Plugins

终端面板：在当前工作区敲命令、看实时输出，多标签页、Tab 补全、Ctrl+C 中断。Terminal panel for DeepSeek Harness: run commands with streaming output, tabs, completion.

DeepSeek Harness plugin: /backup, /backup-list and /backup-restore commands to back up, list and restore the DSH home directory. DeepSeek Harness 备份插件：一键备份 DSH 主目录（~/.dsh）为时间戳 tar.gz 归档、查看历史备份并恢复。

Terminal plugin — a real shell, workspace sync, persistent state, common-command management, and command completion.

Backup and migrate DeepSeek Harness plugin environments via GitHub: one command exports the installed plugin manifest, plugin configs and locally-developed plugin sources into a git repository, and another restores everything on a new machine (VSCode-sett

DSH 插件（用量中心）：常驻用量卡片 · 多提供方用量/余额查询（OpenCode Go 订阅 + DeepSeek 余额 + Command Code 订阅/余额，对齐 cc-switch 查询语义）

Web management panel for Docker on DeepSeek Harness: manages Docker MCP servers (deploy/remove, official catalog search/pull, gateway start-stop-restart, custom deploy) and containers/images (list, start/stop/restart, remove, logs, inspect, interactive terminal, create, pull, build, load) across local CLI and SSH remote targets with one-click switching. Credentials are encrypted with Windows DPAPI, HTTP is loopback-only, and command parameters are whitelist-filtered. Build-free pure ESM; client is zero-dependency.

Two-way agent bridge for Feishu (Lark) and DingTalk groups: chat with a DeepSeek Harness agent from IM groups via long-connection / Stream Mode — no public port needed. Workspace selection/creation, session switching, archiving (synced with DSH GUI), configurable from the DSH settings page. Feishu uses interactive cards, DingTalk uses text commands.

A DeepSeek Harness Web plugin that runs a user-defined command after the web profile has started successfully.

Rolling, integrity-verified backups of each session at turn boundaries: verifies the log still loads before promoting a snapshot, never overwrites the last good one when a turn ends corrupt, and restores in one command even when dsh will not boot.

Makes ctx.logger output visible: a /logs chat command over a full-capture ring (level, name, grep, since filters) plus a default-on stderr exporter for warnings and errors, configurable per plugin; works headless. Also documents that dsh's default log buffer silently drops warn and debug records.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

DeepSeek Harness plugin: per-day token usage statistics — 13-week heatmap, stacked daily chart, /token-usage command

Tools guard that moves agent-issued `rm` targets to the macOS Trash instead of deleting, with a shell-aware lexer covering compound and disguised commands; a switch in Settings → General turns it off.

Background security auditor for DeepSeek Harness: scans agent outputs for secret leakage, checks command safety before execution, and surfaces findings in a persistent audit log.

WSL (Windows Subsystem for Linux) bridge for DeepSeek Harness: run Linux commands, manage distros, convert paths, and copy across the Windows/Linux boundary.

Quality suite: background tsc --noEmit diagnostics fed back after the agent edits TypeScript, plus a /code-review command running five parallel review lenses with confidence scoring; absorbs dsh-code-check and dsh-command-code-review.

Claude Code style /init command and tool that writes a minimal CLAUDE.md and symlinks AGENTS.md to it.

Realtime Avatar (realtimeavatar.ai) for agents: the developer API key held by the harness credentials store, the public docs as five on-demand skills, rta_* tools over the public REST API (balance, avatars, clips, sessions, usage) with approval-gated credit spending, and a /rta command that walks a developer from no key to a live avatar call.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Layered syntax highlighting for bash/pwsh command and read code output in the DSH web GUI (VS Code Dark+ palette: keywords/strings/numbers/functions/comments each get a color); colors only what it recognizes, keeps tables/logs plain; pure frontend, zero token overhead.

Background memory consolidation (auto dream) for DeepSeek Harness: periodically reviews recent sessions and existing memories to dedupe, refresh stale entries, remove contradictions and rebuild the MEMORY.md index, with hybrid/volume auto triggers, /dream command and a settings-panel config card.

File-change diff bar with keep/undo summary, plus dangerous-command approval and red highlighting for bash/pwsh.

Scan project lockfiles (npm/pnpm/yarn/pip/go/cargo/maven/gradle/...) against the free OSV API and report confirmed dependency vulnerabilities with fix versions and remediation commands.

Export a DSH session log as a clean chat log: stream fragments folded into normal messages, every other event kept verbatim. /chat command + browser-download button.