Fix the error where Claude's chain of thought validation failed. #11
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Outdated suggestions cannot be applied.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.
Thank you for your project, it has been very helpful to me!
I am using the Claude-opus-4-5-thinking model, but my service provider has converted it into an OpenAI-compatible mode. I used this project for proxying, but I found that the current project doesn't handle the chain of thought very well, leading to errors in AI clients. So I made some modifications to prevent Claude model chain of thought validation failures.
Previously, the "text" field was used, which caused validation failures and errors, even though clients could see the content. This was because the content was placed in a box named "text" instead of "thinking". Now, Claude-related models can correctly return the chain of thought.
I'm not sure if these modifications will affect native OpenAI-compatible models, but for Claude models, the chain of thought content can now be correctly returned.
I hope this finding is helpful to you.