跳到主要内容

dsh-context7

已验证

dsh-context7 · v0.2.0 · Apache-2.0

Context7 up-to-date library documentation for DSH: context7_search / context7_get_docs model tools backed by the Context7 Public API v2 (context7.com).

安装

dsh plugin add dsh-context7

dsh --profile default --dump-config 确认 layer 已生效 —— 参见安装指南

源码

标签

作者

说明文档

dsh-context7

Up-to-date library documentation for DeepSeek Harness, powered by Context7.

This host-only plugin connects DSH to the official Context7 Public API v2, so your agent can always fetch current, version-pinned documentation and code examples for software libraries. It registers two model tools:

Tool Purpose
context7_search Search libraries by name (optionally with a natural-language question for LLM ranking). Returns matches with their Context7 library IDs (e.g. /vercel/next.js).
context7_get_docs Fetch LLM-reranked documentation for one library by ID (or bare name, auto-resolved) plus a natural-language question: code snippets, doc snippets, library rules and source URLs. Supports version pinning (e.g. v15.1.8) and a fast low-latency mode.

No API key is required — Context7 allows keyless access with low rate limits. For higher limits, get a ctx7sk-prefixed key from the Context7 dashboard.

Installing

From npm (published):

dsh plugin --profile web add dsh-context7

From GitHub:

dsh plugin --profile web add github:Nrxous/dsh-context7

Restart DSH after installing. The tools are called automatically whenever the model needs current library docs, or you can trigger them by asking directly.

Configuring the API key (optional)

Set config.apiKey in your profile patch layer~/.dsh/profiles/<name>/cordis.patch.yml — which is applied after every bundle layer and survives plugin updates:

- id: dsh-context7
  config:
    apiKey: ctx7sk_your-key-here

Save and restart DSH. With a key set, requests carry an Authorization: Bearer header for higher rate limits. Without one, the plugin keeps working at keyless limits.

Development

Pure JS plugin, no build step — main: src/index.js, runtime dependency @deepseek-ai/schemastery (provided by the host).

# Hot-mount into the web profile (no restart)
dev_install_package <this-directory>
# or inside the injector environment
dev_inject_plugin <this-directory>

License

Apache-2.0