All plugins

DSH / BUNDLE / CLIENT-UI

dsh-web-search-diy

v2.0.5aaronlei / dsh-web-search-diyabf1c857ef

InstallableBundlesUI & client pluginsCommunity · Topic auto-analysisWeb UI

Overview

dsh-web-search-diy

DSH web search provider selected by vendor x protocol: Chat Completions, Responses, and Anthropic Messages with built-in search tools, plus the standalone search APIs of DeepSeek, Kimi, and Zhipu; four custom targets cover gateways; UI copy follows the app language (zh, en, ja, es, fr, de, ru, pt).

README / EN

Package documentation

Registry summary

DSH web search provider selected by vendor x protocol: Chat Completions, Responses, and Anthropic Messages with built-in search tools, plus the standalone search APIs of DeepSeek, Kimi, and Zhipu; four custom targets cover gateways; UI copy follows the app language (zh, en, ja, es, fr, de, ru, pt).

dsh.pub verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.

Read the full README on GitHub

LIMITATIONS

Known limitations

- **Kimi Chat is not wired in**: the in-protocol `$web_search` retires on 2026-10-20, and the `api.kimi.com/coding` endpoint is not wired either. Kimi keeps Responses and standalone search (`/v1/tools/search`; the Pro endpoint can be reached by overriding `path` on a custom target). - **Zhipu's Anthropic surface accepts but never runs the tool** (`web_search_requests: 0`), so it is marked unsupported. - **DeepSeek Responses only works with `deepseek-v4-pro`** and returns no `action.sources`; sources come from `open_page` only. - **Qwen Chat returns no sources**; Qwen is wired to the Qwen AI Platform only (`maas.qianwenaiapi.com`), not Alibaba Cloud Model Studio. - **OpenAI Chat only works with `gpt-5-search-api`**; ordinary models ignore the tool. - **OpenRouter Anthropic** accepts the `web_search_20250305` alias per its docs, but it is not verified yet. - **Kimi Responses** rejects `search_context_size` / `blocked_domains` (400). - **Standalone search has no model turn**; its output cap is `digestEntries` / `digestSnippetChars`, not a model token budget. - **Standalone source text is capped** at 2,000 characters for both `snippet` and `summary`, without splitting surrogate pairs; `dsh-tool-web` then trims `summary` to 800 by default before the model reads it. - **Test connection uses a fixed query** (`OpenAI`) and only proves connectivity, not search quality.