Plugins

Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).

SCNet models for DSH. Free SCNet-Max, no client login needed; tokenizer, template and deterministic-output fingerprints match DeepSeek-V4.1-Flash-1017 (README). It reads the SCNet desktop client's stored login when one exists, and otherwise logs in with a phone SMS code from the settings page.

Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Speaks with the system's built-in natural voice, supporting both Windows and macOS; final-reply announcements, approval & question alerts, optional event announcements (turn end, command done, goal change, tool errors, todo updates), replayable final replies, and a bilingual visual settings page.

Connector only, it renders nothing itself: subscribes to DeepSeek Harness session events and folds them into a 12-phase work state (planning / thinking / executing-tool / streaming / waiting-input / voice / awaiting-approval / complete / error / paused / idle / heartbeat), then POSTs each phase to a desktop-pet backend at http://127.0.0.1:8000/api/plugin/dsh/ingest. It holds no window. No API key or token is needed. Requires the Mao Live2D pet application to be separately installed and running (that is a Windows Electron app with its own PowerShell 7 / Python 3.10+ / Node 18+ prerequisites); without it this plugin has nothing to push to.

Connects a Doubao account to DeepSeek Harness as a model provider after a single browser QR sign-in — live model discovery from Doubao web and desktop menus with inline composer billing multipliers and per-model thinking ladders, 「工作任务」 task-mode models spending paid quota, chain-of-thought reasoning streaming, Seedream image generation preferring original uncropped assets over watermarked variants, native DSH token usage and session stats tracking, and a live remaining-quota panel. Windows x64 only, since the session is sealed with DPAPI. Windows x64 only, since the session is sealed with DPAPI.

Remote control: pushes ask / approval / session-end events to an external channel webhook and lets you answer, approve, query status or continue a session from your phone with token auth (npm: `dsh-my-remote`).

Context lens: visualizes token usage of every request (context composition, KV cache hit rate) and enforces per-turn / per-session budgets with warning and blocking (npm: `dsh-my-context`).

Zero-residence context engine: large tool payloads are evicted out of the live context into a queryable store and only deterministic pointers are left behind, so per-turn prompt tokens stop growing with the transcript. Any masked content is reconstructed verbatim from the session log on demand, by tool-call id or session seq.

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

Route eligible shell commands through rtk to compress tool output and save tokens.

The plugin half of the DSH Harmony native HarmonyOS client: native login through the host token exchange (optional Pocket ID passkey), session list and live updates, task overview, per-device notification levels and web session handoff. Published as a prebuilt tarball; no separate relay or gateway daemon is required.

Opens the official chat.deepseek.com page in the DSH main panel through the desktop app's native browser view, so the login survives restarts, without an iframe or request proxying. A fork of JaMoLpE88/dsh-desktop-chat with the changes listed in its NOTICE. The login token is kept in plaintext in session.json.

Shows the current session's equivalent cost in the stats bar below the input, priced from a bundled table of published token prices. Uncached input, cache reads and writes, and output including reasoning are priced separately; model changes add up as separate per-currency segments; subagent costs are included. Clicking the cost opens a per-session and per-subagent breakdown.

Replaces the stat-bar output speed with two figures, for example 207(122) tok/s: outside the parentheses the decoding speed after the first token, inside it the speed over the whole request including first-token latency. Clicking it opens a breakdown of turns, steps, TTFT and per-phase timings. It replaces the native session-stats item; needs DSH 0.2.1-rc.5 or newer.

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.

Connects your GitHub account to DSH agents from the composer GitHub button (OAuth device flow or personal access token) and lets them call the GitHub API through the github_api tool.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Floating macOS-glass DeepSeek usage panel for the DSH web UI: live official balance + token usage (today, session, 24 h smooth trend, per model) without opening platform.deepseek.com/usage. · DSH 毛玻璃用量面板：官方余额 + Token 用量

Deterministic context compression for dsh — zero LLM calls, rule-based pruning that preserves paths, commands, error traces, and open todos verbatim. Compresses ~80k tokens to a few hundred.

Detailed model usage and cost analysis, with per-session usage stats and usage queries for GLM, MiniMax, OpenCode Go, DeepSeek and more.

统计所有经过 DeepSeek Harness 的模型调用：Token 用量、成本核算（含峰谷计价）、首字延迟与输出速度、供应商余额与配额、预算，并按模型/供应商/项目/来源/账号/日期拆分。

Terse prose for DeepSeek Harness — compress the agent's own output so every reply costs fewer tokens (layer 4). Style, never substance.

Codex-style turn folding for the DSH Web UI: keeps final answers visible, groups consecutive reasoning and tool activity, and shows configurable live duration, tool-call, and token metrics with multilingual summaries.