Files
crewAI/docs/ko
João Moura 09e9229efc New Memory Improvements (#4484)
* better DevEx

* Refactor: Update supported native providers and enhance memory handling

- Removed "groq" and "meta" from the list of supported native providers in `llm.py`.
- Added a safeguard in `flow.py` to ensure all background memory saves complete before returning.
- Improved error handling in `unified_memory.py` to prevent exceptions during shutdown, ensuring smoother memory operations and event bus interactions.

* Enhance Memory System with Consolidation and Learning Features

- Introduced memory consolidation mechanisms to prevent duplicate records during content saving, utilizing similarity checks and LLM decision-making.
- Implemented non-blocking save operations in the memory system, allowing agents to continue tasks while memory is being saved.
- Added support for learning from human feedback, enabling the system to distill lessons from past corrections and improve future outputs.
- Updated documentation to reflect new features and usage examples for memory consolidation and HITL learning.

* Enhance cyclic flow handling for or_() listeners

- Updated the Flow class to ensure that all fired or_() listeners are cleared between cycle iterations, allowing them to fire again in subsequent cycles. This change addresses a bug where listeners remained suppressed across iterations.
- Added regression tests to verify that or_() listeners fire correctly on every iteration in cyclic flows, ensuring expected behavior in complex routing scenarios.
2026-02-15 04:57:56 -03:00
..
2026-02-15 04:57:56 -03:00
2025-09-05 17:40:11 -04:00
2025-09-05 17:40:11 -04:00
2026-02-15 04:57:56 -03:00
2026-01-05 15:30:21 -08:00
2025-08-12 15:58:12 -07:00
2025-09-05 17:40:11 -04:00