CrewAI 发布 1.15.24：新增 eval 命令与 Oracle 集成

AI 摘要

CrewAI 发布 1.15.24 版本，新增 crewai eval 命令可在由 agent 运行时打印 markdown 简报，并支持 --models 与 llm_overlay 切换模型和角色。该版本还加入实验性的 turn/reply 身份、job 生命周期与 runner，以及 Oracle 集成，同时修复 CLI 训练文件名报错、human_feedback 输出等问题并更新依赖。

正文节选

## What's Changed ### Features - Add crewai eval to print a markdown brief when run by an agent - Queue relevant background replies - Add experimental turn and reply identities - Add Oracle Integrations - Add experimental job lifecycle and runner - Add crewai eval --models, and llm_overlay to swap models as well as roles ### Bug Fixes - Fix train filename error message in CLI - Allow a start step to re-run on the events it listens to - Let human_feedback emit steps expose the review in outputs

发布时间：2026-10-08 01:39

抓取时间：2026-10-08 02:23

来源机构：CrewAI