feat: auto-categorize merchants with AI when confidence is high#8
Merged
Conversation
Add AI-first categorization for unknown merchants: - NLPService.autoCategorizeMerchant() returns category + confidence - High confidence (>=0.8) with valid expense account: auto-categorize, skip manual flow, don't write to mapping file - Low confidence or invalid category: fall back to manual TG flow - Validate AI output against expense AccountName enum - Remove auto-writing empty mappings for unknown merchants - Update tests for async parse() and new AI categorization paths Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Background
Reduce manual intervention in the categorization flow.
Approach
AI-first categorization: mapping → AI auto (>=0.8 confidence) → manual TG flow.
Changes
Testing
40 tests pass (7 suites).
Code Review