Plugins

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

Pairs two DeepSeek Harness machines with a one-time code - directly on a LAN, or across networks through an end-to-end-encrypted relay with a zero-config official default - so one agent can run tasks and exchange files on the other while each machine keeps its own files in place.

Publish articles to CSDN / Juejin / CNBlog directly from the session, no external server.

Installs an image-input checkbox into the Models catalog so a custom model can declare image input and receive images directly; includes an optional BYO vision relay.

Run one deterministic skill-routing pass on every user instruction, so the skill catalog is consulted before the model answers instead of after it remembers. On the host it scores the live catalog from the instruction's keywords and the catalog metadata, with no LLM or embedding call, and appends a single producer-tagged message to the step: a ranked shortlist by default, the winning SKILL.md body once the score clears a threshold, or an instruction to call a named router skill exactly once. Unrelated instructions stay silent.

Adds a Session without workspace entry to the DSH Workspace picker, creates isolated date-organized directories, and keeps started sessions resumable under Ungrouped.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Cron task scheduler for DSH: on schedule, automatically creates a new session and injects your prompt as its first message, with task history and manual run/stop controls. Also runs KNJ workflows: pick files directly (stored as persistent snapshots, re-handed to the workflow on every fire) or reference them by path. Its sidebar entry is provided by dsh-knj-menu; install together: dsh plugin add dsh-scheduler dsh-knj-menu.

Manage the dsh service via `dsh --profile ctl`: systemd lifecycle (install, start, stop, restart, enable, disable, uninstall), persisted config, health probe and logs, plus shell completions and self-update.

Remote-SSH-style workspaces: turn an SSH host and a remote directory into a native DSH workspace; the agent operates the remote filesystem directly via 12 rw_* tools (SFTP/exec), with workspace-confined paths and known_hosts verification.

Kubernetes ops for the agent: get resources with structured JSON output, describe, logs, exec, apply/delete (user-confirmed) and port-forward.

Lets the DSH web UI attach files of any type as pathless @-mentions: pick a workspace file from the @ menu or drop one into the composer, and the agent reads it directly.

Model-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.

OpenAI-compatible image generation in DSH Desktop chat: generate inline, edit reference images or chain-edit previous results directly (image-to-image) without re-uploading, with storage cleanup.

Picks a random installed skin on every DeepSeek Harness launch and enables exactly that skin, with an on/off switch and a shuffle action inside the Skins settings page. Skins the running host would refuse to load are excluded, and a manual switch still applies until the next launch.

Multi-cluster Kubernetes management panel powered by local kubectl, with resource filtering, YAML editing, live Pod logs, interactive container terminals, workload restart/scaling, and DSH theme synchronization; accessible from the sidebar or session view. Requires DSH 0.2.0-rc.2.

Drive a DSH instance from another device: a host plugin opens a token-authenticated TCP port that a single-file Python CLI drives - listing and creating sessions, sending prompts with images, streaming replies, and switching models, permissions and workspaces.

Enumerate and control Windows top-level windows from WSL: activate, minimize, maximize, restore, move, resize, set always-on-top, close.

Read-only kubectl get / describe / logs / contexts for dsh on WSL (configurable log tail).

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

Policy plugin that gates kubectl by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.