@deepseek-ai/dsh-client-ui-annotator
Message Annotator for DeepSeek Harness: stage numbered quote+comment annotations on assistant messages (selection floating trigger + per-message action), then send them aligned and together to the agent
69 results
Message Annotator for DeepSeek Harness: stage numbered quote+comment annotations on assistant messages (selection floating trigger + per-message action), then send them aligned and together to the agent
Animated reasoning-level slider for DeepSeek Harness model selection.
DSH plugin: select text (划词) in a conversation, then quote it into the composer or reply in a new window.
Adds an 'Invert selection' button to the fetch-models dialog of the Models settings section
Remote multi-server GPU status board for DeepSeek Harness Web: read-only nvidia-smi over SSH with ControlMaster-muxed connections, a host-side cached snapshot, per-server selection, and gpu_overview / gpu_refresh agent tools.
Semantic, configurable chat titles for DeepSeek Harness with model selection and one-click regeneration
Auto model selection for DeepSeek Harness: routes each turn to V4 Flash or V4 Pro through a classifier call
Reusable prompt profiles with per-turn model selection for DeepSeek Harness
DeepSeek Harness client plugin: adds an 'Invert selection' button to the fetch-models dialog of the Models settings section, so only the rows that are already in the model list stay checked on a second fetch + add pass.
Youdao-style word-selection translation for the DSH web GUI. Select text anywhere, click the floating button, get a translation from the harness's own LLM — no API keys, no third-party endpoints. 有道风格划词翻译:DSH Web GUI 里划选文本即现悬浮翻译按钮,点击由 harness 自带大模型翻译,无需 API key、不依赖第三方接口。
DeepSeek Harness bundle: inject the user's IDE context (open editors + current selection) into each turn, via the Claude Code IDE WebSocket bridge (IntelliJ IDEA & VS Code).
Plug-in vision for text-only LLMs — a DeepSeek Harness (dsh) fork of ModLens adding multi-engine support (Gemini, Volcengine Ark/Doubao, Claude) and per-call engine selection
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
DeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs
Enhanced DSH subagent tools with per-call model and reasoning-effort selection
DeepSeek Harness-native Roblox Studio MCP companion: Settings UI listing connected Studio instances, active-instance selection exposed to the agent as runtime context, plus live visibility into Studio's official Script Sync and agent guidance for file-first editing.
Selection toolbar for the DSH web UI: quote (expandable markers in the composer), temp chat (in-page context-free panel), web ask (chat.deepseek.com popup with ?q= prefill)
DSH dual-face plugin: font family and ligature controls for the Web UI. Host half registers a settings namespace; browser half renders the config card in Settings > Plugins with system-font selection and applies the fonts live. Bundle + dsh.client package.
Add selected DSH assistant text to the composer as a structured reference.
Native Auto Review for DeepSeek Harness with automatic host compatibility selection
Ask about selected assistant text in an ephemeral DSH Web sidebar using a snapshot of the main conversation.
Optional workspace selection + workspace-free temporary sessions for DeepSeek Harness Web (dsh).
DSH better-sidebar plugin: read paper PDFs and translate a selection with the LLM, contextual and isolated from the main conversation.
DSH client plugin: collapsible model-provider groups in the composer model picker — click a provider row to fold or unfold its models