1.15.24

תקציר מקורי באנגלית<h2>What's Changed</h2> <h3>Features</h3> <ul> <li>Add crewai eval to print a markdown brief when run by an agent</li> <li>Queue relevant background replies</li> <li>Add experimental turn and reply identities</li> <li>Add Oracle Integrations</li> <li>Add experimental job lifecycle and runner</li> <li>Add crewai eval --models, and llm_overlay to swap models as well as roles</li> </ul> <h3>Bug Fixes</h3> <ul> <li>Fix train filename error message in CLI</li> <li>Allow a start step to re-run on the events it listens to</li> <li>Let human_feedback emit steps expose the review in outputs</li> <li>Ensure crewai eval exits with code 1 unless the gate passed and prompt to log in when nothing was traced unattended</li> <li>Report tracing sent usage from the grant exporter</li> <li>Address multiple d