dsh-web-search-responses
Agent 与会话 活跃维护

dsh-web-search-responses

herminger/dsh-web-search-responses

DSH ctx.web search provider that reuses the conversation model's OpenAI Responses built-in web_search

1
Stars 标星
0
Forks 分支
1
Watchers 关注
0
Open Issues
JavaScript
主要语言
MIT
开源协议
10 KB
仓库大小
1 个月前
最后推送
一键安装扩展 / 插件指令
dsh plugin --profile web add github:herminger/dsh-web-search-responses
git clone https://github.com/herminger/dsh-web-search-responses.git
git clone git@github.com:herminger/dsh-web-search-responses.git
README.md main

dsh-web-search-responses

A DeepSeek Harness (DSH) ctx.web search provider that reuses the conversation model's OpenAI Responses built-in web_search tool, instead of DSH's built-in Anthropic Messages search provider.

Why

DSH's model-facing web_search goes through dsh-tool-web → ctx.web.search() → a registered search provider. The shipped web-search-deepseek provider only speaks the Anthropic-compatible /messages API with web_search_20250305, so a custom model whose Responses endpoint supports built-in web_search cannot be reused by configuration alone.

This plugin registers a provider (responses-web) that sends a Responses API request to the same endpoint the conversation model uses, with:

{
  "tools": [{ "type": "web_search" }],
  "tool_choice": { "type": "web_search" }
}

It parses the web_search_call item and message citations back into DSH's standard WebSearchResult.

Install

From GitHub (recommended)

Requires pnpm on PATH:

dsh plugin --profile web add github:herminger/dsh-web-search-responses

If you previously installed a local link copy and want to switch to the GitHub source:

dsh plugin --profile web remove dsh-web-search-responses
dsh plugin --profile web add github:herminger/dsh-web-search-responses

From a local checkout

dsh plugin --profile web add /path/to/dsh-web-search-responses

Quick test without pnpm (keep overlay.patch.yml next to index.mjs, or use an absolute path):

dsh --profile web --patch /path/to/overlay.patch.yml

Then fully restart dsh web so the new bundle loads.

Configuration

The provider auto-follows the current model by default:

  • provider/model come from the executing agent, the DSH default model, or the single configured llm-pi-ai Responses route
  • baseURL, apiKeyEnv, and api come from that route's llm-pi-ai settings

To pin a route explicitly, edit the profile's cordis.patch.yml:

- id: web-search-responses
  config:
    provider: cpa
Field Meaning Default
provider llm-pi-ai route to reuse current model route
model model for the search request current model
baseURL Responses endpoint prefix (/responses is appended) route baseURL
apiKeyEnv credential reference, e.g. CPA_API_KEY route apiKeyEnv
includeSources send include: ["web_search_call.action.sources"] false
searchContextSize low / medium / high unset
toolChoice { type: "web_search" } or "required" { type: "web_search" }
maxOutputTokens output token cap for the search request 4096

Troubleshooting

  • configured web provider "responses-web" is registered but unavailable — the plugin's config was parsed as YAML null (empty config:). Update to the latest index.mjs, which normalizes config ?? {}, and restart DSH.
  • Responses API returned no web_search_call item — the endpoint/model does not actually support the built-in web_search tool.
  • no API key for "..." — check the route's apiKeyEnv and the credential stored in DSH.

Chinese docs: README.zh.md