feat(core): add topic-aware boundary recall - #76
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Recall now matches complete topic names as well as entities and rejects embedded ASCII token matches:
Karpathyno longer matchesPATH, while用age加密still matchesage. Boundary filtering and deduplication occur before the five-candidate limit, preserving newest-first ordering and existing access scope. README, agent guidance, and MCP descriptions document the literal matching contract.Validation: full workspace/all-target/all-feature tests, build, check, clippy, fmt, and cargo deny passed; independent Standards and Spec review found no merge blockers. Focused core and MCP recall tests cover topic-only discovery, token edges, repeated occurrences, scope, and strict output schemas. No dependencies or output-schema changes.
A one-shot isolated 512-note comparison measured 4.5 ms for the old query and 9.3 ms for the new path; this is a synthetic observation, not a production latency guarantee.