Skip to content
dsh.fish

Browse

204 results

Bundle

dsh-provider-pro

Custom provider enhancements: User-Agent override, reasoning-level switching, and image-input declaration for DSH custom providers · 自定义供应方增强：UA 覆盖、推理等级切换、图片输入声明。

Mortal520
Bundle

dsh-model-ocean-selector

A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.

jiaoTaiLang404
Bundle

dsh-llm-mimo

Xiaomi MiMo v2.5 adapter for DeepSeek Harness LLM seam with thinking chain support

dfhxxc666
Bundle

dsh-reasoning-options

DeepSeek Harness 推理强度与网关增强插件：自动为 llm-pi-ai 下所有模型补齐推理强度档位（off→max 全七档），并自动为 OpenCode Go 网关注入必需的 x-opencode-session 路由 Header，写入 settings 由 dsh 原生解析生效。

Scorp1o117
Bundle

better-basicfun

Host-only DSH foundation helpers: default workspace, resource inspection, and CLIProxyAPI catalog bridging.

CDeZT
Bundle

@arcaneorion/dsh-model-selector-search

DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).

ArcaneOrion
Bundle

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.

zisen123
Bundle

dsh-think-zh-expand-eac

DSH 思考增强插件（EAC 定制版）：思考与回复强制中文（system-prompt 注入）+ 界面硬编码英文中文化。已移除全部接管对话渲染器的显示功能，不再与折叠类插件（dsh-auto-collapse / dsh-turn-fold）抢占 assistant-step 座位。DSH web plugin (EAC fork): force Chinese agent thinking/replies + localize hard-coded UI labels, with all renderer-hijacking display features removed.

jing-hy
Bundle

dsh-token-use

Real-time token usage dashboard for DeepSeek Harness — live totals (input/output/cache/reasoning), filters by model, day, month and project, and a smooth trend chart. · 实时 Token 用量仪表盘：总量/输入/输出/缓存命中按模型、按天、按月、按项目随选，附趋势曲线。

huangyuheng
Bundle

@bo_wu/dsh-reasoning

Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu

BoWuGit
Bundle

dsh-task-effort

Auto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation

zhangzhenwen1
Bundle

dsh-agent-team-model

Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.

XMeowchan
Bundle

dsh-model-compat-guard

DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.

782042369
Bundle

dsh-plugin-reasoning-efforts

Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box

chuling-lingling
Bundle

dsh-effort-router

DSH Effort Router（模型分流）：按每一轮请求的难度自动选择模型与思考强度——简单问题走便宜快模型，难题才叫强模型。规则判定零 token，灰区交给一次小模型裁定，图片档强度随难度升降（low/high/max）。每轮请求级覆盖，不改你的会话选择与默认模型。

wanghaixu-hai
Bundle

@openplan/dsh-fuse

Cost policy for the DeepSeek Harness: per-call metering plus a local fuse that enforces budget, model and reasoning-effort limits before any token is spent.

openplancc
Bundle

dsh-custom-provider

dsh web Settings section (Custom models): subagent delegation allow-list, plus per-model image-input / reasoning-effort mapping.

homily707
Bundle

dsh-deliberation

Primary-controlled deliberation and opt-in masked review for DeepSeek Harness

fly1989
Bundle

@neptune810/dsh-model-router

Flash-only reasoning-effort routing for DeepSeek Harness: classifies each step by its shape and sets the DeepSeek flash model's reasoning effort to match. The model never changes; effort max is opt-in.

Neptune810