Skip to content
dsh.fish

Browse

224 results

Bundle

dsh-subagent-setting

Configure the default provider, model and reasoning effort for new subagents from the Web settings page; optionally apply changes to existing idle subagents. · DSH 插件:在设置页可视化配置 subagent 默认的提供商、模型与思考等级,新创建的 subagent 立即生效,可选的让空闲 subagent 也跟随新设置。

marshfolx1
Bundle

dsh-warm-minimal

DSH 温暖极简模式:官方 minimal 等价 composition,加一条固定工作目录确认首轮。

sch2461
Bundle

dsh-matrix-skin

Black-first Matrix hacker skin for DeepSeek Harness (DSH) Web with efficient displayed-text code rain and readable provider reasoning.

emeryxu1-blip1
Bundle

dsh-matrix-think

Matrix rain for expanded thinking in DeepSeek Harness Web

me93-ghb1
Bundle

dsh-custom-reasoning

在 Settings 面板中为自定义 pi-ai 模型编辑推理等级(reasoningEfforts),支持多选、拖拽、复制粘贴,自动保存。

gao-gao-zai1
Bundle

dsh-delegation-suite

Ranked subagent delegation for DeepSeek Harness: role-based model routing with failover, per-route reasoning effort, fork delegation, transparent model labels, and a visual route editor in Settings.

wenheguo21
Bundle

dsh-model-memory

DSH 自定义模型思考等级管理、渠道重试策略与偏好记忆插件:原生设计语言、全档位思考配置、渠道级重试控制与无感隔离式跨会话偏好记忆。

Mutx1631
Bundle

dsh-zh-reasoning

DeepSeek Harness 插件:让模型的思考(reasoning)与最终回答默认使用简体中文。A Chinese-first plugin that makes DeepSeek Harness reason and answer in Simplified Chinese by default.

zhy2018105761
Bundle

dsh-devtools

DevTools for DeepSeek Harness web: read-only Agent Runtime Trace — turn/step execution timeline, model latency (TTFT/decode), tool-call durations, retries, hook and turn end reasons. Metadata-first, durable events only, zero behavior modification.

izz-BLUE1
Bundle

dsh-reasoning-level

DeepSeek Harness 统一推理等级插件:一个 llm-reasoning 设置项动态配置 DSH 所有模型的默认推理等级(思考等级)——自动为手写声明的模型补齐推理能力、按路由设置默认等级(仅当全部模型支持)、同步 DeepSeek 官方路由,改设置即生效。

peterwangze1
Bundle

dsh-effort-config

第三方模型思考努力度配置(DeepSeek Harness 插件):在设置页为模型声明 reasoningEfforts 档位、路由默认档位与 Anthropic token 预算,写入 llm-pi-ai 命名空间;档位调节复用原生模型框 Effort 面板。

benzhoupo1
Bundle

@lbryany/dsh-codebuddy

CodeBuddy OAuth, dynamic models, and reasoning controls for DeepSeek Harness

Lbryany1
Bundle

dsh-model-capabilities

DSH web plugin: per-model thinking-intensity tiers, provider default reasoning, modalities, gateway compat switches and static custom request headers for custom llm-pi-ai providers, edited inside the official Models settings card. 模型能力:思考强度档位 / 默认思考强度 / 支持模态 / 兼容开关 / 静态自定义请求头。

fuzz1og1
Bundle

dsh-llm-capabilities

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

bamboostrip1
Bundle

dsh-model-extension

DeepSeek Harness plugin: the Models+ settings page — a fully plugin-owned model/provider UI with per-model extension fields (reasoning efforts, input modalities, compat flags) and models.dev metadata prefill

lovezi01
Bundle

dsh-llm-openai-completions

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.

drscrewdriver1
Bundle

@domitor-syh/dsh-ui-skin-switcher

Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel

domitor-syh1
Bundle

dsh-plugin-thinking-size

Live reasoning-token badge — Think(5.2K) — on every Think disclosure row of the DSH web UI, ticking while streaming · 在 web 界面 Think 行标题后实时显示思考内容 token 数的 DeepSeek Harness 插件

focksor1
Bundle

dsh-token-speed

DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

gbeta1
Bundle

dsh-deepseek-relay

DeepSeek 中转站(OpenAI 兼容网关)思考强度适配插件:让 UI 出现 Off/Low/High/Max 推理等级选项,并按中转站格式发送 reasoning_effort / thinking

LXFLGH1
Bundle

dsh-subagent

Named subagent profiles with configurable model routing and reasoning for DeepSeek Harness

xie-tj1