>>>>> REPLACE
```
</div>

81
aider/website/docs/usage/tips.md
View file

@ -6,21 +6,74 @@ description: Tips for AI pair programming with aider.
# Tips
- Think about which files need to be edited to make your change and add them to the chat.
Aider can help the LLM figure out which files to edit all by itself, but the most efficient approach is to add the needed files to the chat yourself.
- Don't add *everything* to the chat, just the files you think need to be edited.
Aider also sends the LLM a [map of your entire git repo](https://aider.chat/docs/repomap.html).
So the LLM can see all the other relevant parts of your code base.
- Large changes are best performed as a sequence of thoughtful bite sized steps, where you plan out the approach and overall design. Walk the LLM through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.
- It's always safe to use Control-C to interrupt aider if it isn't providing a useful response. The partial response remains in the conversation, so you can refer to it when you reply to the LLM with more information or direction.
- If your code is throwing an error,
use the `/run` [in-chat command](/docs/usage/commands.html)
## Just add the files that need to be changed to the chat
Take a moment and think about which files will need to be changed.
Aider can often figure out which files to edit all by itself, but the most efficient approach is for you to add the files to the chat.
## Don't add lots of files to the chat
Just add the files you think need to be edited.
Too much irrelevant code will distract and confuse the LLM.
Aider uses a [map of your entire git repo](https://aider.chat/docs/repomap.html)
so is usually aware of relevant classes/functions/methods elsewhere in your code base.
It's ok to add 1-2 highly relevant files that don't need to be edited,
but be selective.
## Break your goal down into bite sized steps
Do them one at a time.
Adjust the files added to the chat as you go: `/drop` files that don't need any more changes, `/add` files that need changes for the next step.
## For complex changes, discuss a plan first
Use the [`/ask` command](modes.html) to make a plan with aider.
Once you are happy with the approach, just say "go ahead" without the `/ask` prefix.
## If aider gets stuck
- Use `/clear` to discard the chat history and make a fresh start.
- Can you `/drop` any extra files?
- Use `/ask` to discuss a plan before aider starts editing code.
- Use the [`/model` command](commands.html) to switch to a different model and try again. Switching between GPT-4o and Sonnet will often get past problems.
- If aider is hopelessly stuck,
just code the next step yourself and try having aider code some more after that.
Take turns and pair program with aider.
## Creating new files
If you want aider to create a new file, add it to the repository first with `/add <file>`.
This way aider knows this file exists and will write to it.
Otherwise, aider might write the changes to an existing file.
This can happen even if you ask for a new file, as LLMs tend to focus a lot
on the existing information in their contexts.
## Fixing bugs and errors
If your code is throwing an error,
use the [`/run` command](commands.html)
to share the error output with the aider.
Or just paste the errors into the chat. Let the aider figure out and fix the bug.
- If test are failing, use the `/test` [in-chat command](/docs/usage/commands.html)
Or just paste the errors into the chat. Let the aider figure out how to fix the bug.
If test are failing, use the [`/test` command](lint-test.html)
to run tests and
share the error output with the aider.
- {% include multi-line.md %}
- LLMs know about a lot of standard tools and libraries, but may get some of the fine details wrong about API versions and function arguments.
You can paste doc snippets into the chat to resolve these issues.
## Providing docs
LLMs know about a lot of standard tools and libraries, but may get some of the fine details wrong about API versions and function arguments.
You can provide up-to-date documentation in a few ways:
- Paste doc snippets into the chat.
- Include a URL to docs in your chat message
and aider will scrape and read it. For example: `Add a submit button like this https://ui.shadcn.com/docs/components/button`.
- Use the [`/read` command](commands.html) to read doc files into the chat from anywhere on your filesystem.
- If you have coding conventions or standing instructions you want aider to follow, consider using a [conventions file](conventions.html).
## Interrupting & inputting
Use Control-C to interrupt aider if it isn't providing a useful response. The partial response remains in the conversation, so you can refer to it when you reply with more information or direction.
{% include multi-line.md %}

5
aider/website/docs/usage/tutorials.md
View file

@ -8,6 +8,11 @@ description: Intro and tutorial videos made by aider users.
Here are some tutorial videos made by aider users:
- [Using Architect/Editor mode](https://www.youtube.com/watch?v=OPXslklVBZc) -- AICodeKing
- [Using aider to incrementally build a non-trivial app](https://youtu.be/QlUt06XLbJE) -- IndyDevDan
- [Aider and Replit on mobile with your voice](https://x.com/itsPaulAi/status/1830987090617831810) -- Paul Couvert
- [Aider is the OG AI Coding King (Mermaid Diagram AI Agent)](https://www.youtube.com/watch?v=ag-KxYS8Vuw) -- IndyDevDan
- [Installing aider in replit and making a Trello clone](https://x.com/itspaulai/status/1828834199597633724) -- Paul Couvert
- [Step-by-Step Development Environment Setup for AI-Assisted Coding](https://www.youtube.com/watch?v=DnBVgfe6ZQM) -- Coding the Future With AI
- [Generate FULL-STACK Apps with Claude 3.5 Sonnet](https://youtu.be/sKeIZGW8xzg) -- AICodeKing
- [Creating Games with AI from Start-To-End](https://youtu.be/sOd2YYZFMUs) -- AICodeKing

2
aider/website/examples/README.md
View file

@ -8,7 +8,7 @@ has_toc: false
# Example chat transcripts
Below are some chat transcripts showing what it's like to code with aider.
In the chats, you'll see a varity of coding tasks like generating new code, editing existing code, debugging, exploring unfamiliar code, etc.
In the chats, you'll see a variety of coding tasks like generating new code, editing existing code, debugging, exploring unfamiliar code, etc.
* [**Hello World Flask App**](https://aider.chat/examples/hello-world-flask.html): Start from scratch and have aider create a simple Flask app with various endpoints, such as adding two numbers and calculating the Fibonacci sequence.

38
aider/website/index.md
View file

@ -10,6 +10,19 @@ text = open("README.md").read()
text = text.replace('['*3 + 'cog', ' NOOP ')
text = text.replace('['*3 + 'end', ' NOOP ')
text = text.replace(']'*3, '')
# embedding these confuses the syntax highlighter while editing index.md
com_open = '<!' + '--'
com_close = '--' + '>'
# comment out the screencast
text = text.replace('SCREENCAST START ' + com_close, '')
text = text.replace(com_open + ' SCREENCAST END', '')
# uncomment the video
text = text.replace('VIDEO START', com_close)
text = text.replace('VIDEO END', com_open)
cog.out(text)
]]]-->
@ -23,12 +36,23 @@ Start a new project or work with an existing git repo.
Aider works best with GPT-4o & Claude 3.5 Sonnet and can
[connect to almost any LLM](https://aider.chat/docs/llms.html).
<!--
<p align="center">
<img
src="https://aider.chat/assets/screencast.svg"
alt="aider screencast"
>
</p>
-->
<!-- -->
<p align="center">
<video style="max-width: 100%; height: auto;" autoplay loop muted playsinline>
<source src="/assets/shell-cmds-small.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
</p>
<!-- -->
<p align="center">
<a href="https://discord.gg/Tv2uQnR88V">
@ -49,7 +73,7 @@ cog.out(open("aider/website/_includes/get-started.md").read())
You can get started quickly like this:
```
python -m pip install aider-chat
python -m pip install -U aider-chat
# Change directory into a git repo
cd /to/your/git/repo
@ -110,7 +134,7 @@ projects like django, scikitlearn, matplotlib, etc.
- [Configuration](https://aider.chat/docs/config.html)
- [Troubleshooting](https://aider.chat/docs/troubleshooting.html)
- [LLM Leaderboards](https://aider.chat/docs/leaderboards/)
- [GitHub](https://github.com/paul-gauthier/aider)
- [GitHub](https://github.com/Aider-AI/aider)
- [Discord](https://discord.gg/Tv2uQnR88V)
- [Blog](https://aider.chat/blog/)
@ -121,14 +145,14 @@ projects like django, scikitlearn, matplotlib, etc.
- *The best AI coding assistant so far.* -- [Matthew Berman](https://www.youtube.com/watch?v=df8afeb1FY8)
- *Aider ... has easily quadrupled my coding productivity.* -- [SOLAR_FIELDS](https://news.ycombinator.com/item?id=36212100)
- *It's a cool workflow... Aider's ergonomics are perfect for me.* -- [qup](https://news.ycombinator.com/item?id=38185326)
- *It's really like having your senior developer live right in your Git repo - truly amazing!* -- [rappster](https://github.com/paul-gauthier/aider/issues/124)
- *What an amazing tool. It's incredible.* -- [valyagolev](https://github.com/paul-gauthier/aider/issues/6#issue-1722897858)
- *Aider is such an astounding thing!* -- [cgrothaus](https://github.com/paul-gauthier/aider/issues/82#issuecomment-1631876700)
- *It's really like having your senior developer live right in your Git repo - truly amazing!* -- [rappster](https://github.com/Aider-AI/aider/issues/124)
- *What an amazing tool. It's incredible.* -- [valyagolev](https://github.com/Aider-AI/aider/issues/6#issue-1722897858)
- *Aider is such an astounding thing!* -- [cgrothaus](https://github.com/Aider-AI/aider/issues/82#issuecomment-1631876700)
- *It was WAY faster than I would be getting off the ground and making the first few working versions.* -- [Daniel Feldman](https://twitter.com/d_feldman/status/1662295077387923456)
- *THANK YOU for Aider! It really feels like a glimpse into the future of coding.* -- [derwiki](https://news.ycombinator.com/item?id=38205643)
- *It's just amazing. It is freeing me to do things I felt were out my comfort zone before.* -- [Dougie](https://discord.com/channels/1131200896827654144/1174002618058678323/1174084556257775656)
- *This project is stellar.* -- [funkytaco](https://github.com/paul-gauthier/aider/issues/112#issuecomment-1637429008)
- *Amazing project, definitely the best AI coding assistant I've used.* -- [joshuavial](https://github.com/paul-gauthier/aider/issues/84)
- *This project is stellar.* -- [funkytaco](https://github.com/Aider-AI/aider/issues/112#issuecomment-1637429008)
- *Amazing project, definitely the best AI coding assistant I've used.* -- [joshuavial](https://github.com/Aider-AI/aider/issues/84)
- *I absolutely love using Aider ... It makes software development feel so much lighter as an experience.* -- [principalideal0](https://discord.com/channels/1131200896827654144/1133421607499595858/1229689636012691468)
- *I have been recovering from multiple shoulder surgeries ... and have used aider extensively. It has allowed me to continue productivity.* -- [codeninja](https://www.reddit.com/r/OpenAI/s/nmNwkHy1zG)
- *I am an aider addict. I'm getting so much more work done, but in less time.* -- [dandandan](https://discord.com/channels/1131200896827654144/1131200896827654149/1135913253483069470)