dsh-search-hub
DeepSeek Harness 的多入口网页搜索中心：通过可配置的模型入口将 ctx.web 搜索路由至 DeepSeek 官方、GLM Coding Plan Zhipu web_search 以及未来的 Kimi，并确保仅有一个入口处于激活状态；提供 Settings 页面标签页用于管理。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-search-hub@0.1.1
Search Hub 以 dsh-search-hub 发布，当前版本为 0.1.1。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。
Multi-entry web search hub for DeepSeek Harness · DeepSeek Harness 联网搜索多入口管理中枢
DeepSeek Harness's built-in web search is a single fixed channel (deepseek-official, an Anthropic-compatible Messages call with the server-side web_search tool). dsh-search-hub turns that channel into a configurable hub:
anthropic — Anthropic Messages + native web_search_20250305 tool (covers DeepSeek official; ready for Kimi Coding endpoints once verified);zai — Zhipu's standalone Web Search API (POST {base}/web_search): deterministic retrieval with no model turn, no tool-call discretion — every call IS a search. Works with GLM Coding Plan keys.web capability at the hub; remove the bundle and the composition falls back to your previous provider by itself.| DeepSeek Harness | 0.1.1-rc.2 (web profile) |
GLM Coding Plan (zai adapter) | real searches verified against https://api.z.ai/api/paas/v4 (and the /api/coding/paas/v4 variant), structured sources returned |
DeepSeek official (anthropic adapter) | same wire format as the stock provider |
Kimi Coding (anthropic template) |
template only — endpoint support for web_search_20250305 not yet probed |
The repo ships prebuilt artifacts under lib/, so no build toolchain is needed on the installing machine.
Add the dependency and bundle row in <harness-home>/profiles/web/package.json:
"dependencies": {
"dsh-search-hub": "git+https://github.com/Lzh3070/dsh-search-hub.git"
// or a local checkout:
// "dsh-search-hub": "link:D:/path/to/dsh-search-hub"
},
"dsh": { "profile": { "bundles": [
// ... existing rows ...
"dsh-search-hub"
] } }
Install:
npx -y @deepseek-ai/dsh plugin --profile web install
Restart Harness, open 设置 → 搜索, pick the active search model.
chat session ── web_search tool ──▶ ctx.web seam ──▶ search-hub provider
│ active entry
┌───────────────┴────────────────┐
vendor: anthropic vendor: zai
POST {base}/messages POST {base}/web_search
tools:[web_search_20250305] { search_query, search_engine }
→ web_search_tool_result blocks → search_result[] items
Settings persist under the search-hub: namespace of <harness-home>/settings.yaml. Only env-var NAMES are stored (e.g. ZAI_API_KEY); actual keys stay in the credentials store (managed on the Settings → Models page). Each search snapshots the section, so edits apply to the next call without re-registering anything.
baseURL you configure — treat entry config with the same care as the stock provider's base-URL override.anthropic adapter bills as a full model turn on the respective plan (server-side search runs inside a Messages call). The zai adapter is a deterministic per-call search API — no model turn — but still bills against your Zhipu/GLM quota per request.allowLinkless: true map them to zhipu-websearch:// placeholder URLs so titles and snippets still reach the model.npm install # tsdown + typescript + pinned @deepseek-ai type deps
npm run typecheck
npm run build # lib/index.js (Node ESM) + lib/client.js (browser CJS)
DSH_HOME=<home> node scripts/test-zai-adapter.mjs "query" # live zai adapter test
Requires Node.js ≥ 22.
DeepSeek Harness 自带的联网搜索是单一固定通道（deepseek-official，Anthropic 兼容 Messages 请求挂服务端 web_search 工具）。dsh-search-hub 把这条通道变成可配置的搜索中枢：
anthropic —— Anthropic Messages + 原生 web_search_20250305（覆盖 DeepSeek 官方；Kimi Coding 端点验证通过后直接可用）；zai —— 智谱独立 Web Search API（POST {base}/web_search）：确定性检索，不消耗模型轮次、模型无权跳过——每次调用必是一次搜索。GLM Coding Plan 的 key 可直接用；ctx.web 的 searchProvider 接管到本插件，移除 bundle 后自动回落原通道，无需手工改配置。| DeepSeek Harness | 0.1.1-rc.2（web profile） |
| GLM Coding Plan（zai 适配器） | 已对 https://api.z.ai/api/paas/v4（及 /api/coding/paas/v4 变体）实测真实搜索，返回结构化来源 |
| DeepSeek 官方（anthropic 适配器） | 与官方 provider 同 wire 格式 |
| Kimi Coding（anthropic 模板） | 仅模板占位——端点对 web_search_20250305 的支持尚未探针验证 |
仓库内含预构建产物 lib/，安装机器无需任何构建工具链。
在 <harness-home>/profiles/web/package.json 加入依赖与 bundle 行：
"dependencies": {
"dsh-search-hub": "git+https://github.com/Lzh3070/dsh-search-hub.git"
// 本地开发调试可用：
// "dsh-search-hub": "link:D:/path/to/dsh-search-hub"
},
"dsh": { "profile": { "bundles": [
// ...原有行...
"dsh-search-hub"
] } }
安装：
npx -y @deepseek-ai/dsh plugin --profile web install
重启 Harness，打开 设置 → 搜索，选择生效的搜索模型。
会话里的 web_search 工具经 ctx.web seam 进入本插件的统一入口，按当前生效条目分发到对应协议适配器。配置持久化在 <harness-home>/settings.yaml 的 search-hub: 命名空间下；只保存 key 的环境变量名（如 ZAI_API_KEY），明文密钥仍在凭据体系（设置 → 模型）里管理。
baseURL 发起的普通 HTTPS 请求，请像对待官方通道的地址覆盖一样谨慎填写；anthropic 适配器按一整轮模型调用计费（服务端搜索跑在 Messages 请求里）；zai 适配器是确定性的按次检索 API——不走模型轮次——但每次请求仍计智谱/GLM 额度；allowLinkless 的条目会映射成 zhipu-websearch:// 占位链接，标题与摘要照常传给模型。npm install
npm run typecheck
npm run build
DSH_HOME=<home> node scripts/test-zai-adapter.mjs "query" # 直调 zai 适配器真实搜索
需要 Node.js ≥ 22。