Plugins

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

Document-code consistency guard: audits version headers / changelog tables / directory trees / module & test counts / cross-doc references for drift, with severity-sorted, read-only fix suggestions.

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

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.

Registers a `config_doctor` tool that checks the harness's own configuration for problems that boot silently: fields a patch dropped by whole-config replacement, patches targeting missing entry ids, and tool-name collisions. Read-only.

Automatic type-check diagnostics: after the model edits or creates TS files, runs `tsc --noEmit` in the background (debounced per project) and reports errors via the `code_check` tool — grouped by file with line/column, severity and TS error codes, closing the "edit → check → fix" loop.

Real-time stage, ETA & cost dashboard for headless dsh tasks: turns the black-box session event stream into a live multi-task grid (cordis plugin + standalone local dashboard, no API calls).

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.

Bidirectional Feishu/Lark channel for DeepSeek Harness: persistent conversations, true streaming replies, 40 MCP Feishu tools, slash commands, and an IM-bot status tab in the plugin settings.

Code smell radar: statically scans TODO/FIXME debt, stub implementations, long lines, oversized files and duplicated blocks, with severity-sorted read-only fix suggestions.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Exact-profile control of your real logged-in Chrome browser: an MCP server plus MV3 extension and authenticated localhost bridge for tabs, locators, file injection, media export, and durable scroll capture, with no debug profile or remote-debugging port.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Create a one-click Windows desktop shortcut from the Settings page: a .cmd launcher + desktop icon for DeepSeek Harness or any local server, auto-opens the browser, with taskbar pin hints.

Trending-topics collector aggregating Baidu / Toutiao / Douyin / Weibo hot lists in one call (Weibo optional cookie), returning titles with heat values for content creators — tool: `sxs_news_hot`.

Jira Cloud issue-tracker integration exposing eight model tools for issue search, project and transition lookup, creation, updates, comments, and transitions; writes are opt-in and support dry-run.

Measures design rules on the rendered page rather than in the CSS — type-scale count, WCAG AA contrast against the real composited backdrop, spacing-grid drift, palette size, tap targets, and the tells of generated UI such as violet gradients caught by hue angle; ships a design-system skill.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

Zhihu (知乎) dashboard: hot list with trend arrows, follow feed (favorites/creations/followees), post tracking (question/keyword/person) with auto-briefs, and five agent tools (zhihu_search/hot/answer/global_search/followees).

Auto-discovers model listings, pricing and capabilities from OpenAI-compatible API hosts, normalizes them, and emits ready-to-use model configs for dsh.