dsh-effort
DeepSeek Harness 插件:在 Web GUI 中选择模型的推理程度(reasoning effort)。按当前模型的适配器目录展示可选档位(如 Off / High / Max),一键写入会话的模型选择。
74 results
DeepSeek Harness 插件:在 Web GUI 中选择模型的推理程度(reasoning effort)。按当前模型的适配器目录展示可选档位(如 Off / High / Max),一键写入会话的模型选择。
DSH web GUI plugin: auto-expand assistant reasoning (Think rows).
A compact DSH model and reasoning quick-switcher showing the last three choices.
Effort bars for DeepSeek Harness — click signal-style sticks next to the model button to switch the reasoning effort instantly; the model menu opens straight to the searchable list.
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.
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.
DSH Web GUI: one-click expand/collapse all reasoning chains and tool chains in the current session (官方 repository-plugin 格式 / official bundle format)
DSH Web UI model seat: 3-level quick slider (low/medium/high, each preconfigured with model + reasoning effort), advanced model/effort picker, modality icons, and per-provider usage/balance display. DSH 模型选择器增强:低中高三档快切滑块 + 高级选择 + 模态图标 + 供应商用量显示。
Auto-expand / collapse the DSH conversation UI disclosure rows (Think reasoning, tool calls, todo, queue) from Settings. 思考・ツールコールなどの折りたたみを設定から選べるようにするプラグイン。
DSH 思考增强插件(EAC 定制版):思考与回复强制中文(system-prompt 注入)+ 界面硬编码英文中文化。已移除全部接管对话渲染器的显示功能,不再与折叠类插件(dsh-auto-collapse / dsh-turn-fold)抢占 assistant-step 座位。DSH web plugin (EAC fork): force Chinese agent thinking/replies + localize hard-coded UI labels, with all renderer-hijacking display features removed.
Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.
Ultra mode for DeepSeek Harness: a per-session effort tier that pins reasoning to max and activates an orchestration policy section, with a composer ULTRA chip and rainbow border in the web UI
Per-stage model routing for dsh-TUI: let subagents run on a different provider/model/reasoning-effort, configured in /settings (model-switch namespace), status via /model-switch.
DeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.
Adds a search field inside the model picker menu of the composer. Drop-in replacement for the native model seat, sharing the same per-session ModelDirectory so /model popup, the effort selector, and the /model command stay consistent.
Command palette for DeepSeek Harness (Cmd+K) — new chat, jump to session, switch model and reasoning effort, permissions, slash commands, theme, language and settings, all from one fuzzy-searchable bar.
DeepSeek Harness web UI plugin: floating API token usage, context pressure, reasoning-effort control, and cost estimation with official peak/off-peak pricing.
DeepSeek Harness 推理档位皮肤:把 @hytime/dsh-thinking-effort 的推理等级控件重绘成蓝紫渐变、带星点与流光的档位条。 / A skin for the DSH reasoning-tier control: a blue→violet pill with a starfield and a sheen sweep.
A reasoning-effort dial for the DeepSeek Harness composer: a violet particle field with meteors, magnetic level anchors and an eased circular thumb.
Frontend-injected per-model reasoning-effort (thinking strength) configuration for custom pi-ai providers. Registers a per-model 思考强度 editor into the Settings -> Models provider card and persists reasoningEfforts through the settings Remote.
Model selection as a three-level cascading menu (Provider -> Series -> Full model) plus thinking-intensity (reasoning effort) selection for the composer model seat.
Personal usage analytics & activity dashboard for the DeepSeek Harness (dsh) web GUI: token totals, session activity, GitHub-style contribution heatmap, model / reasoning-effort / tool / skill / plugin rankings, streaks and insights. Aggregates real session events through ctx.sessionPersistence; no dsh core changes, no prompt content leaves the machine.
Allowlisted subagent routing for DeepSeek Harness: the calling agent dynamically chooses a configured model and exact reasoning effort per delegation.
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).