dsh-deepseek-search-account
English | 中文
A tiny DeepSeek Harness (DSH) plugin that keeps the built-in web_search and web_fetch tools working when your chat model is served by an external, non-official subscription — for example OpenCode Go (opencode.ai/zen/go), another Anthropic-compatible gateway, or a pi-ai provider — while DeepSeek Harness is signed in to a DeepSeek account.
Search and page fetching then run on the official DeepSeek Search / Fetch API using that DeepSeek account, so both tools keep working without a DEEPSEEK_API_KEY.
When to use it / 适用情况
Use this plugin when all of the following are true:
- Your DSH chat model is served by a third-party subscription or gateway (OpenCode Go / Zen, another Anthropic-compatible endpoint, pi-ai, etc.), not by a DeepSeek Account model.
- You are signed in to a DeepSeek account in DSH (Settings → Account), and that account may be used for search and fetching.
- The built-in web search fails with
DeepSeek search has no API key for "DEEPSEEK_API_KEY", and you do not have (or do not want to use) a DeepSeek API key.
In that situation the harness keeps working as before, but web_search returns an error. This plugin makes web_search use the official Search API and web_fetch the official Fetch API with the signed-in account, so search and fetching still run on the DeepSeek account's official quota and the chat subscription is untouched.
Do not install it when:
- Your chat model is a DeepSeek Account model: the shipped provider already searches with the account sign-in.
- You have a
DEEPSEEK_API_KEY stored: the shipped provider already works (and the Search API can be enabled in Plugins → Built-in plugin settings → Web search).
- You already use another web-search provider plugin (Exa, Tavily, SearXNG, Zhipu, etc.) that suits you.
Why it is needed
The shipped search providers (dsh-web-search-deepseek, dsh-web-deepseek-api) only use the DeepSeek account sign-in when the initiating session's model route is deepseek-account:
ctx.get("agents")?.currentInitiator()?.session.requestContext()?.provider === "deepseek-account"
With OpenCode Go as the chat provider, that check fails, the provider falls back to the DEEPSEEK_API_KEY credential, and — with no key stored — web_search fails. This plugin resolves the same account token (ctx.deepseekAccount.resolveToken(endpoint)) on every search and fetch, without looking at the conversation's model route, and falls back to DEEPSEEK_API_KEY (Bearer) only when account sign-in is unavailable.
What it does
- Registers a search provider named
deepseek-account-search and a fetch provider named deepseek-account-fetch on the ctx.web seam.
- Calls the official DeepSeek Search API (
POST https://api.deepseek.com/v1/tools/search) by default — one HTTP request per search, about 0.5–1 second, returning title, url, snippet and date; no auxiliary model turn, no extra model tokens.
- Calls the official DeepSeek Fetch API (
POST https://api.deepseek.com/v1/tools/fetch) for web_fetch — one HTTP request, the page body returned as Markdown, instead of the shipped anonymous http provider.
- Keeps a legacy
mode: messages search backend (Anthropic-compatible Messages endpoint + the native web_search_20250305 server tool) as an explicit fallback.
- Ships a bundle patch (
cordis.patch.yml) that registers both providers and pins web.searchProvider / web.fetchProvider to them.
Install
From GitHub into a profile
dsh plugin --profile desktop add github:Chip-G0202/dsh-deepseek-search-account
# for a plain `dsh web` server: --profile web
The package declares dsh.bundle, so dsh plugin add records it in the profile's bundles and applies cordis.patch.yml at boot — no hand-written row is needed. Installing from this check-out works the same way:
dsh plugin --profile desktop add /path/to/dsh-deepseek-search-account
Or attach the prebuilt tarball from the latest GitHub release:
dsh plugin --profile desktop add https://github.com/Chip-G0202/dsh-deepseek-search-account/releases/latest/download/dsh-deepseek-search-account.tgz
Then restart DSH (a profile bundle list change is applied on boot). For the Desktop app use the desktop profile as above.
Manual install (file-path row)
If you prefer not to install a package, copy this folder somewhere stable and add two rows to the profile's cordis.patch.yml (~/.dsh/profiles/<profile>/cordis.patch.yml):
- insert:
- id: web-search-deepseek-account
name: '/path/to/dsh-deepseek-search-account/provider.js'
config:
mode: search-api
count: 10
- id: web
name: '@deepseek-ai/dsh-web'
config:
searchProvider: deepseek-account-search
fetchProvider: deepseek-account-fetch
Keep web_fetch on the local anonymous transport and only move search? Pin fetchProvider: http instead — the plugin then leaves fetching alone.
Note: DSH reloads profile configuration live, but it does not re-import a plugin module when only the module path of an existing row changes. After editing provider.js, restart DSH — or toggle the row disabled: true / back — to load the new code.
Configuration
Installed as a bundle, the row lives in this package's cordis.patch.yml. Override it from the profile patch with an id-targeted entry that repeats the row name:
- id: web-search-deepseek-account
name: dsh-deepseek-search-account
config:
mode: search-api
count: 8
| Key | Default | Meaning |
|---|
mode | search-api | Search backend: search-api = official Search API; messages = Anthropic Messages + web_search_20250305 server tool |
baseURL | https://api.deepseek.com/v1/tools | Search/Fetch API base URL (/search and /fetch are appended) |
count | 10 | Results per Search API request, 1–50; the tool's searchMaxResults wins when smaller |
sendOriginalQuestion | true | Send ori_question (the session's latest user prompt, ≤128 chars) |
fetchMaxChars | 100000 | Cap on the Markdown characters one fetch returns (the seam marks the result truncated) |
fetchTimeoutMs | 30000 | Provider-side timeout for one Fetch API request |
apiKey / apiKeyEnv | unset / DEEPSEEK_API_KEY | API-key fallback when account sign-in is unavailable |
messagesBaseURL | https://api.deepseek.com/anthropic/v1 | Only mode: messages (/messages is appended) |
model | deepseek-flash | Only mode: messages |
apiVersion | 2023-06-01 | Only mode: messages (ignored by DeepSeek, per its Anthropic-compatibility docs) |
maxTokens | 4096 | Only mode: messages |
maxUses | 5 | Only mode: messages, server-side searches per request |
Billing and quotas
- Both the Search and Fetch APIs bill per successful request: 5 CNY / 1000 successful requests (about 0.005 CNY per call), charged to the DeepSeek account since 2026-11-01 00:00 Beijing time. For search, only requests that return a non-empty
results array are billed; for fetch, only requests that return page content. Failed requests and timeouts are not billed. See the official Search & Fetch guide.
- Search and fetch do not consume chat-model tokens and do not touch the subscription used for chatting (e.g. OpenCode Go). Only the DeepSeek account's web quota is involved.
- Latency is about 0.5–1 s per search and about 0.2–1 s per fetch.
- Account-level rate limits are separate per API: Search 100 QPS, Fetch 25 QPS.
mode: messages is different: one search costs a full auxiliary model turn (thousands of input tokens, 4–6 s), and server-tool searches are also billed per call as of the same date. Use it only as a fallback.
Security
- The DeepSeek account token is read from the DSH credential service per request (
ctx.deepseekAccount.resolveToken) and sent only to the api.deepseek.com origin; the account service validates the origin.
- The plugin never writes the token to disk and never exposes it to the browser.
- Fetches are performed by DeepSeek's server, so the target URL leaves your machine to the DeepSeek API rather than being fetched locally. Pin
fetchProvider: http if you want the shipped local transport instead.
- No runtime dependencies, no install scripts: plain ESM using
node: built-ins and the global fetch.
Requirements
- DeepSeek Harness
0.2.1-rc.5 or later (the ctx.web seam and deepseekAccount service it relies on).
- Signed in to DeepSeek in DSH, with network access to
api.deepseek.com.
- Node.js 22+ (the DSH desktop app bundles its own runtime).
Verifying and troubleshooting
scripts/verify.mjs runs the providers exactly as the harness does, using the real account token from ~/.dsh/.credentials.yaml (the token never leaves the process):
NODE="/Applications/DeepSeek Harness.app/Contents/Resources/runtime/primary-runtime/dependencies/node/bin/node"
"$NODE" scripts/verify.mjs "query" # official Search API, ~0.4–0.6 s, snippets included
"$NODE" scripts/verify.mjs --fetch "https://example.com" # official Fetch API, Markdown body
"$NODE" scripts/verify.mjs "query" --messages # legacy Messages backend, ~4–6 s
If search or fetch fails, the structured error names the cause: WEB_PROVIDER_CREDENTIAL_MISSING (not signed in and no API key), WEB_PROVIDER_ERROR (HTTP/network, with the endpoint that was used), WEB_INVALID_URL (fetch URL rejected before dispatch), WEB_FETCH_TIMEOUT (provider-side timeout), or WEB_ABORTED (cancelled). If the account sign-in is rejected, sign in to DeepSeek again — the endpoint does not need changing.
Uninstall
dsh plugin --profile desktop remove dsh-deepseek-search-account
This removes the package and its bundle layer; the profile's own search configuration is not touched. For the manual install, delete the two rows described above.
License
MIT
