DESKTOP-RTLN3BA\$punk eec4db4a3b feat: Enhance LLM configuration and routing with model profile attachment ... - Added `_attach_model_profile` function to attach model context metadata to `ChatLiteLLM`. - Updated `create_chat_litellm_from_config` and `create_chat_litellm_from_agent_config` to utilize the new profile attachment. - Improved context profile caching in `llm_router_service.py` to include both minimum and maximum input tokens, along with token model names for better context management. - Introduced new methods for token counting and context trimming based on model profiles.		2026-03-10 18:18:59 -07:00
..
tools	feat: refactor agent tools management and add UI integration	2026-03-10 17:36:26 -07:00
__init__.py	feat: migrated to surfsense deep agent	2025-12-23 01:16:25 -08:00
chat_deepagent.py	feat: refactor agent tools management and add UI integration	2026-03-10 17:36:26 -07:00
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 LLM configuration and routing with model profile attachment	2026-03-10 18:18:59 -07:00
sandbox.py	feat: enhance caching mechanisms to prevent memory leaks	2026-02-27 17:56:00 -08:00
system_prompt.py	feat: refactor agent tools management and add UI integration	2026-03-10 17:36:26 -07:00
utils.py	inject tools at runtime	2025-12-20 18:35:39 +02:00