feat & refactor: add search function feature to test scheduler on a modified locome benchmark, and slightly change the logic of query consume and query monitors#204
Merged
CaralHsi merged 6 commits intoMemTensor:devfrom Aug 1, 2025
Conversation
…odified locome benchmark, and slightly change the logic of query consume and query monitors
…nitialize working memories (logically uneccessary). change the function parameters of search as the function input info as an addition
tangg555
changed the title
tianxing02
pushed a commit
to tianxing02/MemOS
that referenced
this pull request
Feb 24, 2026
…odified locome benchmark, and slightly change the logic of query consume and query monitors (MemTensor#204) * feat & refactor: add search function feature to test scheduler on a modified locome benchmark, and slightly change the logic of query consume and query monitors * refactor: not showing userinput to working memory * fix bugs: fix a bug in retriever, and add new auth info for neo4j db * fix bugs & new feat: fix bugs in mem_scheduler examples, and remove initialize working memories (logically uneccessary). change the function parameters of search as the function input info as an addition --------- Co-authored-by: CaralHsi <caralhsi@gmail.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Summary: (summary)
Here's a concise description of the code changes:
Configuration Enhancements:
Added GraphDB connection parameters (URI, user, password, db_name, auto_create) across multiple scheduler initialization files
Scheduler Core Improvements:
Added current_mem_cube tracking in base scheduler
Refactored memory transformation with query keywords parameter
Removed deprecated initialize_working_memory_monitors method
Enhanced memory update logic with better error handling
Monitoring System Upgrades:
Restructured query monitors as nested dictionaries (user_id → mem_cube_id)
Implemented thread-safe registration with double-checked locking
Added detailed logging for threading operations
Improved memory monitor initialization logic
Search Functionality:
Added fine-grained search method (TreeTextMemory_FINE_SEARCH_METHOD)
Enhanced search with info parameter for history tracking
Improved search result handling in test scheduler
Prompt Engineering:
Refined retrieval decision framework prompts
Clarified output specifications for evidence tracking
Testing:
Removed obsolete test cases
Focused on core functionality validation
These changes improve thread safety, monitoring granularity, and search flexibility while maintaining backward compatibility.
Fix: #(issue)
Docs Issue/PR: (docs-issue-or-pr-link)
Reviewer: @(reviewer)
Checklist: