fix(plugins/ai-proxy): the request will panic if the model name with /
#14805
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
For Gemini/VertexAI, it concats the model name in the url, so it will return NOT FOUND error if the model name wrongly brings the provider prefix like `google/gemini-2.5-flash`. And it will raise an error while decoding the empty string with `cjson` instead of `cjson.safe`.
There was a problem hiding this comment.
Pull request overview
This PR fixes a panic issue in the ai-proxy plugin when model names contain forward slashes (e.g., "google/gemini-2.5-flash"). When such model names are used with Gemini/VertexAI providers, they are concatenated into the URL path, resulting in invalid API requests that return empty or malformed responses. The fix migrates from the regular cjson library to cjson.safe, which returns errors instead of throwing exceptions, preventing service panics when decoding these empty responses.
Key Changes:
- Switched from
cjsontocjson.safeto handle JSON decode failures gracefully - Added explicit error handling with logging for decode failures
- Used nil-safe access pattern for the decoded response table
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
Author
|
@oowl @StarlightIbuki Would you mind taking a look this? |
git-hulk
force-pushed
the
fix/panic-when-model-is-invalid
branch
from
fc07f17 to
39b9502
Compare
StarlightIbuki
approved these changes
Dec 16, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Summary
For Gemini/VertexAI, it concats the model name in the url, so it will return NOT FOUND error if the model name wrongly brings the provider prefix like
google/gemini-2.5-flash. And it will raise an error while decoding the empty string withcjsoninstead ofcjson.safe.Checklist
changelog/unreleased/kongorskip-changeloglabel added on PR if changelog is unnecessary. README.md