プラグイン

Token usage dashboard in the DeepSeek Harness sidebar: daily totals from session logs with a 12-month heatmap, per-provider breakdown over today/7d/30d/all (hourly for today) including each route's average output speed, and a per-session ranking that includes archived and deleted sessions and folds subagent usage into its parent.

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.

Shows your DeepSeek balance and what the current session has cost in a corner overlay, with budget alerts, peak-hour warnings and opt-in official price sync.

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.

Shows a card in the sidebar footer with the DeepSeek account balance (read from the official /user/balance endpoint with the API key DSH already stores) and the unit prices of the active model — input, cache read and output — taken from a built-in snapshot of the official price table. A dot marks the current billing window and a countdown shows the time left until it flips: peak is Mon–Fri 9:00–12:00 and 14:00–18:00 Beijing Time, excluding Chinese public holidays, and everything else is off-peak. Prices and the dot appear only for official DeepSeek models; for any other model the card shows the balance alone. The card refreshes every 30 seconds, on click, and when the model changes, and follows the app theme and the DSH language.

Collapses the DSH sidebar panel list into a single group row, and its gear opens an edit mode to show, hide and drag-reorder two groups: sidebar extension entries and conversation view tabs.

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.

Provides an always-on-top window feature for the DSH window, preventing it from being hidden unexpectedly, Windows only; requires PowerShell 7 (pwsh.exe) on PATH.

Render Mermaid fenced code blocks as native diagram cards with 8 design-system themes and adaptive layout.

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.

MCP server and skill management for DeepSeek Harness: a sidebar panel and a plugin-page config section with search, status lights, per-row switches, expandable details, and an add-server form following Codex mcp_servers fields.

Element-level PowerPoint canvas that edits the opened .pptx in place: click, marquee-select or pick a whole slide, describe the change, and the AI writes byte-preserving OOXML patches with undo and redo.

AI short-drama workspace for DeepSeek Harness, with a dedicated drama agent preset, 35 agent tools and 10 bundled skills covering outline, characters, script, storyboard and export.

Shows JeV-selected task plans, progress updates and stage summaries in DSH chat, with native translation or lightweight summaries. Requires a JeV key; the Jev service is called externally and may bill. and hierarchical serial/parallel task flows.

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.

Select text in any Windows app to explain, summarize, translate, or read it aloud with DeepSeek Harness — answered in a streaming always-on-top overlay with a horizontal capsule menu.

File search palette for the DSH workspace: find files by name or content, open results in DSH's native right-sidebar preview, and edit text files inline with version-conflict checks.

One-click prompt refinement for the DSH composer: the ✦ button next to Send rewrites the draft into an agent-ready prompt in Standard or Light mode, with Revert and Retry; asks follow-up questions through the question card when the draft is missing information; checks that paths, identifiers, numbers, URLs, inline code and @mentions survive the rewrite and adds back any that were dropped; runs on the conversation model or a dedicated model chosen on the Plugins page.

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.

Standalone Network Engineer Assistant agent preset plus a bundled 32-doc command knowledge base skill for DPtech, H3C, Huawei and Ruijie switches and routers: KB-first retrieval, cross-vendor command translation, topology and CLI-output screenshot reading, online manual lookup with cited sources, and mandatory risk annotations for dangerous commands; answers networking topics only.

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.

Endpoint of a companion mobile app that also runs headless, with no desktop shell or Electron required: it serves a restricted mobile API over a relay tunnel or LAN pairing, for listing, opening and driving DSH sessions, following the live device event stream, and authenticating with revocable per-device credentials.