Command: Remove model override for Test command #3343
Merged
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
umpox
approved these changes
Mar 8, 2024
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Outdated suggestions cannot be applied.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.
Removes model override for the Generate Unit Test command
This pull request removes the model override for the Generate Unit Test command, granting users the flexibility to utilize any edit model for generating unit tests.
Previously, we defaulted to using Claude 2.0 due to observed regressions with other models, as detailed in this discussion. However, with the introduction of Claude 3 and the availability of more alternative models, Claude 2.0 is no longer the sole option for generating effective unit tests. Therefore, we can remove the override for the test command, allowing users to choose from a wider range of models.
Moreover, the regressions we noticed previously in ChatGPT 4.0 and Claude 2.1 models are no longer present from what I've tested so far.
ChatGPT 4.0:
Claude 2.1:
ChatGPT 3.5 and Claude Instant struggle to follow the instructions fully due to their smaller context windows, but I don't see a point of overriding them if we have other alternatives that are proven to work fine that the users can use.
Test plan
Pick any edit model in the edit menu before running the unit test command.