This repository was archived by the owner on Aug 1, 2025. It is now read-only.
Add a test for autoedit anomalies #8155
Draft
Conversation
This file contains hidden or 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
mkondratek
force-pushed
the
mkondratek/test/point3d
branch
from
fd353c2 to
2683e6a
Compare
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
See https://linear.app/sourcegraph/issue/CODY-6178/investigate-inconsistent-behavior-in-auto-edits-feature.
Problem
We have noticed a strange behavior recently: https://sourcegraph.slack.com/archives/C05AGQYD528/p1750845105385289
We've observed that in some cases, the
insertTextandoriginalTextfields of the autoedit completion result are inconsistent. This can lead to duplicated or malformed suggestions in the editor.We suspect the issue originates from the LLM response itself, rather than from any post-processing on our end.
SolutionReproDescriptionThis PR introduces a test case designed to help us reproduce the issue more reliably. By running it repeatedly, we hope to capture examples of the faulty behavior and better understand the root cause.Initially, I've tried to run the test repeatedly. I have never managed to get the incorrect result. Then I played with the params and responses that I caught in a debug session. Based on that it seems to me that the problem is related to the bad response (not to the post-processing) issues.
Test plan
tbd