v1.6.32
AIPentest/CyberStrikeAIv1.6.32Jun 8, 2026by Ed1s0nZ
AI Summary
Fixes a bug where disabling model reasoning caused 400 errors with DeepSeek V4 models in the Plan-Execute workflow by explicitly disabling thinking parameters.
Key Highlights
- Fixes Plan-Execute 400 errors when reasoning is set to Off
- Handles DeepSeek V4 default thinking behavior
- Removes provider-specific detection logic for the Eino path
Full Release Notes
修复了 Eino 路径下「模型推理 = 关闭」时仍可能触发 DeepSeek V4 默认 thinking 的问题：原先 off 仅表示不下发参数，但 deepseek-v4-flash 等模型默认开启 thinking，与 Plan-Execute 的强制 tool_choice 冲突并返回 400；现改为在 off 时统一显式下发 {"thinking": {"type": "disabled"}}，无需再按 DeepSeek 线路单独检测。
---
Fixed Plan-Execute 400 errors when reasoning was set to Off: previously Off meant omitting thinking parameters, but DeepSeek V4 models default to thinking enabled, which conflicts with Plan-Execute’s forced tool_choice. Off now always sends {"thinking": {"type": "disabled"}} on the Eino path, with no provider-specific detection required.