Skip to content

Conversation

@Nsuccess
Copy link

Closes #243

  • Add ToolCallResult model for tracking tool execution history
  • Add 'tool' to MemoryType literal
  • Add when_to_use field for retrieval hints
  • Add metadata field for type-specific data
  • Add tool_calls field for tool execution history
  • Add get_tool_statistics() method for success_rate, avg_time_cost, avg_score
  • Add tool.py prompt for tool memory extraction
  • Update repository interfaces and implementations (inmemory, postgres)
  • Add 14 unit tests for Tool Memory feature

Nsuccess and others added 3 commits January 16, 2026 11:23
Closes NevaMind-AI#243

- Add ToolCallResult model for tracking tool execution history
- Add 'tool' to MemoryType literal
- Add when_to_use field for retrieval hints
- Add metadata field for type-specific data
- Add tool_calls field for tool execution history
- Add get_tool_statistics() method for success_rate, avg_time_cost, avg_score
- Add tool.py prompt for tool memory extraction
- Update repository interfaces and implementations (inmemory, postgres)
- Add 14 unit tests for Tool Memory feature
@evan-ak
Copy link
Collaborator

evan-ak commented Jan 20, 2026

Thank you very much for your contribution. We are actively working on merging this feature into MemU.

Given that there are multiple PRs introducing various kinds of fields to the memory item, and that some of them are exclusively used by specific memory types or applications, we’ve decided to consolidate these attributes into a single "extra" field to keep the memory item’s structure clear and concise.

As a result, we are still working on a few minor revisions to the current commits and will proceed with the merge once these adjustments are complete.

Thanks again for the great work!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[2026NewYearChallenge] Specialized Memory Types with Tool Learning

2 participants