插件
浏览、筛选并安装 DeepSeek-Harness 插件。
共 99 个插件
dsh-reasoning-effort
lunfengchen/dsh-reasoning-effort
Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.
dsh-model-router
neptune810/dsh-model-router
按步骤设置 DeepSeek flash 模型的思考等级:短小的廉价请求关闭思考,普通请求用 low,工程类工作用 high,只有反复出现工具失败才继续升档。模型本身不会改变,max 档需要手动开启。
dsh-zentao-mark-effort
bakeham/dsh-zentao-mark-effort
DeepSeek Harness bundle for ZenTao MCP, task/bug workflows, reports, and verified formal effort recording.
dsh-reasoning
bowugit/dsh-reasoning
Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu
dsh-sub-cli
dingminhua/dsh-sub-cli
Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.
dsh-reasoning-ruler
zisen123/dsh-reasoning-ruler
A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.
dsh-reasoning-tiers
1069137617/dsh-reasoning-tiers
在 llm-pi-ai 设置节为第三方模型提供商补齐推理档位(reasoning effort)声明,让 DSH 自带的思考强度选择器对 pi-ai 目录之外的模型真正可用。
dsh-model-selector-search
arcaneorion/dsh-model-selector-search
搜索增强的会话模型选择器:两段式宽松匹配(先归一化子串,未命中再退子序列,glm53 命中 GLM-5.3、ds 命中 DeepSeek)、近七天成功调用过的供应商置顶,推理档位面板记住每个模型上次显式选择的档位。
dsh-context-budget
zpis666/dsh-context-budget
在模型设置页为每个 pi-ai 路由新增上下文窗口与压缩阈值字段,并在输入框右下角按厂商提供思考强度选择器,写入 llm-pi-ai 容量、reasoningEfforts 与 compaction-basic 补丁行。
dsh-effort-slider
smailpang/dsh-effort-slider
在原位置将 DSH 原生推理等级选项替换为可拖动的 Off、Low、High、Max 滑块,并保留官方模型选择流程。
dsh-model-reasoning-defaults
xht-code/dsh-model-reasoning-defaults
DSH (DeepSeek Harness) 插件:为每个 LLM 模型配置默认推理等级(reasoningEffort),并在请求进入底层调用链前按路由规则自动补齐
dsh-model-fix
tikaflow/dsh-model-fix
为非官方(自定义)提供方的模型自动填充推理级别、最大上下文、输出上限与图片模态,数据来自 models.dev。同时提供了设置卡片以控制插件行为。
dsh-task-effort
zhangzhenwen1/dsh-task-effort
根据任务自动调整模型推理档位(off/low/high/max):任务分类判定、\[effort=...] 显式标记、轮内出错升级、DeepSeek 高峰计价时段自动限档省钱并显示切换倒计时、GUI 手动选择优先。
dsh-codex-harness
bainianlaoyao/dsh-codex-harness
面向 DeepSeek Harness 上 GPT 模型的 Codex 风格编码工具与 agent 预设:exec_command、write_stdin、apply_patch、view_image,以及 OpenAI Chat Completions 与 Responses API 两条路由,并桥接 DSH 原生的计划、提问、审批与压缩。长命令注册为 DSH 后台作业,输出首尾有界,可用 job_output 读取;每种子代理类型可独立指定 Preset、Provider、Model 与 Reasoning effort。
dsh-reasoning-options
scorp1o117/dsh-reasoning-options
通过 DSH 设置为自定义 pi-ai 模型补充缺失的推理强度声明,启用原生强度选择器,并自动处理后续添加的模型。
dsh-model-capabilities
lylarcher/dsh-model-capabilities
一个DSH插件,为自定义模型配置输入类型(input)、推理模式(reasoningEfforts)
dsh-rich-indexing
savageops/dsh-rich-indexing
分级压缩中枢:把单一的 80% 压缩阈值换成可配置的阶梯(默认 30/50/70/90),逐级加强压缩力度;每次检查点都折叠入确定性关键词索引,让事实跨周期累积;摘要走模型链——主模型加最多 3 个回退,各自独立推理档位。附带 Compaction 模块子标签页与设置卡片;关闭插件始终恢复原版压缩。
dsh-better-model-setting
hiseax/dsh-better-model-setting
替代官方「模型」设置页:提供方生命周期管理、每模型思考档位、重试覆盖、拖动排序与上游模型同步。
dsh-llm-capabilities
bamboostrip/dsh-llm-capabilities
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
dsh-model-search-select
manuelgb00/dsh-model-search-select
Searchable model selector for DeepSeek Harness (DSH) web: a faithful fork of the native model seat (Model/Effort, provider-grouped list, reasoning effort) with a search box at the top of the model list that filters while you type.
dsh-more-models-thinking-level
henta111/dsh-more-models-thinking-level
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
oh-my-dsh-slim (npm-package)
ninipa/oh-my-dsh-slim
专家子代理委派预设(orchestrator + 5 角色),安装即自动播种——后台优先派发+完成通知,JSON 驱动模型/effort/工具权限,subagent_result 只读取回结果,调研角色带 MCP。
dsh-model-selector
deepvite/dsh-model-selector
DeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.
dsh-reasoning
lanqin996/dsh-reasoning
Configure model input capabilities and reasoning efforts for DeepSeek Harness