dsh-plugin-thinking-size
Live reasoning-token badge — Think(5.2K) — on every Think disclosure row of the DSH web UI, ticking while streaming · 在 web 界面 Think 行标题后实时显示思考内容 token 数的 DeepSeek Harness 插件
52 results
Live reasoning-token badge — Think(5.2K) — on every Think disclosure row of the DSH web UI, ticking while streaming · 在 web 界面 Think 行标题后实时显示思考内容 token 数的 DeepSeek Harness 插件
DeepSeek 中转站(OpenAI 兼容网关)思考强度适配插件:让 UI 出现 Off/Low/High/Max 推理等级选项,并按中转站格式发送 reasoning_effort / thinking
Top-right widget counting 'let me' / 'we' / 'let's' / 'I'll' across all reasoning chains of the current conversation.
Message review (configurable multi-round cross review + auto summary + thinking-effort) + quote (Q&A chips) for the DSH conversation UI
DSH Web 三栏工作台:对话流只保留 AI 输出(工具调用/思考移入右侧面板),左侧工作区文件树带 git 状态徽标。Three-column workbench for the DSH web GUI: clean conversation flow, workspace file tree with git badges, and a live tool-call/think panel.
Hover timestamps for DSH web chat nodes — start–end (and duration) on Think, Bash and every tool/step row · 在 web 界面 hover Think/Bash 等会话节点行时显示开始-结束时间与用时的 DeepSeek Harness 插件
Per-turn thinking-token statistics for DeepSeek Harness, folded once by a durable session projection and read by the composer dock.
Lightweight personalisation for the DeepSeek Harness running-turn status line: rotating bilingual quips, six configurable loading icons and one-click theme-colour matching. A drop-in DSH web client plugin (bundle) with no dependencies and no build step.
Fold each DSH Web turn's thinking, tool calls and context into compact expandable process boxes cut at every piece of model text, and reuse the shipped turn-process disclosure row as the toggle whenever it exists.
Extra prompt slots (${provider} ${thinking} ${time} ...) for the official turtle-ui TUI of DeepSeek Harness
DeepSeek Harness web GUI: collapse the agent trajectory (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trajectory is default-collapsed after the final output completes (default on).
DSH web GUI plugin: auto-expand assistant reasoning (Think rows).
Easy-fold plugin for the dsh Web GUI: sticky Think fold row and fold scroll compensation for long expanded content
An Eason-themed floating desktop pet for the DeepSeek Harness Web UI: 18 Eason-only transparent animations (concert, coding, daily life), session-linked behavior mirroring the agent (thinking→coding, streaming→singing, tools→progress bar, waiting→peeking,
DSH bundle: plays distinct chimes in the Web UI on message received, thinking start, tool call, and turn end.
Declutter the DeepSeek Harness chat: hide agent execution-log rows (Think / context injection / tool calls), tighten message spacing and font sizes, wrap messages in rounded-corner bubbles, and inject an editable "reply concisely" instruction into the system prompt.
DeepSeek Harness web GUI: collapse the agent trace (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trace is default-collapsed after the final output completes (default on).
Model selection as a three-level cascading menu (Provider -> Series -> Full model) plus thinking-intensity (reasoning effort) selection for the composer model seat.
Auto-fold context/system messages in DSH conversation — hide the large system prompt / instructions by default, click to expand.
Jarvis blue-tech HUD skin for the DSH web GUI: deep blue-black palette, ice-cyan neon tokens, glass panels, HUD corners, and a breathing J.A.R.V.I.S. watermark that answers FOR YOU, SIR, ALWAYS while the agent thinks.
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。
Hide DSH 0.1.1-rc.2 thinking and tool-process rows in the Web UI.
A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.
Live execution status bar for the DeepSeek Harness web GUI: real-time activity (thinking tail, running tools, elapsed time) plus event-driven LLM achievement summaries with expandable structured detail reports.