[WIP][feature enhancement] Add all supported litellm models to "other" option in cli/wiz #331
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
…/wiz flows, but also for searchable models) use_shortcuts is a bummer with search, so bye make the filters behave use a real list of the providers we dont need preferred models honestly, it all lives in the lite llm package anyway cleanup linting/comment changes, move all models list to the other option cleanup cli/wizard implementation and move a util to utils get tests passing and do a little more pr noise cleanup formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise format manually something is weird. missing double-quote get tests passing and do a little more pr noise cleanup formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise formatting noise format manually something is weird.
|
i'd like to reevaluate this. at the very least using questionary, as that was a better UX than inquirerer |
bboynton97
reviewed
Mar 5, 2025
There was a problem hiding this comment.
lets drop this file though, as we should be using uv instead of poetry
There was a problem hiding this comment.
howdy! sorry to go dark on y'all, sick + flooding crawlspace -.-
Inquirer was in there, so I assumed just swap em out, what is the poetry-lock doin in there? Asking for this guy I know whos never done dev work on a windows or dealt with multiple pyenvs locally lol
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.
Pausing this - I need to make sure my local env works more deterministically rq. Getting tests tidied up and testing on both my platforms before I return to this. should help clean up the PR too!
📥 Pull Request
Round two - begin! Would love additional comments since I reworked some things and cleaned up the commit history I had to perma-close the original. #326.
Opted for the route suggested by @bboynton97 of keeping the preferred models, but having the option of trying anything liteLLM supports via the other option in the cli/wiz
📘 Description
🧪 Testing
tox passing locally 🥂
going to run some manual tests as well, but I'm by no means an AgentStack power user.
I also want to add some test coverage around the new list of models, or at least a script to manually test or spot check a few