mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-04-26 09:16:22 +02:00
- 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. |
||
|---|---|---|
| .. | ||
| stream_new_chat.py | ||