Plugins

Routes DeepSeek Harness outbound traffic through a local Clash proxy, with automatic fallback to direct when the proxy is off.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

DeepSeek account balance in the sidebar footer plus spend per session, today, this month and all time, priced by a configurable time-of-day price table per currency (DeepSeek CNY/USD defaults included). Two read-only remote methods, no host routes, key read through the host credentials seam on every call, egress only to the configured provider origin.

Quote earlier content of the current session into the composer: select text in any message for a Quote pill, or type @ to pick a whole message; the quote travels as a native reference chip and is serialized into the prompt as a blockquote. Client-only, no host routes, no custom session events.

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Planner/executor delegation with named roles: a strong planner steers, disposable executor sub-agents (per-role routes and prompts) implement. Default role plus per-delegation override, a global reasoning-effort knob in the composer chip, and a settings page for role management.

Connects a Feishu self-built app over WebSocket, routes each chat to an independent DSH agent session, and streams replies through a Card JSON 2.0 card with plain-text fallback.

Centro de memoria y conocimiento de DeepSeek Harness que enruta llamadas de actualización, recuperación y suscripción entre plugins compatibles, con un backend opcional transaccional en Rust.

Enruta las imágenes del chat a un modelo de visión fijo compatible con OpenAI, devuelve observaciones factuales al modelo principal seleccionado y reutiliza las observaciones por sesión a través de repeticiones, compactación y reinicios.

Make DSH llm-pi-ai opencode routes pass Zen free-tier gate: opencode User-Agent + canonical ses_ session + bash/read tools. Scoped to opencode.ai only.

Routes eight DSH lifecycle events through dedup, quiet hours and digest batching into seven channels. Severity maps to the fields Bark, ntfy, Telegram and webhooks actually support; failed deliveries retry with jittered backoff and survive a restart; per-channel circuit breakers stop hammering a dead endpoint; and a self-check reports a degraded relay instead of going silent.

Fixes the Windows workspace-open action. The shipped opener runs `explorer.exe "<file:// URI>"`, which on some hosts reports success without raising a window — the exit-code verdict cannot tell an opened window from nothing happening. This routes that one action to `explorer.exe /e,<dir>`, which raises a window reliably, and leaves every other application in the menu on the shipped path.

Extra LLM provider routes for DeepSeek Harness: OpenCode Go with per-session x-opencode-session routing, and OpenAI Codex over ChatGPT-subscription OAuth.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

Four right-Sidebar panels for the dsh web client — an artifacts browser, long-term memory, a terminal and notes — paired two per tab with a draggable split, so two panes show all four at once. Ships the host half as well: nine memory_* tools, artifacts_list, the /memory command, the /api/artifacts/* and /api/terminal-notes/* routes. The terminal runs one bash command per line, with a 120-second deadline and a stop button. Requires dsh 0.1.5 or newer, which is where the right Sidebar replaced the old details column.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

Auto-switch DeepSeek models: routes every request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual overrides.

Grouped provider and manufacturer model selector for DeepSeek Harness, preserving provider/model routes and reasoning levels.

Shows MiniMax Token Plan usage in the Settings page through webServer routes and reads either subscription key name from environment or credentials file.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Audits every plugin HTTP route in a profile for a browser-trust fence: plugin routes win the web server's longest-prefix match ahead of the /api gateway, so they never see its trust check and must pin the Host to loopback themselves. Grades PASS/WARN/FAIL per route and fails a fence that compares Origin to Host without pinning it (bypassable by DNS rebinding). Ships as a CLI for CI and a route_fence_scan tool.

Product-thinking companion for DeepSeek Harness: clarifies negative boundaries first, separates facts from assumptions, routes through seven product lenses, and persists confirmed decisions to project memory.

Tree-shaped Markdown knowledge base for DSH agents: kb_list/kb_read/kb_write tools, tree/node HTTP routes, and a browser panel companion.

GLM (Zhipu bigmodel) web search provider - routes ctx.web search through Zhipu's Anthropic-compatible endpoint with the native web_search server tool, billing your existing GLM quota or Coding Plan instead of the DeepSeek platform. Includes a translation layer for Zhipu's non-standard tool_result response layout.