Plugins

img2img-studio 的 GUI 插件（一个包两个面）：① 输入框里的图片编辑器（编号标记 / 移除背景 / 涂抹擦除 / 调整大小，支持键盘操作与裁切遮罩预览）；② 设置页「识图与生图」供应商面板（供应商目录选择 + 脚本扫描标注、账号库驱动 chatgpt-web 通道、每行测试/试跑/复制命令、保存前预览、余额探测；中/英双语），保存即写回两个 skill 的 scripts/.env

Right-click any attachment or path in the transcript and hand it to your own action: send it to a WeChat contact, open it in Chrome, or anything else you configure — one right-click, anything you want. Ships with quote-into-composer, reveal in the OS file manager, copy path and Send to…, and lets you add your own entries (command, open with, shortcut, link, PowerShell). Menus are drawn in the app's own style, never the system one.

Per-session execution gears for the DSH composer: an OVERDRIVE toggle turns Turbo on for the current session only, the Fast and Max gears swap the agent's planning and verification policy and may lower the request's reasoning effort, and the Host keeps the authoritative mode plus per-turn latency, step count, tool calls and whether a verification command ran.

A whale-maid with a jar, sitting in the corner of your DSH window. She goes exploring on Bilibili for whatever you are into, ranks by like, coin and favourite rate rather than view count, and brings back pickled snacks that suit your taste. When a term runs dry she takes another route. Five picks go into the jar, and she tells you what each video is about. News-type axes keep only the last two weeks; game guides and music have no limit, and each axis decides for itself.

Switchable backends behind the native web_search and web_fetch, chosen per session from a composer menu or /setup-search and /setup-fetch: DeepSeek, Exa, Firecrawl, Tavily, Tinyfish, OpenAlex, Semantic Scholar and server-side model search for search; local HTTP with a private-network allowlist, the DeepSeek Fetch API, Exa, Firecrawl, Tavily and Tinyfish for fetch.

Vision-first Mac computer use, for when the accessibility tree is unavailable. Ships 11 desktop_* tools - window list, screenshots, OCR text targeting, numbered elements, coordinate clicks, typing, scrolling, drag - plus a Codex-style cursor overlay with spring animation. Clicks are delivered to the target process, so the real pointer never moves and nothing steals focus. In DSH it shows up as Mac Desktop Control with a settings page that checks the engine and the Screen Recording / Accessibility permissions, with a button that opens the matching System Settings pane. Works out of the box: the tarball bundles the dsh-cu engine and the overlay as prebuilt universal binaries (Apple silicon + Intel, macOS 11+, ad-hoc signed), compiled from the repo's Swift sources by the release workflow - no clone, no Xcode, no install.sh. The only setup is granting DeepSeek Harness Screen Recording and Accessibility once. macOS only; on Windows and Linux the plugin loads without registering the desktop tools.

Adds two UI surfaces: a composer image editor (numbered marks with per-mark instructions, background removal, brush-mask erase, resize with crop/padding preview, keyboard-accessible markers; results return as attachments plus a version-1 manifest) and a Settings → vision/generation provider panel (explicit provider picker, providerId normalization, ChatGPT-web accounts synced into channels, per-channel test/try-run/copy-command, script readiness scan, save validation with .env preview, probing that only disables on explicit quota errors, Chinese/English UI) that writes providers back to the skills .env files.

Reusable Agent Team presets for DeepSeek Harness: a Settings page stores named Teams — a captain with its own prompt and tool allow-list, plus members carrying their own provider/model route, reasoning effort, prompt and tools — and a composer control applies one Team to the current Session, installing the captain prompt and registering the spawn_team_member, get_team_preset and update_team_preset tools.

Codex-style context window auto-management for DeepSeek Harness: a lossless rollover engine with zero summarization model calls, task-oriented handoff anchors, working notes that survive compaction, verbatim recall of archived windows, and a stale-notes gate that downgrades to an explicit warning instead of vouching for outdated notes. One-click composer button plus /smart-compact command, three-band automatic rollover, mandatory anchor sanitization; works out of the box with zero configuration.

Turns a one-line DSH draft into a complete task brief (role / goal / constraints / output format). The engine is a byte-verified port of linshenkx/prompt-optimizer (three modes, 10 templates identical to upstream); history is consent-gated with version chains and structural comparison; every run reports its token usage. Nothing is written back or sent without a click.

A right-sidebar job panel for the dsh web GUI: click a row in the background-jobs popover to inspect the command, follow its terminal output (iterm2-style bounded scrollback), and stop it.

Codex-style drag-drop: drag any file into the DSH web GUI, it lands in ~/.dsh-dropbox, and the path is inserted into the composer as a whole blue chip.

css-in-js styling kit (styled / Token / Styling) for the forked conversation UI: consumes the official --dsw-* design tokens, so no CSS Modules precompile step is needed.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Supervises a local workbuddy2api gateway process and exposes its models as an LLM provider, reading context windows and reasoning efforts from the gateway's own model endpoint.

An opencode-inspired terminal UI for DeepSeek Harness that boots as a dsh profile app plugin, with a session sidebar, streaming chat, markdown tool cards, todo lists, slash-command suggestions, a telemetry footer with a context meter and inline approval prompts.

Tool-call discipline for DeepSeek Harness with behavior prompts, failure-driven concurrency reduction and retry guidance, post-write checks with backup rollback, high-risk command gates, change summaries and verification reminders, advisory project-memory checks, configurable project-discipline reminders after compaction or at intervals, and compliance statistics.

Adds a Web composer switch between the native DSH agent and Grok Build, proxying Grok Build sessions and slash commands through ACP.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Personalization for the agent: a Web UI panel (about-you, reply style & tone, traits for headings/lists and emoji, output language, custom instructions) and `/soul` commands, with nickname/occupation/bio/style/traits/language compiled into a system prompt and re-injected into active sessions. Exposes `soulConfig` for other plugins and a `set_persona` tool the agent can call.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

eDEX-UI-style shell over the DSH web GUI: system-telemetry left bar with per-core CPU sparklines, encom-globe world-map right bar with up/down traffic chart, filesystem browser with file preview, and a terminal-styled composer that follows the active workspace.

Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.