Include x-coding-assistant=aider-version header in litellm calls #2988
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jhrozek
changed the title
Proxies that inspect traffic between the development environment and an LLM might be interested in whether it's aider or another tool calling in order to be able to inspect and/or modify the payload. The most common way of solving this would be to add a `user-agent` header. However, litellm which aider uses calls into OpenAI libraries directly when making the request and it seems like the only way to set a custom `http_client`. This seemed like something that might have unforeseen consequences (timeouts? retries?). For other LLMs, litellm seems to use its own httpx wrapper which might presumably be easier to customize, but I have not tried. To make things easier, let's just add an aider specific header. I put the string aider followed by the version there, but the value - and indeed the key - of the header are not that interesting, what I would like to do is to just be able to to tell aider calls.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proxies that inspect traffic between the development environment and an
LLM might be interested in whether it's aider or another tool calling in
order to be able to inspect and/or modify the payload.
The most common way of solving this would be to add a
user-agentheader.However, litellm which aider uses calls into OpenAI libraries directly
when making the request and it seems like the only way to set a custom
http_client. This seemed like something that might have unforeseenconsequences (timeouts? retries?). For other LLMs, litellm seems to use
its own httpx wrapper which might presumably be easier to customize, but
I have not tried.
To make things easier, let's just add an aider specific header. I put
the version there, but the value - and indeed the key - of the header
are not that interesting, what I would like to do is to just be able to
to tell aider calls.