Conversation
- Improved in-memory rate limiting by evicting timestamps outside the current window and cleaning up empty keys. - Updated LLM router service to cache context profiles and avoid redundant computations. - Introduced cache eviction logic for MCP tools and sandbox instances to manage memory usage effectively. - Added garbage collection triggers in chat streaming functions to reclaim resources promptly.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![recurseml[bot]](https://avatars.githubusercontent.com/in/1054195?s=60&v=4){kind=small}
There was a problem hiding this comment.
Review by RecurseML
🔍 Review performed on 4105bd0..cc0d8ad
✨ No bugs found, your code is sparkling clean
✅ Files analyzed, no issues (7)
• surfsense_backend/app/agents/new_chat/llm_config.py
• surfsense_backend/app/agents/new_chat/sandbox.py
• surfsense_backend/app/agents/new_chat/tools/mcp_tool.py
• surfsense_backend/app/app.py
• surfsense_backend/app/services/llm_router_service.py
• surfsense_backend/app/services/llm_service.py
• surfsense_backend/app/tasks/chat/stream_new_chat.py
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Motivation and Context
FIX #
Screenshots
API Changes
Change Type
Testing Performed
Checklist
High-level PR Summary
This PR enhances caching mechanisms across the application to prevent memory leaks and reduce memory growth. The core changes introduce a cached singleton pattern for
ChatLiteLLMRouterinstances to avoid repeated initialization overhead, add size limits and eviction strategies to various caches (MCP tools cache, sandbox cache, rate limit cache), and trigger explicit garbage collection after chat stream completion to reclaim objects with circular references. Theget_auto_mode_llm()function now returns cached router instances keyed by streaming mode, and the router's context profile computation is cached globally to avoid repeated model info lookups.⏱️ Estimated Review Time: 30-90 minutes
💡 Review Order Suggestion
surfsense_backend/app/services/llm_router_service.pysurfsense_backend/app/services/llm_service.pysurfsense_backend/app/agents/new_chat/llm_config.pysurfsense_backend/app/agents/new_chat/tools/mcp_tool.pysurfsense_backend/app/agents/new_chat/sandbox.pysurfsense_backend/app/app.pysurfsense_backend/app/tasks/chat/stream_new_chat.py