fix: strip thinking tags before all JSON parse strategies#209
Open
haosenwang1018 wants to merge 1 commit intoHKUDS:mainfrom
Open
fix: strip thinking tags before all JSON parse strategies#209haosenwang1018 wants to merge 1 commit intoHKUDS:mainfrom
haosenwang1018 wants to merge 1 commit intoHKUDS:mainfrom
Conversation
…oning model output
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #159
When using reasoning models (qwen2.5-think, deepseek-r1, etc.), the
<think>...</think>tags were only stripped in_extract_all_json_candidates(), meaning the regex fallback strategy (_extract_fields_with_regex) still operated on the raw response including thinking content. This could cause it to extract content from the thinking section rather than the actual analysis.This fix moves the think-tag stripping to the top of
_robust_json_parse()so all downstream strategies work with clean model output.