dsh-open-with
Open registered DeepSeek Harness workspaces in detected or configured local editors from the Web GUI
94 results
Open registered DeepSeek Harness workspaces in detected or configured local editors from the Web GUI
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。
DSH plugin: a virtual model-router provider that aggregates every configured provider and model, routes each request to the model's currently active provider, and ships a settings page for per-model provider ordering and switching.
DSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default, and automatically route requests that carry image content to a configured vision-capable model (deepseek-v4-flash-vision-exp) 鈥?no manual model switching (periscope).
Steno — inline shorthand expansion plugin for dsh. Type #tag in a message and it is replaced with the configured text before sending.
Configure model input capabilities and reasoning efforts for DeepSeek Harness
DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.
DSH web plugin: per-workspace quick commands. Configure named shell commands per DSH workspace, run one from the session header with live stdout/stderr in a floating popup.
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
在每次会话开头固定注入一段用户配置的文本上下文(设置页输入框可编辑),作为模型可见的 instructions 注入第一轮请求。 | Injects a user-configured text block as model-visible instructions context at the start of every DSH session (editable from the settings page).
Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.
Widget Center for DSH: manages multiple native desktop widget instances (shares quotes, notes) — each an independent NSPanel window, configured as instance cards in the DSH settings UI, with the market_quote model tool.
DeepSeek Harness plugin: typeset LaTeX as font-free SVG/PNG images, draw geometry and function figures from a declarative spec, convert formulas or SVG into embeddable images, and assemble documents with those images inserted
Preconfigured DeepSeek Harness bundle that mounts the AlgoVault MCP server: composite BUY/SELL/HOLD trade calls, market regime, and cross-venue funding arbitrage for perpetual futures.
AI4Scholar for DeepSeek Harness (dsh): 38 native academic tools — Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI resolution, PDF full text, auto-cite, scientific figures, credit balance — with an API-key card in the Web UI settings.
flomo (浮墨笔记) integration for DeepSeek Harness: configure your flomo API URL / API Key in the web settings panel, then let any agent send notes, memos, and summaries straight into flomo via the flomo_send tool
Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes
IM bot notifications for dsh-TUI: push long-turn completion and approval requests to a 飞书/钉钉/企业微信/generic webhook, configured in /settings (webhook namespace), status via /webhook.
One-click provider/model switcher for the DeepSeek Harness web GUI: a session-header action that lists every configured provider and its models and switches the session in a single click.
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.
Unified real-time quota dashboard for DeepSeek Harness: OpenCodeGo windows, DeepSeek balance, OpenRouter credits, SiliconFlow and Moonshot balances in one collapsible panel — auto-detects configured credentials, no keys leave the host.
A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.