dsh-subagent-model-router
Model-selectable subagents and guided model routing setup for DeepSeek Harness
31 results
Model-selectable subagents and guided model routing setup for DeepSeek Harness
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
DSH composer model seat with accessible per-provider collapsible groups.
DSH model-facing delegation tool that routes continuable/one-shot subagents to a model-selected LLM provider and model
DeepSeek Harness 前端插件:梁系强度滑动条 —— 用 6 档滑块替换输入框的模型与推理等级按钮(小难梁/牢梁/梁子/梁圣/梁神/梁祖),悬停时在进度条上方显示对应档位形象图,切换带交叉淡入淡出渐变
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
DSH web plugin: splits the composer model selector into two independent controls — a searchable, favorite-marking model dropdown and a reasoning-effort slider — plus Ctrl+P (cycle favorite models) and Ctrl+T (cycle reasoning effort) shortcuts.
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
DSH client plugin: collapsible model-provider groups in the composer model picker — click a provider row to fold or unfold its models
Global model command palette and provider/model configuration panel for DeepSeek Harness, with selective request retries, OpenRouter free-model import, loopback relays, online capacity presets, and optional media tools.
Provider-first model selector for the DeepSeek Harness model seat: pick a provider, then a model from that provider — current model always shows Model · Provider; search and hardening (v0.3.2, verified against DSH 0.1.1-rc.2).
DeepSeek Harness plugin: control which models appear in the model selector — per-model switches, provider-level batch toggles, and search. Hiding a model never touches your provider config or running sessions.
DSH plugin: exposes per-provider balance / coding-plan usage (5h window + weekly) in a status bar pinned to the native session-stats row.
Model selection as a three-level cascading menu (Provider -> Series -> Full model) plus thinking-intensity (reasoning effort) selection for the composer model seat.
A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.
DSH 供应商管理插件:在设置 → 模型页为每个供应商提供启用/禁用开关,禁用后该供应商的模型从输入框模型选择器和 /model 命令弹层中隐藏,且会话不会再调用该供应商的模型;模型选择器新增关键字搜索;供应商编辑卡片支持点击标题内联重命名。
DSH web UI 插件:把输入框官方「模型选择」控件替换为两个独立按钮(供应商选择 + 模型选择,两级联动),保留推理等级调节;只动这一处控件,不改 DSH 源码。
DeepSeek Harness 的增强模型选择器:单层菜单(搜索 + 分组)+ 底部内联推理强度(Effort)滑杆。
模型选择器美化:厂商官方图标 + 原生/识图/mv 三级分类 + 爱心置顶 + 置顶主力超时路由
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
DeepSeek Harness plugin: replace the model selector with one that shows real brand marks per provider (DeepSeek, Zhipu, Xiaomi, OpenCode Go…), so same-named models on different providers are never confused. Theme-adaptive, OpenCode-flavored.
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
DSH 子代理模型插件:在 composer 底部(官方模型菜单左侧)增加「子代理模型」菜单,为子代理独立配置 provider/model/推理强度/档位(与「设置 -> Agent 预设」同源:官方内置 + 插件预置的 轻量执行/只读研究 注册为真实用户预设 + 用户自建预设);主 agent 模型仍走官方管理。注册 delegate_subagent 工具让子代理真正使用配置的模型与档位,解决官方默认 subagent 与主模型同源造成的资源浪费。
DSH 插件:为模型选择器添加跨平台搜索过滤功能,支持商汤、百炼等所有配置的模型源。