Plugins

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Beginner panel for DeepSeek Harness: routes a plain-language request into ready-to-use plans (prompt variants, matching skills, advanced moves) with a local keyword engine and fills the chosen plan into a new session in one click.

Real-time LSP diagnostics loop: lsp_diagnostics / lsp_workspace_errors / lsp_hover tools over headless stdio language servers (TypeScript/JavaScript + Python), plus an auto-injected post-edit diagnostics delta wired to the harness fs/observed event — Cursor-style edit → diagnostics → fix for dsh agents.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Plan review enhancement for DeepSeek Harness Web: reply to the plan-review card inline to have the model revise the plan, and browse, compare, edit and archive every plan version in a full-screen overlay.

Cron scheduler for agent tasks: create jobs by natural language or a sidebar UI, inject a user message into a new or fixed session on schedule to trigger a full agent turn, with run history, manual trigger, and live SSE sync.

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

Password-protected HTTPS login gate that lets LAN devices securely access the DeepSeek Harness web UI over the network.

A PIN-protected, chat-only mobile web client for DeepSeek Harness, served on an isolated port over LAN or a self-provided tunnel.

Bing-backed web search provider for the built-in web_search tool: scrapes the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeps searches off the model's own search quota. Endpoint configurable.

A customized fork of TQSY114514/dsh-ui-appearance for theme palettes, wallpapers, and glassmorphism, with a layout fix for duplicate blank space alongside better-sidebar 0.18.0.

Peak/off-peak billing cost dial for the DSH Web GUI: session token usage billed at the official DeepSeek peak and off-peak rates, a rate dial with a model-colored needle and switch countdown, a balance ring with a low-balance alarm, drag-to-resize, and a minimized status-lamp mode.

Inline Command Code plan usage badge in the DSH composer toolbar beside the model selector: 5h and weekly window usage plus remaining credits, clicking the badge opens an upward detail popover with reset countdowns; reuses the commandcode/report remote from @mars-sea/dsh-commandcode-provider.

Three draggable, resizable, auto-positioning floating desktop widgets for DSH Desktop — daily schedule, goals tracker, and calendar planner.

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

Browser notification plugin for DeepSeek Harness - system toasts when a task finishes, a run errors, or your input is needed (question / approval / plan review), click to open the session, per-type toggles, and no false 'done' while the main session waits on its subagents.

External Agent control plane for Codex, Claude Code, Cursor Agent, and Antigravity adapters with settings and background job visibility.

Brings the codebase knowledge-base capability of langchain-ai/openwiki into DSH — one-click generate/read/update of the repository Wiki, Grounded Claims (source-traced knowledge cards) and a project knowledge base built from uploaded local files, reusing the model DSH already has configured, with no second API key.

Kimi Coding web search and web fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams (POST /v1/search and /v1/fetch), a settings card in the GUI stores it via the credentials service, and the fallback chain reads the Kimi CLI config for zero-setup installs.

Reports PowerShell, cmd, and LANG encoding for UTF-8 versus code-page issues.

Share the DSH workspace over the local network: phones, tablets and other computers browse, download and upload files via browser with no DSH login. Token gate, path boundary, read-only mode and rate limit. Zero-dependency (node:http).