FAQ

Use /help <question> to ask for help about using aider, customizing settings, troubleshooting, using LLMs, etc.

How can I add ALL the files to the chat?

People regularly ask about how to add many or all of their repo’s files to the chat. This is probably not a good idea and will likely do more harm than good.

The best approach is think about which files need to be changed to accomplish the task you are working on. Just add those files to the chat.

Usually when people want to add “all the files” it’s because they think it will give the LLM helpful context about the overall code base. cecli will automatically give the LLM a bunch of additional context about the rest of your git repo. It does this by analyzing your entire codebase in light of the current chat to build a compact repository map.

Adding a bunch of files that are mostly irrelevant to the task at hand will often distract or confuse the LLM. The LLM will give worse coding results, and sometimese even fail to correctly edit files. Addings extra files will also increase your token costs.

Again, it’s usually best to just add the files to the chat that will need to be modified. If you still wish to add lots of files to the chat, you can:

  • Use a wildcard when you launch cecli: cecli src/*.py
  • Use a wildcard with the in-chat /add command: /add src/*.py
  • Give the /add command a directory name and it will recursively add every file under that dir: /add src

Can I use cecli in a large (mono) repo?

cecli 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.

Be sure to check the general usage tips before considering this large-repo specific advice. To get the best results from cecli 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 cecli to ignore the repo outside of the directory you start in.

You can also create a .aiderignore file to tell cecli to ignore parts of the repo that aren’t relevant to your task. This file conforms to .gitignore syntax and conventions. For example, to focus only on specific directories in a monorepo, you could create a .aiderignore file with:

# Ignore everything
/*

# Allow specific directories and their contents
!foo/
!bar/
!baz/

# Allow nested files under these directories
!foo/**
!bar/**
!baz/**

You can use --aiderignore <filename> to name a specific file 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 cecli with multiple git repos at once?

Currently cecli 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 cecli 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 cecli see key functions or docs from the other repo.
  • You can run cecli --show-repo-map > map.md within each repo to create repo maps. You could then run cecli 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 cecli to write documentation about a repo. Inside each repo, you could run cecli docs.md and work with cecli to write some markdown docs. Then while using cecli 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 cecli to write a small script that demonstrates the functionality you want to use in repo B. Then when you’re using cecli in repo B, you can /read in that script.

How do I turn on the repository map?

Depending on the LLM you are using, cecli 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 cecli with --map-tokens 1024.

How do I include the git history in the context?

When starting a fresh cecli 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 cecli session and you want to provide context about recent work.

You can also use cecli to review PR branches:

/run git diff one-branch..another-branch

...

Add 6.9k tokens of command output to the chat? (Y)es/(N)o [Yes]: Yes

/ask Are there any problems with the way this change works with the FooBar class?

And of course you can prepare diff output outside of cecli and provide it as a file for cecli to read:

$ git diff -C10 v1..v2 > v1-v2-changes.diff
$ cecli --read v1-v2-changes.diff

cecli v0.77.2.dev+import
Main model: anthropic/claude-3-7-sonnet-20250219 with diff edit format, 8k think tokens
──────────────────────────────────
v1-v2-changes.diff
> Do you see any potential bugs in this PR?

The /git command will not work for this purpose, as its output is not included in the chat.

How can I run cecli locally from source code?

To run the project locally, follow these steps:

# Clone the repository
git clone git@github.com:cecli-AI/cecli.git

# Navigate to the project directory
cd cecli

# It's recommended to make a virtual environment

# Install cecli 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 cecli
python -m cecli

Can I change the system prompts that cecli uses?

The most convenient way to add custom instructions is to use a conventions file.

But, cecli is set up to support different actual system prompts and edit formats in a modular way. If you look in the cecli/coders subdirectory, you’ll see there’s a base coder with base prompts, and then there are a number of different specific coder implementations.

If you’re thinking about experimenting with system prompts this document about benchmarking GPT-3.5 and GPT-4 on code editing might be useful background.

While it’s not well documented how to add new coder subsystems, you may be able to modify an existing implementation or use it as a template to add another.

To get started, try looking at and modifying these files.

The wholefile coder is currently used by GPT-3.5 by default. You can manually select it with --edit-format whole.

  • wholefile_coder.py
  • wholefile_prompts.py

The editblock coder is currently used by GPT-4o by default. You can manually select it with --edit-format diff.

  • editblock_coder.py
  • editblock_prompts.py

The universal diff coder is currently used by GPT-4 Turbo by default. You can manually select it with --edit-format udiff.

  • udiff_coder.py
  • udiff_prompts.py

When experimenting with coder backends, it helps to run cecli with --verbose --no-pretty so you can see all the raw information being sent to/from the LLM in the conversation.

You can also refer to the instructions for installing a development version of cecli.

What LLMs do you use to build cecli?

cecli writes a lot of its own code, usually about 70% of the new code in each release. People often ask which LLMs I use with cecli, when writing cecli. Below is a table showing the models I have used recently, extracted from the public log of my cecli analytics.

Model NameTotal TokensPercent
gemini/gemini-2.5-pro222,04729.7%
gpt-5211,07228.2%
None168,98822.6%
gemini/gemini-3-pro-preview81,85111.0%
o3-pro36,6204.9%
gemini/gemini-2.5-flash-lite15,4702.1%
gemini/gemini-2.5-flash-lite-preview-06-1711,3711.5%

How are the “cecli wrote xx% of code” stats computed?

cecli is tightly integrated with git so all of cecli’s code changes are committed to the repo with proper attribution. The stats are computed by doing something like git blame on the repo, and counting up who wrote all the new lines of code in each release. Only lines in source code files are counted, not documentation or prompt files.

Why did cecli ignore/discard its proposed edits after it asked to add a new file to the chat?

If cecli prompts you to add a new file to the chat and you say yes, it will re-submit the original request. The fact that the LLM’s reply indicated that it needed to see another file (and you said yes) is often a sign that the LLM should have been able to see/edit that file in the first place. Without access to it, there is increased chance that it’s done a bad implementation of the requested change. Often LLMs will hallucinate content for the files they needed but didn’t have. So cecli re-submits the original request in this situation.

Why does cecli sometimes stop highlighting code in its replies?

cecli displays the markdown responses that are coming back from the LLM. Usually, the LLM will reply with code in a markdown “code block” with triple backtick fences, like this:

Here's some code:

```
print("hello")
```

But if you’ve added files to the chat that contain triple backticks, cecli needs to tell the LLM to use a different set of fences. Otherwise, the LLM can’t safely include your code’s triple backticks inside the code blocks that it returns with edits. cecli will use fences like <source>...</source> in this case.

A side effect of this is that the code that cecli outputs may no longer be properly highlighted. You will most often notice this if you add markdown files to you chats that contain code blocks.

Why is the LLM speaking to me in an unexpected language?

cecli goes to some effort to prompt the model to use the language that is configured for your system. But LLMs aren’t fully reliable, and they sometimes decide to speak in an unexpected language. Claude is especially fond of speaking French.

You can explicitly set the language that cecli tells the model to use with --chat-language <language>. But the LLM may not comply.

Can I share my cecli chat transcript?

Yes, you can now share cecli chat logs in a pretty way.

  1. Copy the markdown logs you want to share from .aider.dev.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/cecli-AI/2087ab8b64034a078c0a209440ac8be0

  2. Take the gist URL and append it to:

    https://cecli.dev/share/?mdurl=

This will give you a URL like this, which shows the chat history like you’d see in a terminal:

https://cecli.dev/share/?mdurl=https://gist.github.com/cecli-AI/2087ab8b64034a078c0a209440ac8be0

Can I edit files myself while cecli is running?

Yes. cecli always reads the latest copy of files from the file system when you send each message.

While you’re waiting for cecli’s reply to complete, it’s probably unwise to edit files that you’ve added to the chat. Your edits and cecli’s edits might conflict.

What is cecli AI LLC?

cecli AI LLC is the company behind the cecli AI coding tool. cecli is open source and available on GitHub under an Apache 2.0 license.

Can I Script cecli?

Yes. You can script cecli via the command line or python. See more from here: Scripting cecli