fix(kg): robust LLM JSON parsing and extraction feedback#48
Merged
Conversation
- Strip markdown code fences from LLM output before JSON parsing
- Fix unescaped ASCII double quotes in CJK text (e.g. "灰潮事件")
- Support {"items": [...]} JSON wrapper format
- Add response_format hint for JSON-capable providers
- Switch to "all" filter after extraction so auto_approved results are visible
- Show success toast with extracted count after KG extraction
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address review findings: - Narrow Unicode range to CJK unified ideographs only (exclude fullwidth punctuation) - Move `import re` to module top level for consistency Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Owner
Author
|
No description provided. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
_safe_loads_listcouldn't handle markdown-fenced JSON or unescaped CJK quotes in LLM outputpendingbut all proposals wereauto_approvedChanges
kg_extraction.py): Strip markdown fences, fix unescaped ASCII quotes in CJK text, support{"items": [...]}wrapper, addresponse_formathintkg-panel.tsx): Switch to "all" filter after extraction, show success toast with countTest plan
🤖 Generated with Claude Code