Bundle
dsh-reasoning-settings
Reasoning effort settings and per-call subagent model routing for DeepSeek Harness custom providers
JuneLearn5
4 results
Reasoning effort settings and per-call subagent model routing for DeepSeek Harness custom providers
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens
Multi-agent orchestration for DeepSeek Harness: delegate, adversarial review, diverse explore, background runs + converge. One prompt. A team of agents.
常驻视觉服务:直连视觉模型(默认 opencode-go/minimax-m3,回退 zai-coding-cn/glm-4.6v)。describe_image / subagent_vision 工具 + 粘贴图片自动转译(llm/stream 钩子)+ 输入框视觉状态小胶囊与详情页(活动日志:指令/思考过程/输出)。零子代理、零 agent 上下文开销,按会话记忆窗支持视觉追问与验收。