Plugins

Kimi Coding web search and web fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams (POST /v1/search and /v1/fetch), a settings card in the GUI stores it via the credentials service, and the fallback chain reads the Kimi CLI config for zero-setup installs.

Gives read-only advice for Windows .wslconfig memory and mirrored networking.

Text-to-image and image-to-image generation via OpenRouter's unified Image API: configurable model aliases with parameters gated against the live model capability listing, reference-image inputs, a settings card, and inline chat display of results.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.

Hard-stops further tool calls after a configurable per-session budget is reached.

Code RAG semantic index panel and settings card: live index bar with start/rebuild/cancel, plus one-click detection and configuration.

Configurable web search for DeepSeek Harness using SearXNG, Wikipedia, Tavily, Brave, or Gemini, with per-client engine selection and bounded retries.

Compact DSH wallet panel for any Sub2API-compatible third-party balance site. Uses /v1/usage with a long-lived API Key, auto-discovers configured providers, and shows balance plus daily usage.

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).

Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retries, capacity presets, and optional OpenRouter image/video generation tools.

Single-password authentication gate for the dsh web surface: configurable session validity, Ctrl+Shift+L lock, CLI password management, brute-force lockout, in-UI password controls.

TickTick (滴答清单) daily task dispatcher: an interval timer pulls due tasks from a chosen list into a Markdown task file and notifies only when the task set changes (WeChat via ClawBot / flomo / macOS); it can also auto-execute each task in its own headless DSH session under a configurable timeout, optionally gated to DeepSeek's off-peak hours so peak-time work queues to the next off-peak window instead of starting, plus a settings panel for the deferred write-back queue and dispatcher_status / dispatcher_config / dispatcher_run / dispatcher_report tools.

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

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.

Model visibility manager for DeepSeek Harness: hide or show any model in the conversation model selector from a dedicated settings page. Per-model switches, search, provider-level batch actions, reset-all. Zero intrusion - writes only its own hidden list, never the provider config; hiding a model in use never interrupts a running session.

SOP-driven business Agent Teams for DeepSeek Harness: configurable captain/member agents, human- or agent-defined SOP workflows (nodes, dependencies, quality gates, manual gates), event-driven task scheduling, and a web dashboard (SOP canvas, run board, a

DSH 服务控制：给 dsh 命令一对翅膀——`dsh --profile ctl` 管理服务的 systemd 生命周期、配置与诊断。 / DSH service control: wings for the dsh command — manage the service's systemd lifecycle, config and diagnostics via `dsh --profile ctl`.

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.

Configurable VS Code style keyboard shortcuts for the DSH web GUI, with a settings-page keybinding editor, conflict detection and JSON import/export.

Web-UI-Plugin, das die Think- und Tool-Aufrufe jeder gestaffelten Antwort in pro Segment begrenzte, scrollbare Schiebefenster mit konfigurierbarer Höhe faltet, sodass jede Zwischenantwort sichtbar bleibt.

run_command im Antigravity-Stil für DSH: Kurze Befehle kehren innerhalb eines konfigurierbaren Wartefensters inline zurück (Standard 10s), während längere automatisch in ctx.jobs übergehen, um später eingesammelt zu werden und Abschlussbenachrichtigungen zu erhalten — ausgeführt über ctx.shell innerhalb der Sitzungs-Sandbox und der Genehmigungspipeline.

Scannt in Claude Code, Codex und CodeBuddy konfigurierte MCP-Server und prüft die tatsächliche Konnektivität über stdio- und streamable-http-Initialize-Handshakes, mit Ein-/Aus-Schaltern und einem /mcp-Kontrollpanel.