Skip to content

feat: implement persistent long-term memory for agents#149

Open
muscariello wants to merge 6 commits intomainfrom
130-add-long-term-memory-to-agents-to-create-a-long-term-scheduling-plan
Open

feat: implement persistent long-term memory for agents#149
muscariello wants to merge 6 commits intomainfrom
130-add-long-term-memory-to-agents-to-create-a-long-term-scheduling-plan

Conversation

@muscariello
Copy link
Member

Implements FileMemoryService to allow agents to persist sessions across restarts. Updates scheduler_agent, guide_agent, and tourist_agent to use this new logical memory service. Adds comprehensive tests for memory and dashboard components, significantly improving coverage. Resolves #130.

Adds FileMemoryService for persisting agent sessions, updates agents to use it, adds comprehensive tests for memory and dashboard, and updates the blog post with SLIM usage details.

Signed-off-by: Luca Muscariello <muscariello@ieee.org>
@codecov-commenter
Copy link

codecov-commenter commented Jan 14, 2026

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

This commit implements persistent session storage using DatabaseSessionService with aiosqlite for Scheduler, Guide, and Tourist agents. It also wires up FileMemoryService for long-term memory and upgrades project dependencies.

Signed-off-by: Luca Muscariello <muscariello@ieee.org>
Added comprehensive unit tests for core message schemas and CLI entry points for Scheduler, Guide, and Tourist agents. This significantly increases code coverage for agent modules and message handling.

Signed-off-by: Luca Muscariello <muscariello@ieee.org>
Added error handling and retry logic tests for guide and tourist CLIs, bringing coverage to 99% for both agents.

Signed-off-by: Luca Muscariello <muscariello@ieee.org>
…ory-to-agents-to-create-a-long-term-scheduling-plan

# Conflicts:
#	tourist_scheduling_system/pyproject.toml
#	tourist_scheduling_system/uv.lock
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.

Add long-term memory to agents to create a long-term scheduling plan.

2 participants