deepseekplugins

DeepSeek Harness plugin

dsh-web-search-provider

Native web search provider for the DeepSeek Harness web seam (ctx.web): one provider that speaks the OpenAI Responses API (web_search, with search / open_page / find_in_page actions) and the

Docs & Rendering
Jump to install

Source facts

Repository
hiyms/dsh-web-search-provider
Latest update
Aug 16, 2026
Category
Docs & Rendering
GitHub stars
1
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/hiyms/dsh-web-search-provider
Plugin: dsh-web-search-provider
Author: hiyms

Check the source files

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

File explorer4 files
README.mdSource · read only
README language

dsh-web-search-provider

![npm version](https://www.npmjs.com/package/dsh-web-search-provider)

简体中文

Network search support for the Deepseek Harness, powered by the model provider's server-side capability.

Using this plugin requires the model provider to use the OpenAI Responses API or an Anthropic-compatible Messages API, and to provide a web search capability.

> [!TIP] > The Anthropic-compatible Messages API only provides a search capability, while the OpenAI Responses API additionally supports viewing a URL's page content / finding specific content within a URL's page. Providers on the OpenAI Responses API are recommended.

> [!TIP] > Verified to work with: the Deepseek official Messages API (the DSH built-in Deepseek provider), the OpenCode Go Messages API, the OpenCode Go Response API, and an OpenAI relay station's Response API.

> [!WARNING] > The DSH built-in OpenCode Go provider uses different API types for different models. For example, for its Deepseek V4 Flash/Pro models, to use this plugin's capability you need to manually add a custom provider of the Response / Message API type.

> [!WARNING] > Some model providers may charge extra for the web search capability this plugin uses.

This plugin does not provide its support through the web_search tool inside the Deepseek Harness, so you can use it alongside other web search provider plugins (such as the built-in web-search-deepseek).

Comparing with web-search-deepseek

> TL;DR Compared with web-search-deepseek, this plugin has a clear advantage in both token consumption and time.

web-search-deepseek is the Deepseek Harness's built-in search plugin: when the model in a session calls the web_search tool, it creates a new internal session to run the search and returns several URLs with their content summaries.

Compared with web-search-deepseek, the AI in this plugin's sessions sends the network search request directly to the server, making each individual search faster. Also, the model can directly view / search page content (only with the OpenAI Responses API), reducing the tokens the AI spends on bash/curl to read a page's full content.

Using the Deepseek official Messages API's deepseek-v4-flash model with high think, each plugin performed 5 specified searches per run, tested 10 times:

PluginAverage tokensAverage time
web-search-deepseek4,44647.5s
web-search-provider82214.5s

Time is measured from the answer duration shown in the Deepseek Harness. Tokens are the average of the "output" tokens reported on the Deepseek Open Platform, using two different API tokens (because the Deepseek Harness does not count tokens consumed inside tool calls).

The results are for reference only. On tasks that need more web search content, this plugin is expected to show a more pronounced advantage.

Install

dsh plugin add dsh-web-search-provider

------

Or install from source:

pnpm install

Reference the built plugin from a cordis.yml overlay:

- insert:
    - id: web-search-provider
      name: 'dsh-web-search-provider'
      config:
        enabled: true
        probe: true

Config

Settings section web-search-provider (a live namespace: edits reach the next request). All fields are optional unless noted.

KeyDefaultMeaning
enabledtrueMaster switch; false sends every request down the normal adapter path.
providers[]Provider whitelist (llm-pi-ai route keys). A request is served only when its provider is also the current chat route (the plan derives its endpoint facts from that route); the whitelist restricts which of its providers may be served. Empty = serve the current chat route.
baseURLrouteEndpoint base override for the route's candidates; /responses or /messages is appended.
modelloop modelModel override; used by the capability probe and by the served wire request.
apiKeyEnvroute refCredential reference resolved per operation.
includeSourcestrueAppend include: ['web_search_call.action.sources'] to Responses wire requests.
stripServerToolstrueStrip the function-tool variants (web_search/open_page/find_in_page) from the wire tools.
idleTimeoutMs300000Idle bound for one inline request, in milliseconds.
probetrueVerify the endpoint executes native search before serving.
probeTimeoutMs30000Bound on one probe request, in milliseconds.
- id: web-search-provider
  name: 'dsh-web-search-provider'
  config:
    enabled: true
    probe: true

Known limitations

  • For providers that use the Response API / Message API but do not provide a search capability, the session errors on first use. Keep sending messages / open a new session and DSH keeps working without this plugin's capability.
  • When the AI uses this plugin's web search capability, there is no visible search-call UI. The usage may appear as multiple consecutive thinking segments, with the tail of a thinking segment containing something like "*Let me make search queries*".

Contributing

Building

pnpm install
pnpm build        # tsc emits lib/types, tsdown bundles lib/index.js
pnpm test         # vitest unit suite
Back to searchOpen GitHub repository

More related plugins

View category