Skip to content

Conversation

@abrookins
Copy link
Collaborator

@abrookins abrookins commented Oct 15, 2025

Changes

The long_term_memory_strategy parameter was documented but not exposed in client methods or the MCP server.

Fixed

  • Added long_term_memory_strategy parameter to get_or_create_working_memory() and get_or_create_working_memory_tool() client methods
  • Added long_term_memory_strategy parameter to MCP set_working_memory() tool
  • Added MemoryStrategyConfig model to client models package
  • Fixed documentation example that referenced non-existent thread_aware strategy and used incorrect field names

Documentation

  • Updated docs/working-memory.md with correct examples showing strategy and config fields
  • Added examples for all available strategies: discrete, summary, preferences, custom

Testing

  • Added 4 tests for client method support
  • Added 5 tests for MCP tool support
  • All 419 existing tests pass

Version

  • Bumped client version to 0.13.0

- Add long_term_memory_strategy parameter to client get_or_create_working_memory() and get_or_create_working_memory_tool()
- Add long_term_memory_strategy parameter to MCP set_working_memory() tool
- Add MemoryStrategyConfig model to client models
- Fix documentation example using non-existent 'thread_aware' strategy and incorrect field names
- Bump client version to 0.13.0
Copilot AI review requested due to automatic review settings October 15, 2025 22:19
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

Adds support for the long_term_memory_strategy parameter to client methods and MCP tools, enabling users to configure memory extraction strategies for promoting working memory to long-term storage.

  • Added the MemoryStrategyConfig model to the client package with strategy types (discrete, summary, preferences, custom)
  • Enhanced client methods get_or_create_working_memory and get_or_create_working_memory_tool to accept strategy configuration
  • Extended MCP set_working_memory tool to support strategy parameter with proper documentation and examples

Reviewed Changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.

Show a summary per file
File Description
agent-memory-client/agent_memory_client/models.py Added MemoryStrategyConfig model and long_term_memory_strategy field to WorkingMemory
agent-memory-client/agent_memory_client/client.py Added strategy parameter support to client methods with examples
agent-memory-client/agent_memory_client/init.py Bumped client version to 0.13.0
agent_memory_server/mcp.py Added strategy parameter to MCP set_working_memory tool with documentation
docs/working-memory.md Updated documentation with correct strategy examples and field names
tests/test_client_strategy_support.py Added comprehensive client method tests for strategy support
tests/test_mcp_strategy_support.py Added comprehensive MCP tool tests for strategy support

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

@abrookins abrookins merged commit eb87d44 into main Oct 16, 2025
14 checks passed
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.

2 participants