fix: handle GitHub Copilot gpt-4.1 model ID response bug #6106
+184
−0
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
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
- Added debug logging to track VS Code LM API responses for Copilot models - Implemented detection for when model ID is returned instead of actual content - Skip model ID chunks and continue processing valid content - Throw descriptive error when only model ID is returned with no valid content - Added comprehensive tests for the workaround Fixes #6105
dosubot
bot
added
size:L
hannesrudolph
added
the
Issue/PR - Triage
|
il test the fixes tommorow |
|
This could help debug but debug changes shouldn't be merged into main |
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Outdated suggestions cannot be applied.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.
This PR fixes issue #6105 where GitHub Copilot's gpt-4.1 model returns only the model ID ("copilot/gpt-4.1") instead of generating actual AI responses.
Problem
When using the VS Code Language Model API with GitHub Copilot's gpt-4.1 model, users were seeing "copilot/gpt-4.1" as the response instead of actual AI-generated content. This appears to be a bug in either the VS Code Language Model API or the GitHub Copilot extension.
Solution
Testing
Notes
This is a workaround for what appears to be an upstream bug in the VS Code Language Model API or GitHub Copilot extension. The fix ensures users get a clear error message instead of seeing the model ID as the response.
Fixes #6105
Important
Fixes GitHub Copilot gpt-4.1 model bug by skipping model ID responses and throwing errors for invalid content in
vscode-lm.ts.vscode-lm.ts, added logic to detect and skip chunks containing only the model ID for GitHub Copilot's gpt-4.1 model.vscode-lm.spec.tsto verify handling of model ID responses, including variations in model ID patterns.vscode-lm.tsto track responses and identify when model ID is returned as content.This description was created by
for 9c8b9e4. You can customize this summary. It will automatically update as commits are pushed.