SurfSense/surfsense_backend/app/agents/new_chat
DESKTOP-RTLN3BA\$punk f4b2ab0899 feat: enhance caching mechanisms to prevent memory leaks
- 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.
2026-02-27 17:56:00 -08:00
..
tools feat: enhance caching mechanisms to prevent memory leaks 2026-02-27 17:56:00 -08:00
__init__.py feat: migrated to surfsense deep agent 2025-12-23 01:16:25 -08:00
chat_deepagent.py feat: add performance logging middleware and enhance performance tracking across services 2026-02-27 16:32:30 -08:00
checkpointer.py feat: implement connection pooling for AsyncPostgresSaver in checkpointer 2026-02-05 17:32:43 -08:00
context.py organize deepagent codebase 2025-12-20 18:35:39 +02:00
llm_config.py feat: enhance caching mechanisms to prevent memory leaks 2026-02-27 17:56:00 -08:00
sandbox.py feat: enhance caching mechanisms to prevent memory leaks 2026-02-27 17:56:00 -08:00
system_prompt.py refactor: remove security notes from system prompt 2026-02-25 01:56:16 -08:00
utils.py inject tools at runtime 2025-12-20 18:35:39 +02:00