DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Tool Router — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
T

@local/dsh-tool-router

Tool Router

延迟工具发现:在预填充阶段隐藏所有工具架构,并根据决策模型的选择按需显示其中一个。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:residenthiago2011/DSH-Tool-Router#bbec9697b180dbcd50e45f93e9eb88db9ee76f38
README兼容性版本

兼容性与来源证明

Tool Router 以 @local/dsh-tool-router 发布,当前版本为 1.1.0。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
github
Registry 更新时间
2026/10/17

版本

1.1.0stable
2026/10/17

相关插件

正在加载相关插件…

最新版
1.1.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
any
许可证
MIT
发布源
github
GitHub
★ 1
周下载
0
最近提交
2026/10/17
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 models-usage 分类下经过校验的插件。

Whale Widgetdsh-whale-widgetDSH Web 界面右下角的 DeepSeek 余额小鲸鱼挂件:余额/今日已用/峰谷定价、自定义泡泡点击序列(文本/余额/今日/峰谷/图片/随机语句与并列加权选择)、逐行样式与字体、悬浮快捷编辑、音效与每轮消耗、自定义角色/动图/音效、吸附与翻转自定义Usage@linxin666/dsh-usage用于 dsh Web GUI 的使用统计插件:检测各提供商的余额和编程套餐配额,并实时记录令牌使用情况;侧边栏 Settings 行上方显示紧凑的价格概览卡片Client Ui Model Capabilities@linxin666/dsh-client-ui-model-capabilities为自定义 pi-ai 提供商声明每个模型的能力(图像输入和推理力度),可直接在 Models 设置卡片中编辑;写入官方 llm-pi-ai 设置命名空间,不更改 DSH 源代码。Cost Meterdsh-cost-meterDeepSeek Harness 会话费用统计插件:本会话成本、当日费用、历史记录与官方价格同步,支持多厂商多模型价格计费(内置 170+ 模型 ID 价格目录与自动匹配)、主流 Coding Plan 订阅额度查询与显示(14 家,含 WorkBuddy 官方积分、OpenDesign 工作区查询、含小米 MiMo Token Plan 控制台 Cookie 查询、SCNet Token Plan 本地 Credits 计量与火山方舟 Volcano Ark Coding Plan AK/SK 签名查询

README

DSH Tool Router

Lazy tool discovery for DSH: hides every tool schema from the model's prefill and reveals exactly one tool on demand through a decision model API.

  • Prefill cost: one small find_tool schema instead of every mounted tool (26 schemas on a default Standard profile — see Why?).
  • Stage 0 — full-surface send: every mounted tool (≤ 24) carries a 160-char criterion, ordered by a stopword-filtered lexical rank (the rank only bounds pathological mounts — d1-omni does not saturate as the choice count grows; see Why?).
  • Stage 1 — one POST /v1/systemone to the decision model API: a bestTool choice plus a usable question kept as telemetry only (~235–500 tokens, ~6–7 s on-device).
  • Stage 2 — accept iff confidence >= 0.70: return the winner's JSON Schema and reveal exactly that one tool; otherwise return a probability-ordered shortlist whose reason names the closest match, so the model can retry with that exact tool name (or send an empty request to get the whole catalog). Exact tool-name requests skip the decision call and reveal instantly.

Why?

Fresh session, first message, server-reported usage.prompt_tokens — the DSH Standard preset (the platform default) versus this plugin's no-prefill preset:

Cost before the first wordStandardno-prefill
Prefill tokens6,559283
System prompt5,816 chars372 chars
Tool schemas shipped up front26 schemas (21,417 B)1 schema (697 B)

Standard makes the model ingest a 5.8k-character system prompt plus every mounted tool schema — 6,559 tokens — before it emits a single word, and pays it again on every subsequent turn. no-prefill ingests 283 tokens (23× less, 96% smaller prefill): a slim persona plus the single find_tool schema. On the measured backend that difference was ~40 s versus ~14 min of prompt evaluation for the first reply.

What that buys you:

  • Latency — time-to-first-word scales with the whole tool shelf today. Reveal-on-demand makes it scale with the tool you actually call.
  • Context budget — 6.5k tokens of standing preamble is 6.5k tokens you don't have for code, conversation, and results. On a 32k window that's ~20% of the model's world spent before work starts.
  • Reliability on small models — a model reading 26 schemas behaves like a model reading 26 instructions it must never violate. One schema at a time is one schema to follow; the rest of the shelf doesn't exist for it.
  • Pay for what you use — a turn that calls no tool costs 283 tokens instead of 6,559. A turn that calls one tool reveals that one schema once; the other 25 are never sent.

If a session ends up using most tools anyway, the gap narrows — but the unused half of the shelf is exactly what a default profile charges for from word one.

What the bundle patch declares

cordis.patch.yml (applied when the bundle is selected):

  1. preset-no-prefill — an agent preset whose composition is only persona + dsh-tool-router. The persona tells the model: no tools are declared; call find_tool first — and if a result carries no schema, retry with an exact tool name or an empty request instead of giving up.
  2. Host tool rows enabled — tool-bash, tool-fs, tool-fs-search, tool-todo, tool-web flipped to disabled: false, plus a present row inserted. Discovery needs the tools to exist somewhere; preset-scoped registrations shadow host ones, so other presets keep their own behavior. The slim preset keeps the Agent Presets page showing only find_tool.

Prerequisites

  • DSH 0.2.0-rc.2 (bundles mechanism with dsh.bundle.patch).
  • A running decision model API that speaks POST /v1/systemone (the router defaults to http://127.0.0.1:8081/v1/systemone; edit ROUTER_BASE in index.js to point at another host or port).
  • pnpm on PATH of the host running DSH (the plugin manager installs through pnpm; the CLI forwards pnpm arguments).

Install

From GitHub (recommended): Plugins → install → spec

git+https://github.com/residenthiago2011/DSH-Tool-Router.git

or via the CLI:

dsh plugin --profile <profile> add git+https://github.com/residenthiago2011/DSH-Tool-Router.git

From a prebuilt tarball: download dsh-tool-router.tgz from Releases, then install from the local path (also accepted: absolute path, git URL, or an npm registry name after publishing):

dsh plugin --profile <profile> add /path/to/dsh-tool-router.tgz

Then select the bundle on the Plugins page (installation enables it by default) and restart DSH if the profile runs without HMR.

Uninstall

Deselect/remove the bundle on the Plugins page. The preset row and the host tool flips vanish with the bundle patch; other presets are untouched.

Files

FilePurpose
index.jsThe router plugin: registers find_tool, masks every other tool per agent, runs the 3-stage decision.
cordis.patch.ymlThe bundle patch: preset declaration + host tool enablement.
tool-registry.jsonStage-0 labels and Stage-1 criteria (25 tools, both shells incl. bash).

Tests

node router-import-test.mjs   # module shape (no dependencies)
node rank-sim.mjs             # Stage-0 ranking on sample queries (needs tool-registry.json)
node router-e2e-test.mjs      # full flow: arm/deny-set/live reveal — requires the decision endpoint at 127.0.0.1:8081

router-e2e-test.mjs uses a stub DSH context that emits tools/change synchronously (the worst case that once caused a ~970x feedback loop), then drives the real find_tool against a live decision endpoint: armed-once, deny-set dedup, late registration, reveal re-arm, empty-request catalog hint, and the exact-name fast path. ALL_PASS is expected.

Notes

  • find_tool registers with a standard JSON Schema (type/properties/required/additionalProperties). A raw register with author-style parameters reaches the LLM unconstrained — the model then calls with {}. Always compile.
  • The empty-request catalog hint and the exact-name fast path exist for small models; see execute() in index.js.