Plugin

Context governance for DSH: folds oversized tool results, collapses the tool surface and keeps the prompt cache warm, so long sessions stop getting more expensive.

Eager, tail-heavy, line-aware tool result trimmer plugin: hooks into post-execution pipeline to trim oversized command outputs with smart semantic reducers and ANSI stripping.

Model-linked AI personas and desktop pet for DSH, with shared world lore, separate editable memories, task animations, usage statistics, optional AI diaries and idle-time diary consolidation. The native pet window is Windows x64 only; sleep consolidation spends tokens in the background. Before installing or updating, close the visible desktop pet and notification bubble by choosing Close All (全部关闭) in the context menu; otherwise, files in use may cause installation to fail.

Locks the model's reasoning, replies and tool-call descriptions to a chosen target language (Simplified Chinese by default) with system-prompt sections at the head, middle and tail of the prompt, offering three strength levels, an auto mode that follows the DSH interface language, a settings panel that shows the language currently in effect, and a sidebar quick switch.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.1 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox.

OpenCode Zen free-tier models for DeepSeek Harness with anonymous no-key access, a loopback OpenAI-compatible shim, and real bash/read gate tools.

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

Main UI skin that extends the dsh-startup-screen archive layout to the whole workspace, picking up from the boot animation when it hands off.

Genshin Impact white-and-gold skin for the DSH web GUI: a random in-game landscape wallpaper on every page load, the Genshin UI font site-wide, a Paimon-style menu and a running-status element ring, and a switchable Paimon/Phanes assistant persona. The repository ships 262 wallpapers across eight regions at 1920x1080.

Tianlight skin for DeepSeek Harness: 4K video/image wallpapers, local upload and auto-rotation, optional WebWallGL scenes, liquid glass, and a Mint cat companion. Alt+W opens the wallpaper panel.

Per-turn tool cost line in the chat stream: after each turn a collapsible row under the reply lists which tools ran, how many times, and how many tokens each tool injected into the context (input plus output), expandable to per-tool detail.

Provider-reported quota snapshots for GLM Coding Plan and GitHub Copilot in DSH: a draggable floating capsule with detail panels for quota windows, reset times, per-model usage and Copilot credits, plus an optional sidebar card hidden by default; credentials are resolved by the DSH host and no quota history is stored.

Usage panel on the blank-session hero: sessions, messages, total tokens, active days, peak hour, favourite model and a contribution heatmap, over all time, 30 days or 7 days.

Per-turn first-token latency and output speed beside the built-in usage pill, folded on the host over the durable event log: first-token time is replayed from each message's compact stream, so historical turns stay exact after a reload rather than showing an estimate.

Agent-team task Gantt chart for the DSH sidebar - one swimlane per teammate, real session-log time on the x-axis, and every shared task drawn with its title and summary. Requires dsh-better-sidebar 0.4.0 or later (the tab has nowhere to register without it).

Keeps DSH reasoning in Simplified Chinese and auto-expands every Think row in the Web UI.

Opens the NeoXider Agent Deck desktop widget (chat, the slime pet avatar or the hinge handle) from a Harness session, and reports its mode, installed version, running state and whether it follows the same Harness.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

Arknights-flavoured startup animation for the DSH Web GUI: a PRTS terminal boot, sonar scan, hologram lock-on and an operator-file splash that end in a deep-sea lockup, about 4.6 seconds, with four selectable original score presets (or sound off), skippable with a click or Esc and switchable, re-timed or replayed from Settings.

Watches a turn for long silences and, once the threshold passes, injects a user message asking the model to state in prose what it is doing before carrying on, so the turn keeps going. The same text is mirrored in a lower-left overlay above the composer. The silence threshold and the minimum gap between reports are set in minutes, the prompt can be replaced wholesale, and it runs with no runtime dependencies. Requires DSH 0.2.1+ and Node.js 18+.

Replaces the sidebar account label — the phone number, email, username, or account name — and avatar with your own display name and image. A new "Edit display name" row in the account menu opens one dialog for both, so screenshots do not expose the original.

Makes the agent narrate its process: every turn opens with how it reads the message and what it will do first, then short interim notes between tool-call batches, with in-app settings for style, sentence cap and toggles.

Adds six AI coding platforms to DSH — OpenCode, Qoder, Qoder CN, TRAE, WorkBuddy and WorkBuddy International — each as its own group in the native model picker, and manages their accounts from one settings page, with daily check-in where the platform has one, credit balance lookups, and retry on another account of the same platform when one is rate-limited. Models carry their credit multiplier where the platform declares one. OpenCode's anonymous free tier works with no credential, and TRAE stays hidden by default until it is enabled in the settings.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.