Wrapped googleai decoding logic in a pcall to prevent crash on stream termination#294
Open
Konkord360 wants to merge 1 commit intoRobitx:mainfrom
Open
Wrapped googleai decoding logic in a pcall to prevent crash on stream termination#294Konkord360 wants to merge 1 commit intoRobitx:mainfrom
Konkord360 wants to merge 1 commit intoRobitx:mainfrom
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When using gemini-3-pro-preview the API stream sends a final chunk (likely usage metadata or [DONE] signal) that does not match the expected
"text":...fragment format.The current implementation manually wraps the line in braces:
vim.json.decode("{" .. line .. "}").When the final non-conforming chunk arrives,vim.json.decodethrows an error (Expected object key string but found T_OBJ_END), crashing the plugin callback just as the response finishes.Wrapping the decoding logic in a
pcall(similar to the ollama integration) solves the issue and the chat integration works flawlessly.