FAQ

Use /help <question> to ask for help about using PairPilot, 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. PairPilot 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 PairPilot: PairPilot 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 PairPilot in a large (mono) repo?

PairPilot 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 PairPilot 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 PairPilot to ignore the repo outside of the directory you start in.

You can also create a .PairPilotignore file to tell PairPilot 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 .PairPilotignore 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 --PairPilotignore <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 PairPilot with multiple git repos at once?

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

How do I turn on the repository map?

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

How do I include the git history in the context?

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

You can also use PairPilot 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?

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

How can I run PairPilot locally from source code?

To run the project locally, follow these steps:

# Clone the repository
git clone git@github.com:PairPilot/PairPilot.git

# Navigate to the project directory
cd PairPilot

# It's recommended to make a virtual environment

# Install PairPilot 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 PairPilot
python -m PairPilot

Can I change the system prompts that PairPilot uses?

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

But, PairPilot is set up to support different actual system prompts and edit formats in a modular way. If you look in the PairPilot/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 PairPilot 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 PairPilot.

What LLMs do you use to build PairPilot?

PairPilot 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 PairPilot, when writing PairPilot. Below is a table showing the models I have used recently, extracted from the public log of my PairPilot analytics.

Model NameTotal TokensPercent
claude-3-5-sonnet-20241022938,56962.9%
fireworks_ai/accounts/fireworks/models/deepseek-v3273,00518.3%
deepseek/deepseek-chat97,7456.6%
o3-mini75,4005.1%
fireworks_ai/accounts/fireworks/models/deepseek-r165,2514.4%
claude-3-5-haiku-2024102239,4302.6%
gemini/REDACTED1,8590.1%
ollama_chat/REDACTED3090.0%

Some models show as REDACTED, because they are new or unpopular models. PairPilot’s analytics only records the names of “well known” LLMs.

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

PairPilot is tightly integrated with git so all of PairPilot’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 does PairPilot sometimes stop highlighting code in its replies?

PairPilot 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, PairPilot 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. PairPilot will use fences like <source>...</source> in this case.

A side effect of this is that the code that PairPilot 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?

PairPilot 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 PairPilot tells the model to use with --chat-language <language>. But the LLM may not comply.

Can I share my PairPilot chat transcript?

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

  1. Copy the markdown logs you want to share from .PairPilot.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/pair-pilot/2087ab8b64034a078c0a209440ac8be0

  2. Take the gist URL and append it to:

    https://PairPilot.chat/share/?mdurl=

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

https://PairPilot.chat/share/?mdurl=https://gist.github.com/pair-pilot/2087ab8b64034a078c0a209440ac8be0

Can I edit files myself while PairPilot is running?

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

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

What is PairPilot AI LLC?

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