Plugins

A draggable mascot invites you to play Xiangqi (Chinese chess) while the AI thinks, with a built-in engine, move-record export, and optional multi-model commentary.

Dynamic Schulte grid waiting-time mini-game: click 1..N in order on a static grid or a spinning roulette wheel while the model thinks.

Draggable floating cat-or-dog companion for the dsh web GUI that changes expression with the session and is configured on a Companion settings page.

Pull a 3D lever next to the send button and turn the model's reasoning signals into a pixel-art gacha reveal.

Steam-style plugin storefront: a plugin registry browsable inside DSH with one-click install, uninstall and update, plus a zero-dependency CLI and agent-callable market tools.

Turns a stated need into a plugin choice: an agent skill that queries a catalog of the whole `dsh-plugin` topic (2600+ repos, recrawled every 6 hours, Chinese descriptions from Workers AI) through a ranked search API, then hands back the matching `dsh plugin add` command.

Plugin center for DeepSeek Harness: installed-plugin metadata, a community market with stars and versions, one-click install and update, and a What's New dialog.

A plugin market for DeepSeek Harness: search and one-click install GitHub dsh-plugin plugins straight from the web GUI.

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

Conversation header badge showing the DeepSeek Harness version, checking npm for the latest release and prompting upgrades.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Keeps what the agent builds at runtime: turns a `cordis_define` dynamic package into a real installed plugin that survives restart, writing the bundle and registering the profile layer with no pnpm, no network, and no build authorization.

Reloads an upgraded plugin inside the running dsh process instead of restarting it, and rolls back to the old version when a reload fails.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history and maintain a quarantine manifest.

Complement to official Creator mode: stage, validate, live-mount via ctx.plugin, score, and solidify or roll back in-memory tool-plugin trials.

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

Hands standalone jobs to the Cursor CLI signed in on the same machine, with child-model settings and a read-only connectivity test.

Manage and organize your agent skills by category, tags and collections in DeepSeek Harness, with a settings panel and a slash-command folder picker.

Self-healing runtime layer: a resource control loop with strategy switching and repair escalation, error-storm and fiber-failure insight, cross-session knowledge carry-over, a self-healing dashboard and 7 tools.

Collapsible right-docked web terminal (xterm.js) bridged to a host PTY over WebSocket: bash/zsh switching, resizable panel, and fold/unfold that keeps the session alive.

Docker-isolated real-host lifecycle tests for DSH plugins across install, boot, tool registration, update, uninstall, reinstall, and recovery, with structured evidence.