dsh-search-first
DeepSeek Harness plugin: force web search before the model answers (Search First) — query extraction, unified search engine, fetch, cache and runs persistence
AI 分析
核心用途是实现“先搜后答”的 RAG 流程，确保模型回答的时效性与准确性。适合需要高频联网查询的用户，需配置至少一个搜索 API 密钥。
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:v587d/dsh-search-firstドキュメント
README 全文を読む ↗Configuration (Settings → Search first)
| Section | Fields |
|---|---|
| General | default enabled, failure policy (continue / block), injection mode, overall timeout |
| Query Extraction | explicit provider/model (empty = follow session model), timeout, max tokens |
| Cache | dir (empty = $DSH_HOME/search-first; root applies after restart), search/fetch TTL, clear button |
| Limits | max search results, max fetch pages, max inject chars |
| Search APIs | mode (sequential failover / parallel fan-out + merge), big-three enable/credential-ref/priority, per-provider timeout, ctx.web fallback, local HTTP fallback, Test all connections |