DeepSeek Harness plugin

dsh-local-web

Local web fetch provider: fetches web pages and summarizes/parses them with the local Ollama model before returning to the agent

Jump to install

Source facts

Repository
wanghj040530/dsh-local-web
Latest update
Aug 18, 2026
Category
Workflow & Automation
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/wanghj040530/dsh-local-web
Plugin: dsh-local-web
Author: wanghj040530

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer2 files
README.mdSource · read only

dsh-local-web

> 本地网页读取插件:让 dsh 的 web_fetch 走「抓网页 → 本地 Ollama 模型整理 → 返回」链路,网页内容不出本机。

背景

DSH (DeepSeek Harness) 默认没有内置 fetch provider,web_fetch 工具因缺少 provider 而不可用。本插件注册一个 local-ollama fetch provider,补全整条链路:

dsh web_fetch(url)
  → Node fetch 抓取网页
  → 轻量 HTML→text 提取
  → 本地 Ollama (qwen3.5:9b) 整理/总结
  → 返回 { url, statusCode, body: { kind: 'text', content }, truncated }

特性

  • 本地处理:网页内容只发给本地 Ollama,不上传云端
  • 零依赖抓取:用 Node 原生 fetch + 正则提取 HTML 文本,不引 turndown
  • 即装即用:注册后 dsh 的 web_fetch 工具自动走此 provider

安装

# 复制到本地插件目录
cp -r dsh-local-web ~/.dsh/local-plugins/dsh-local-web

# 安装到 profile(以 desktop 为例)
dsh plugin --profile desktop add "link:~/.dsh/local-plugins/dsh-local-web"

# 配置 fetch provider(在 profile 的 cordis.patch.yml 中)
# web:
#   fetchProvider: local-ollama

# 重启 DSH

前置要求

  • 本机运行 Ollama,并已拉取模型(如 qwen3.5:9b
  • DSH profile 已启用 tool-webdisabled: false + fetch: true

配置

插件在 cordis.patch.yml 中的默认配置:

- id: dsh-local-web
  config:
    baseURL: http://127.0.0.1:11434/v1   # Ollama OpenAI 兼容端点
    model: qwen3.5:9b                     # 本地整理模型
    timeoutMs: 120000                     # 抓取+推理总超时
    maxChars: 8000                        # 送入模型的文本上限
    prompt: >-
      请用中文简洁总结以下网页内容,提取关键信息与要点。
      如果内容为其他语言,请用与内容相同的语言总结。

License

MIT