6 Commits

Author	SHA1	Message	Date
Gui Vieira	7696b45fc3	Fix tool usage (#925) ... * Fix tool usage * new tests --------- Co-authored-by: João Moura <joaomdmoura@gmail.com>	2024-07-15 17:13:35 -03:00
João Moura	b856b21fc6	updating tests	2024-03-03 20:54:15 -03:00
João Moura	e9aa87f62b	Updating tests	2024-02-20 10:40:37 -03:00
João Moura	b21191dd55	updating tests	2024-02-13 01:50:12 -08:00
João Moura	d4c21a23f4	updating all cassettes	2024-02-10 00:55:40 -08:00
João Moura	af9e749edb	Adding tool caching a loop execution prevention. (#25) ... * Adding tool caching a loop execution prevention. This adds some guardrails, to both prevent the same tool to be used consecutively and also caching tool's results across the entire crew so it cuts down execution time and eventual LLM calls. This plays a huge role for smaller opensource models that usually fall into those behaviors patterns. It also includes some smaller improvements around the tool prompt and agent tools, all with the same intention of guiding models into better conform with agent instructions.	2023-12-29 22:35:23 -03:00