dsh-provider-qoder
Run the following command in DeepSeek Harness:
dsh plugin install mo-n/dsh-provider-qoder
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install mo-n/dsh-provider-qoder in your terminal to install the plugin. The source repository is at https://github.com/mo-n/dsh-provider-qoder . After installation, restart your DSH profile and configure the PAT and model selection under Settings → Models.
About this plugin
If you already hold a Qoder subscription and want to call its models directly from within DeepSeek Harness, you need a bridge. dsh-provider-qoder is a community adapter plugin that plugs Qoder's text, image, streaming, and tool-calling capabilities into the DSH workflow.
It supports both the Global and China service regions, authenticates via a Personal Access Token, and auto-discovers available models on your account with pricing multipliers and reasoning-effort tiers. For vision-capable models, images are published to the Qoder center service and referenced by URL to keep payloads small; if publication fails, the image is sent inline so the turn still completes. Streaming responses, reasoning content, tool calls, and multi-turn interactions all work natively within DSH. The settings page also surfaces account details, personal quota, organization resource packs, and reset dates.
This plugin suits developers who already run Qoder subscriptions inside DSH and want a single, manageable model pipeline-especially those juggling both Global and China regions, relying on image input, or chaining multi-step tool calls. The plugin handles only authentication and model communication; tool execution, workspace operations, and permission management remain with DSH itself, keeping responsibilities clean.
Use Cases
- Call Qoder models directly inside DSH for multi-turn chat and streaming output
- Combine image and text input with Qoder vision models and chain tool calls
- Manage Qoder subscriptions across both Global and China regions from one interface
Best For
- Developers with an active Qoder subscription who want a unified DSH interface
- AI application builders relying on image input and multi-step tool-calling chains
- Teams managing model services across both Global and China regions
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.