aaronlei/dsh-web-search-diy1

dsh-web-search-diy

DSH web search provider over any OpenAI-compatible Responses API gateway exposing the native web_search tool. Registers a ctx.web search provider (defaults to Qwen Token Plan as a working example) and overrides the shared searchProvider to it; UI copy follows the app language (zh / en).

包名
dsh-web-search-diy
版本
0.1.4
许可证
MIT
最近更新
2026年9月6日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aaronlei/dsh-web-search-diy

Configuration

The provider resolves options with precedence: UI-managed file ($DSH_HOME/dsh-web-search-diy.json, written by the Settings card) > settings section / entry config > package defaults.

KeyDefaultMeaning
apiKeyLiteral API key; overrides apiKeyEnv when set
apiKeyEnvQWEN_TOKEN_PLAN_CN_API_KEYCredential reference resolved per search via ctx.credentials
baseURLhttps://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1Responses API base; /responses is appended
modeldeepseek-v4-flash-0731Model served by the endpoint; before switching, confirm the model actually exposes the web_search tool on the gateway (not all models support live web search) — otherwise the search fails loudly with WEB_PROVIDER_ERROR, never a no-search fallback
maxOutputTokens1024max_output_tokens for one search call

Settings card

The configuration card lives under Settings → Plugins → Plugin configuration → Custom web search, in the same form as the shipped Shell / Agent loop cards: edits stage locally (an "unsaved" badge appears in the header) and only Save writes, while Discard reverts to the stored values. Saving takes effect immediately — no restart. Card copy follows Settings → Language (zh / en). The API key input is write-only: leave it blank to keep the stored key.