v1.7.20 v1.7.19

Sep 22, 2026· 29 days ago

This release integrates CyberStrikeAI with the TypeSafe Jev engine to function as a Human-in-the-Loop (HITL) audit backend. It replaces chat model JSON output with a structured, parallel risk and authorization check mechanism. The system defaults to approving authorized pentesting while blocking destructive operations such as live system destruction, data loss, and configuration changes.

Sep 18, 2026· 1 month ago

Fixes a bug where the final reply was missing the audit report content when the Supervisor ended via exit with a short intro, by prioritizing the final_result field to ensure the full report is displayed.