Repository navigation
Reduce repeated recall database work - #9
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Recall repeats graph visibility queries, rebuilds the concept search corpus for each query, and loads evidence that its prompt never uses. Batch those reads, reuse the corpus within each recall, and prefilter keyword matches through the existing text-search index. Full concept reads retain their evidence. No new service or dependency.
Validation: 110 targeted tests passed. Across eight solveos questions with three paired repeats, local median fell from 1.170s to 0.962s; all 24 prompts and ordered memory selections matched, and all 24 pairs were faster. Mercury and background sync excluded. Median SQL count fell from 163 to 43.
Bumps the package to 0.1.66.