mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-04-10 04:52:40 +00:00
* no need post tool reflection on native tools * refactor: update prompt generation to prevent thought leakage - Modified the prompt structure to ensure agents without tools use a simplified format, avoiding ReAct instructions. - Introduced a new 'task_no_tools' slice for agents lacking tools, ensuring clean output without Thought: prefixes. - Enhanced test coverage to verify that prompts do not encourage thought leakage, ensuring outputs remain focused and direct. - Added integration tests to validate that real LLM calls produce clean outputs without internal reasoning artifacts. * dont forget the cassettes