dsh-workbuddy-xdpool
Run the following command in DeepSeek Harness:
dsh plugin install aosi526/dsh-workbuddy-xdpool
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install aosi526/dsh-workbuddy-xdpool in DeepSeek Harness to install; see source at https://github.com/aosi526/dsh-workbuddy-xdpool
About this plugin
With a single WorkBuddy account, one 429 rate-limit brings the entire workflow to a halt; manually switching accounts and waiting out cooldowns is tedious and easy to get wrong. dsh-workbuddy-xdpool automates the whole thing: it scans every login snapshot left by the WorkBuddy desktop app on your machine and merges all of them into one shared DeepSeek Harness model pool with no credential entry required.
At the core is an automatic failover chain. Each account tracks its own 429 cooldown independently; a rate-limited account is skipped immediately and the request lands on the next healthy one, rejoining rotation after the cooldown expires. Requests pause only when every account is cooling simultaneously. The settings card shows live pool health, per-account token expiry, cooldown countdowns, and a per-account plus total credit balance that refreshes in real time; the model directory annotates each model with its credit multiplier, free or time-limited tags, image-input capability, and context window.
Built for DSH users who already have multiple accounts logged into the WorkBuddy desktop app and want zero-config automatic failover rotation out of the box: install, enable, and the pool appears in the model selector with no further manual steps.
Screenshots
Use Cases
- A 429 on one account triggers instant failover to the next healthy member mid-session
- Batch inference tasks stay uninterrupted as the pool round-robins across accounts
- No manual account switching or cooldown waiting—the pool manages all WorkBuddy tokens automatically
Best For
- DSH users with multiple accounts logged into the WorkBuddy desktop app
- Developers who need uninterrupted model inference and cannot tolerate rate-limit downtime
- Plugin users who want zero-config, no-credential-management out of the box
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.