370 results
DeepSeek Harness (dsh) bundle that routes the harness through the OpenLLM gateway — an `openllm` provider on the in-box pi-ai adapter (via the local daemon gateway) plus the OpenLLM MCP server. Pure config; install OpenLLM first (see README).
Global model command palette and provider/model configuration panel for DeepSeek Harness, with selective request retries, OpenRouter free-model import, loopback relays, online capacity presets, and optional media tools.
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.
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
DSH plugin: shows the DeepSeek account balance at the bottom of the sidebar, with a configuration card on the Plugins page.
DSH-native video understanding with configurable multimodal providers
DeepSeek Harness plugin: configurable keyboard shortcuts (settings UI + input history + approval/plan hotkeys)
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
DSH MCP manager — inspect, add, edit and remove MCP server configs in the profile patch; restarts are delegated to the host agent. · DSH MCP 管理器：查看/新增/编辑/删除 profile 中的 MCP server 配置，重启生效交由 agent 处理。
保险配置
One settings page for every plugin that opts in: declare fields, get a rendered form
Engineering verify gate for DeepSeek Harness: configured commands are authority; dirty receipts block conclude.
莉娅 DSH UI 润色插件：tapIndex 注入 CSS 统一加大圆角；radius 走 settings 配置（设置→插件→配置卡可编辑，保存即时生效），host config 为启动兜底。v0.3.1 修复 settingsScope 重复 bind 导致配置永不生效 + 覆盖样式被 host 默认压掉的层叠坑。
DSH Web GUI 个性化插件：背景图、遮罩浓度、半透明面板、主题色板、字体、滚动条、选中色、favicon 与标题自定义。
DSH (DeepSeek Harness) network plugin that bundles User-Agent rewriting, an HTTP/CONNECT/SOCKS5 proxy, and configurable request auto-retry for every outgoing global-fetch request, all configured from a single “网络设置” (Network) settings tab.
Evidence-backed production-readiness completion barrier for DeepSeek Harness with persistent operator-configurable control center.
Configurable OpenAI Responses-compatible native web search provider for DeepSeek Harness, with a Settings UI
Configurable Auto model routing tier for DeepSeek Harness
DeepSeek Harness plugin: bridge image-bearing messages to a user-configured OpenAI-compatible vision endpoint when the active text model cannot see images
Configurable skill discovery provider for DeepSeek Harness (DSH): cwd / project / ancestors / global layers plus editable parent dirs, with an install wizard to replace or coexist with dsh-skill-filesystem. Hot-pluggable — install via `dsh plugin --profile <name> add @sidleo3/skill-scan`.
Configurable model-request retry limit for DeepSeek Harness (Settings → General).
Local Claude Code provider for DeepSeek Harness: a configurable 'claude-code' LLM route that runs your locally installed `claude` CLI and streams its output into the harness
Correctly activate DeepSeek v4 flash on the Volcano Ark plan API for DeepSeek Harness: default config injection (ark provider + reasoningEfforts + reasoningEffort=max) plus an ark_plan_doctor self-check tool.
Route image-bearing turns to a configurable image-capable model for DeepSeek Harness