Plugins

Inserts the full path as text when a folder is pasted into the input box, instead of trying to upload it (Windows and macOS).

Shell-style prompt history in the DeepSeek Harness composer: ArrowUp walks back through the messages you already sent, ArrowDown walks forward and restores your draft.

Wayland desktop control for GNOME/Mutter sessions: screenshot, OCR with screen coordinates, click by text, and batch input actions. Needs a Python 3 backend with python3-gi and GStreamer; OCR needs Tesseract.

Cost pill at the right end of the composer stats row, showing the estimated cost of the current turn and the session total; clicking it opens a two-column panel with input, cache and output spend for the turn and the session, dialogue turns, today's and lifetime spend, and this session's cache-hit rate and cache saving. Rates follow the official DeepSeek price table including peak pricing (double on weekdays 09:00–12:00 and 14:00–18:00 Beijing time, statutory holidays excluded), each message is priced at the time it settled, and prices.json reloads without a restart.

CLI-style chat history recall for the DSH input box: press ArrowUp/ArrowDown to recall previously sent messages.

Provider logos and model IDs in the DSH model picker, registered as a label decorator on the official conversation.input.model.label slot; providers match by token, display name, model ID and explicit override, falling back to a letter monogram when unknown.

Kizuna agent letterbox: four tools that let an agent read its own inbox (mailbox status, pending letters, one letter in full) and answer a letter with completed / failed / input-required / working state. Kizuna is an agent directory with a reliable task relay: a per-agent kizuna-box on the same machine holds the inbox, retries unanswered deliveries after 3 / 10 / 30 / 60 / 120 minutes and records every delivery attempt in an append-only trail. The plugin talks to the local loopback box only and holds no credential.

Conversation lock for the DeepSeek Harness sidebar: every conversation row gets a lock button, and a locked conversation blurs only the conversation area behind a password box while the sidebar stays usable. Re-locks on window blur, tab hide, page hide, or whenever the open conversation changes, and never pauses a running turn - the veil reports that background work continues. The password digest, lock flags, and preferences live in <DSH_HOME>/session-lock/state.json behind two same-origin routes guarded by a custom header, so clearing the page localStorage unlocks nothing; PBKDF2-SHA256 with a random salt, and a 30-second input lockout after five wrong attempts. Recovery is opt-in per machine: a Windows login password (enabled only after a real .NET PrincipalContext ValidateCredentials check against the local machine, so Microsoft accounts and passwordless machines keep it off) and a cooling period chosen while creating or changing the password (1/6/24/72/168 hours; expiry clears the password and releases every lock, and the correct password cancels the countdown). A settings section covers status, changing the password, lock new conversations, hiding locked titles, a three-position archive-restore policy (all / locked only / off, switching needs the password), lock everything, and unlock everything. Dialogs use the native dialog top layer, so a dialog opened from Settings is never covered by it. Requires DSH 0.2.0-rc.1 or newer; no build step.

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

Mounts the REA (Reverse Engineer Anything) MCP server through two gateway tools instead of registering its 200+ tool schemas on every request: rea_list searches the catalog or returns one tool's input schema, and rea_call invokes that tool, each call spawning a short-lived rea mcp process, so the tool definitions sent per step drop from about 780 KB (207 tools as measured in REA 6.5.0) to about 1-2 KB. When no rea entry point is found it installs rea-agents into a plugin-private directory with the pnpm bundled in DSH (dependency build scripts skipped) and links the reverse-engineer-anything and rea-gateway skills into the skills directory without overwriting existing ones.

OpenAI OAuth login for ChatGPT Codex that adds ChatGPT as a selectable LLM provider (streaming, Off/Low/High/Max reasoning effort, image input) and a codex tool for per-session DeepSeek escalation, with optional light-task delegation to DeepSeek and subscription usage and reset-credit management.

Token usage dashboard for DeepSeek Harness. A dedicated settings page shows cumulative input / output / cache-read / cache-write token totals, a green GitHub-style daily heatmap colored by usage, and a pie / bar chart toggle for per-model (provider/model) usage shares — all read from local session logs, no upstream API calls.

Hands-free voice for DSH on Windows: local wake word, local Chinese speech-to-text inserted and sent into the composer, and spoken replies that can be interrupted and resumed. Requires a one-time run of the bundled install.ps1 (Python speech dependencies plus microphone pick) and a SenseVoice model already downloaded by the DSH voice input (or placed under models/sensevoice-onnx).

DSH plugin for Gaussian 16: SMILES-to-3D, input generation, serial job management, output parsing, and Multiwfn/VMD post-processing (orbital/ESP/RDG).

Token spend panel for DeepSeek Harness: today and 7/30-day totals, natural month/quarter/year sums, cost split by cache-hit input, cache-miss input and output, per-model and per-session detail, daily and monthly budgets with a projected day-end spend, peak/off-peak pricing, CSV and JSON export, and a zero-dependency CLI report. Also prices GLM (Zhipu) and Kimi models shipped through third-party routes. Maintained fork of olimc2016/dsh-token-meter-panel (MIT, 0.6.7) with a rewritten panel; it uses its own row, route and slot ids, so it installs alongside the upstream entry rather than replacing it.

A Telegram bot plugin for DeepSeek Harness, with shared sessions, image input, and interactive agent conversations

Natural, human-sounding voice for the dsh harness: server-proxied neural TTS read-aloud and agent speech tools over OpenAI-compatible endpoints, browser-native or Whisper speech input, and a Voice settings section

Jujutsu (jj) version-control panel in the DSH web GUI: a Jujutsu tab renders the jj log change graph with change details, changed files and file diffs, a revset input, and jj-native history edits (drag-to-rebase, split by file, describe, squash, abandon, undo, push); it reads jj directly rather than through git, and every command runs as an argv array through a whitelisted host service with confirmations, timeouts and output caps.

The composer predicts what you are about to type. Inline ghost text sits on the caret, measured against the editor's own font and line box, and Tab turns it into real text (Esc ignores it). The prediction is one short call through the session's own model router, seeded with your draft and the last few turns of the conversation, so an empty composer also gets a next-prompt guess written in the user's voice; suggestions that merely restate the assistant are dropped. Host side is one HTTP route with sub-path endpoints (loopback-only, 64 KB body cap, 2-minute result cache, 20-second miss cache, one in-flight call per session); client side is one 0-height overlay registered on conversation.input.overlay, with insertion guarded by the composer's draftRev CAS and a setDraft fallback. IME composition and slash commands are skipped. 16 node:test cases, zero runtime dependencies, real screenshots in docs/.

A 44x44 always-on-top desktop ball for DSH that reflects what the agent is actually doing (thinking, searching, web fetch, error, waiting for input) and shows an exclamation or question-mark badge when a task finishes or needs an answer while you are away. Windows only; it downloads its own Electron runtime on first use.

Open a Mac or Windows DeepSeek Harness Web instance from iPhone or iPad Safari: 8-digit pairing, a LAN gateway for loopback-only hosts, optional Tailscale Serve, and iOS-only Safari input and touch fixes. Installs with dsh plugin add.

Composer meter for the DeepSeek Harness Web UI: a pill under the input shows draft character count, estimated tokens and this session's estimated cost from DeepSeek's published prices (peak/off-peak, Flash/Pro or custom rates), and opens a panel with the token breakdown, a six-snapshot per-session draft vault and a draft cleaner; every write goes through the host setDraft API instead of touching the editor DOM.

Annotation browser in the DSH sidebar: a real Chrome page streamed over CDP with input forwarded, where picking an element or selecting text attaches its source location, component stack, styles and a crop to the chat input. Needs a local Chrome (on Windows set chromePath).

Annotate quoted answer text in the transcript: each selection keeps its quote plus a note of your own, notes pile up as chips in the composer and travel with the message, and two or more also get a chip above the input to jump back or clear them. The chips need dsh-paste-chip installed; without it each note is a plain text line in the draft.