dsh-model-router：DeepSeek Harness 任务感知型模型路由
DeepSeek Harness 插件 `dsh-model-router` 旨在实现“一切皆插件”，通过任务感知智能路由模型。它根据任务类型（如研究或闲聊）和模型能力，自动调度请求至最优模型，优先保证研究质量或使用免费模型处理闲聊。该插件支持 Grok 限制、速率限制处理、子代理及模式切换，提供 dryRun 验证和详细日志，有效简化了智能体模型维护。
Read Moredsh-model-router: Adding Role Routing to DeepSeek Harness
`dsh-model-router` is a plugin for DeepSeek Harness that addresses the limitation of treating all model calls uniformly by dividing agents into two roles: “planner” and “executor.” The planner is responsible for reasoning and delegation, while the executor handles specific tasks. The plugin implements this through request routing, prompt injection, and skill packs, and provides vision routing to handle image requests. It supports configuration via a GUI or configuration files, and defaults to using the Flash model to reduce costs.
Read Moredsh-model-router: Add virtual model providers to DSH and route requests based on active providers.
`dsh-model-router` is a community plugin for DSH designed to address management pain points in multi-provider and multi-model configurations. By registering a virtual provider named `model-router`, it aggregates models scattered across various providers into a single selector, supporting strict merging based on model IDs. Users can view the available providers for each model in the model selection menu or settings card, and support one-click switching of the currently active provider as well as drag-and-drop adjustment of priority order. The plugin adopts a real-time routing mechanism, preserving the virtual provider identifier within the session and resolving/delegating to the currently active real provider only when an LLM request is issued, ensuring consistent routing logic for main agents, sub-agents, and tool calls. The plugin features automatic synchronization capabilities, allowing it to automatically clean up configurations and fall back to active states when new providers or models are added or removed. It is suitable for Web, C...
Read Moredsh-model-router: A Thin Routing Strategy Plugin for DeepSeek Harness (DSH)
dsh-model-router is a thin routing policy plugin for DeepSeek Harness (DSH), version v0.2.2, licensed under the MIT License. It adds rule execution on top of DSH's existing model management, with core features including deterministic keyword routing, the whitelist-based model switching tool `model_route` that is disabled by default, and an isolated Beta image generation channel `image_gen`. Routing rules are executed in configuration order, stopping at the first match, while preserving the current state if no rule matches; model switching requires precise validation of provider, model, and other fields. `image_gen` uses an OpenAI-compatible endpoint, enforces HTTPS and strictly restricts result downloads, and supports integration with third-party services such as Seedream; however, video, audio, and 3D features are not included.
Read Moredsh-model-router: Model Routing and Cost Dashboard for DeepSeek Harness
`dsh-model-router` is a model routing and cost optimization plugin for DeepSeek Harness. It routes simple requests to cheaper models through heuristic rules, reserves complex requests for the main model, and automatically falls back on instantaneous failures. This approach reduces costs while ensuring quality for requests requiring context, vision, or reasoning capabilities. The plugin supports vision-aware routing, prioritizing available vision models if messages contain images, and respects user-selected models. In automatic mode, it prompts the user for a quick response when a simple request is detected. Additionally, it provides a real-time panel in the Composer Dock, displaying token usage, cache hits, and estimated costs based on the pricing table. Installation requires ensuring the `dsh` CLI is in the PATH, followed by restarting the Web profile.
Read More