dsh-model-switch
DSH plugin: choose models for subagents and plan execution separately / 为子代理和计划执行选择更合适的模型
18 results
DSH plugin: choose models for subagents and plan execution separately / 为子代理和计划执行选择更合适的模型
novel-solo helper for DeepSeek Harness: a subagent-count setting (1-12) card in the Settings → Plugins panel, persisted to disk and consumed by the novel-solo preset to cap parallel subagent fan-out.
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
GrayPrint — live reasoning-style fingerprints for the DeepSeek Harness web chat. Compares grayscale-vs-current writing style by internal reasoning paragraphs and independently tracks Let me exploratory openers versus We need planning openers.
多 agent 团队协作:并行调试、并行功能开发、任务协调、沟通协议、团队构成。受 wshobson/agents(38k★ MIT)启发。
Readable thinking display for DeepSeek Harness: live per-paragraph summaries of the reasoning stream, rendered in the chat history where the 'Think' row is, with a user-chosen summary model (thinking disabled on summary requests).
Two-level fold for DeepSeek Harness chat: collapse think+tools as a process, then fold tool rows separately. Official cards stay intact. 聊天主视图两层折叠:过程一层、工具一层,不替换官方卡片。
编程范式
Map-reduce council of subagents for the DeepSeek Harness: one task fans out to independent members, their findings are deduplicated, verified by a separate panel, and reduced to a quorum report
Tune the conversation area: font, width, line height, paragraph spacing, and Cursor-like sticky user prompts. 对话区界面设置:字号 / 字体 / 行距 / 段距 / 宽度 / 滚动钉住本轮用户消息。
动态滚动窗口子代理任务池:一次调用跑完整批独立任务,内部滚动补位,后台运行不阻塞主对话
并行功能开发:文件所有权、接口契约、避免冲突、集成策略(垂直切片 vs 水平分层)。受 wshobson/agents(38k★ MIT)启发。
巴拉圭国家
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness
Fixes malformed tool-call arguments (nested {"arguments":{…}} wrappers, wrapper-key aliases, param-key aliases) at the llm/stream seam — repairs execution, persistence and history replay in one place. 修复模型产出的畸形工具参数。
DeepSeek Harness bundle: a bounded, de-confounded hyperparameter sweep ledger with a research-campaign playbook skill and paper-ready report tables
Ships a skill that tells the agent when to delegate work to subagents instead of doing it inline, how to fan several out in parallel, and how to check what they returned.