feat: L0/L1 tiered memory retrieval + redundancy compression + governance improvements#2
Merged
XuPeng-SH merged 2 commits intomatrixorigin:mainfrom Mar 12, 2026
Merged
Conversation
LeftHandCold
approved these changes
Mar 12, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What type of PR is this?
Which issue(s) this PR fixes
Fixes #
What this PR does / why we need it
Implements three major enhancements to Memoria's memory governance and retrieval system:
L0/L1 Tiered Retrieval — Session-scoped working/tool_result memories (L0) are now explicitly loaded and prepended to cross-session semantic/procedural/profile results (L1). Opt-in at the retriever level; controlled by the TieredMemoryLoader at the context assembly layer.
Redundancy Compression — Daily governance now detects and deactivates near-duplicate memories using vectorized L2² distance (numpy). Per-type grouping and configurable similarity threshold (default 0.95) avoid O(n²) DB pressure.
Governance Robustness — Fixed broken
_mark_daily_usermethod, added bounded marker keys (short user_ids kept readable, long ones hashed to 64-bit), improved incremental governance change detection.