dingminhua/dsh-connect-workbuddy
Connects locally signed-in WorkBuddy models, CN and international alike, to DSH, reading each model's credit multiplier from the upstream catalog on every refresh, with per-model image input toggles, account switching backed by an auto-failing-over pool, manual daily check-in, and read-only credit overviews shown as compact pills on the card and in the composer.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run yesterdayon DeepSeek Harness 0.2.2-rc.1.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, yesterday.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Registers locally signed-in WorkBuddy (CN and global) as DSH providers and refreshes each model's credit multiplier from upstream.
Who it is for — You already have a WorkBuddy login on the machine and you are doing coding work in DSH, but GLM-5.3, DeepSeek-V4-Pro, or GPT-5.6 still cannot be chosen there. Skip it if the official WorkBuddy app is where that account should be used, and DSH is not the place those models should appear.
Watch out — WorkBuddy is already limiting unofficial client traffic, so the bridge can stop when upstream tightens, and long-term API availability is not promised. Calls spend your own credits; the plugin does not change account state, and it does run shell commands. A clean-profile install succeeded and was registered into that profile.
The verdict — I'd add it as a part I can delete overnight—only if those models never become a load-bearing step.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-connect-workbuddy is a DeepSeek Harness plugin that connects locally signed-in WorkBuddy models to the DeepSeek Harness model selector. It supports the domestic and international WorkBuddy services as separate providers, workbuddy and workbuddy-global. On each model refresh, dsh-connect-workbuddy reads the upstream catalogue for model availability, credit multipliers, limits, reasoning modes and activity information, rather than hard-coding prices. Settings are managed under Settings → WorkBuddy; model selections, image-input settings, reasoning defaults and other directory options are saved locally, while catalogue and multiplier updates take effect when refreshed.
Accounts can be switched individually or managed through an auto-failing-over pool. The settings page also provides manual daily check-in and read-only credit readings, shown as compact pills on model cards and in the composer. Image input and “off” reasoning modes can be controlled per model. Domestic and international accounts remain separate, and either provider can be disabled without deleting its saved configuration.
This is for developers who already use WorkBuddy on the same machine and want its signed-in account available in DeepSeek Harness. It is a poor choice where only official WorkBuddy clients or supported public APIs are acceptable: the plugin relies on WorkBuddy’s client interfaces, which are not official open APIs and may be restricted or changed. The terminal surface is relevant because its optional capability can authorise calls to the local CodeBuddy CLI. Requests consume the installed WorkBuddy account’s own credits; dsh-connect-workbuddy does not provide credentials, bypass billing or grant extra permissions.
DeepSeek Harness exposes the plugin at Settings → WorkBuddy. The page has separate domestic and international tabs, with independent account pools, model catalogues and unsaved drafts. Each provider is enabled by default; clearing its provider checkbox removes that provider’s models and routes from the DeepSeek Harness model selector and model settings, while retaining its accounts, catalogue, credits and selections. Re-enabling it restores them.
Model management starts with a refresh from the upstream catalogue. Refreshing immediately stores and applies catalogue data, including credit multipliers, context and output limits, reasoning modes and activity details. It does not save pending directory edits. Model enablement, context budgets, image-input choices and default reasoning modes require Save; Discard abandons those drafts. Image input is initially enabled only for models covered by the plugin’s verification table. Models without supporting evidence are treated as unverified, but can be selected manually. The off option is controlled per model; nine reviewed models that return an error for this mode cannot enable it.
The account-pool section can detect locally signed-in accounts, switch accounts and enable automatic failover. The README also documents a manual daily check-in action. Credit information is read-only. A diagnostics section reports the active region, upstream domain, serving account name, login expiry, catalogue counts, account-pool state and the latest upstream error text.
The optional sidebarPanel setting adds a WorkBuddy entry to the DeepSeek Harness sidebar and opens the same page in a full-width panel. It is disabled by default and takes a shared sidebar slot. Capability controls also cover local CodeBuddy CLI calls, model-initiated image generation and credit-pill placement. The README names sidebarPanelEnabled as the host-side value used to seed the sidebar state.
The plugin uses WorkBuddy client interfaces rather than an official public API. WorkBuddy may restrict non-official client requests, and upstream changes can make the plugin unusable. Models from a region without a locally signed-in account are not listed. Closing a provider while a session still selects one of its models causes NO_ADAPTER on a later call.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
Ebony-Vinyl
Adds free model lanes to DeepSeek Harness — DeepSeek V4.1 Flash, Kimi K3 and others — with no login, sign-up or API key, plus a local OpenAI-compatible gateway, fallback routing and a usage dashboard.
Installed cleanly when we ran it
zouyuxuan122
在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.
Installed cleanly when we ran it
HunYiSage
DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分
Installed cleanly when we ran it
Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.
Installed cleanly when we ran it
Mars-Sea
Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.
Installed cleanly when we ran it
FishBottle7
Exposes OpenCode Zen free models to DeepSeek Harness, with no API key.
Installed cleanly when we ran it
