fix: Clamp waypoint weights to [0, 1] range to prevent score corruption #56
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
Database may contain waypoint records with corrupted weights (e.g., 1.4 trillion instead of expected 0-1 range). These corrupted weights cause irrelevant memories to dominate search results due to massive score inflation in the hybrid scoring formula. This fix adds defensive clamping in two locations: 1. expand_via_waypoints() - when calculating expansion weights from neighbors 2. hsg_query() scoring loop - when using waypoint weights in final score calculation The clamping ensures that even if database contains invalid values, they won't corrupt query results. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
Member
|
Hey amihos, thanks for your interest in OpenMemory. I appreciate your pull request but it has failed the Build Test, please resolve the issues. |
Fixed TypeScript build errors by properly adding AWS_REGION, AWS_ACCESS_KEY_ID, and AWS_SECRET_ACCESS_KEY properties to the env configuration object. These properties were being referenced in embed.ts but were missing from cfg.ts. Changes: - Removed incorrect aws_model property with 3-argument str() call - Added AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY as individual properties with proper default values Fixes TypeScript errors: - cfg.ts(53,9): Expected 2 arguments, but got 3 - embed.ts: Property 'AWS_*' does not exist errors This is the same fix applied to PRs CaviraOSS#54 and CaviraOSS#55. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
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
expand_via_waypoints()andhsg_query()scoring loopProblem
During debugging, we discovered that some waypoint records in the database had corrupted weights (e.g.,
1.4 trillioninstead of the expected0-1range). This caused irrelevant memories to rank #1 in search results because the hybrid scoring formula:Would be dominated by the massive waypoint weight, effectively ignoring semantic similarity.
Solution
Added
Math.min(1.0, Math.max(0, weight || 0))clamping in two locations:This ensures that even if the database contains invalid values, they won't corrupt query results.
Test plan
🤖 Generated with Claude Code