98 results
Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.
DSH web sidebar foot ordering: force the sidebar.footer.action slot into a vertical stack (display: contents → flex column), configure entry order (including the settings row under id `settings`), and manage layout, gap, align, and item order within settingsArea.
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
DeepSeek Harness settings page: cap every configured model service to a working context window, clamped to what each model can actually hold
DeepSeek Harness host plugin: serves a configured workspace/media folder over the web server under /media, so any conversation can display local images by referencing http://<host>:<port>/media/<relative-path>.
Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。
DeepSeek Harness plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.
Host-only custom agent preset editor via the /preset-composer slash command: name, description, preset prompt, skills, and plugins. A client UI (child-slot configure button) is reserved for future DSH support of out-of-tree client bundles.
A paper-review panel for the DeepSeek Harness: converts PDF papers into structured, selectable text (columns, headings, tables, sub/superscripts, table of contents) with figure and display-equation rendering, a floating ask-about-the-selection dialog, and per-project paper stores under a Paper workspace.
dsh plugin bundle porting the rpiv advisor subsystem: an on-demand zero-parameter advisor() tool that forwards the full session to a separately-configured reviewer model and returns a plan, correction, or stop signal.
Provider/model fallback chain plugin for DeepSeek Harness — when the current model fails with an eligible error code (e.g. RATE_LIMIT or QUOTA), the agent loop automatically retries with the next provider/model in the configured chain.
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.
Steno — inline shorthand expansion plugin for dsh. Type #tag in a message and it is replaced with the configured text before sending.
DeepSeek Harness plugin: bridge image-bearing messages to a user-configured OpenAI-compatible vision endpoint when the active text model cannot see images
The omdsh plugin hub: a Settings tab that installs, disables and configures omdsh plugins from a configurable upstream, from the settings schema each already registers
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
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由：三级难度 + 视觉自动路由，模型从「设置-模型」已配置模型中选取，虚拟 smart 模型零配置接入。
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。
Configure model input capabilities and reasoning efforts for DeepSeek Harness
Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes
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.
Turn a paper into an academic talk for DeepSeek Harness (dsh) — 论文转 PPT / 组会汇报 / 会议报告 / 答辩 / 开题. Reads the real full text, budgets the slot per venue, and builds the deck around the figures with the speaker notes written as the script. Drives dsh-ai4scholar and dsh-slides.
A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.
丘吉尔