Specifying coding conventions
Tell aider to follow your coding conventions when it works on your code.
Sometimes you want GPT to be aware of certain coding guidelines, like whether to provide type hints, which libraries or packages to prefer, etc.
The easiest way to do that with aider is to simply create a small markdown file and include it in the chat.
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.
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:
Example
See below for an example of how the conventions can affect the code that aider writes.
> $ aider --read CONVENTIONS.md useragent.py > > Aider v0.24.2-dev > Added CONVENTIONS.md to the chat. > Added useragent.py to the chat.
write a function that uses httpbin to check the user agent on the request. return the ua.
To fulfill your request, I will:
Add an import for
httpx
.Write a function named
check_user_agent
that makes a GET request tohttpbin.org/user-agent
and returns the user agent string.
Here is the diff for the useragent.py
file:
This function uses httpx
to make a GET request to httpbin.org/user-agent
, which returns a JSON response containing the user agent of the HTTP client. The function then extracts the user agent string from the JSON response and returns it.
Applied edit to useragent.py
GPT correctly used httpx
and provided type hints. See below for the transcript of this same coding task conducted without using CONVENTIONS.md
. In this case, GPT used requests
and skipped types, which is perhaps more typical in small python scripts.
> $ aider useragent.py > > Aider v0.24.2-dev > Added useragent.py to the chat.
write a function that uses httpbin to check the user agent on the request. return the ua.
Applied edit to useragent.py
Last updated