Plugins

Maximizes the DeepSeek Harness desktop window automatically on startup, equivalent to clicking the maximize button once. Cross-platform (Windows/macOS/Linux), best-effort, host-only.

Available on npm as dsh-doudizhu-lan. Three-player LAN Dou Dizhu (斗地主) played from a floating window: one machine opens a room on its own port, the other two join with a six-character room code plus an address. Empty seats can be filled by computer players in four switchable strengths (easy, medium, hard, hell), so one or two people can still play a whole hand; the deal starts as soon as the three seats are filled. 54 cards in four suits, bidding of 1/2/3 or pass, the landlord takes the three bottom cards and holds 20, play runs clockwise, and the first-bid seat rotates clockwise between hands. The rule engine is pure and covers 11 legal shapes, with big joker > small joker > 2 > A > K down to 3, suits never compared, straights, pair-straights and planes excluding the 2s and the jokers, and a rocket that beats everything. The table itself is built to be read at a glance: three seat cards side by side in play order (you, then your next and previous seats) with role, hand count and a bar that runs out, one line that says whose hand is on the table and what would beat it, the bottom cards as text, an in-place play history that folds into a single summary line and unfolds into every trick including the passes, plus hint and auto-play buttons that pick the cheapest legal answer out of the local rule enumeration. Nicknames can be changed mid-hand (twelve characters, duplicates get a suffix). Computers run inside the authority and are handed only their own hand, the public record and the seat counts, so no hand can leak; the authority is the only place that decides which card ids leave it. Computers are driven by the room itself, so a one-person table keeps playing with nobody else on the LAN port. Humans have no turn timer, the collapsed floating pill can be dragged around the screen, and 179 unit tests pin the rules, the wire format, the theme tokens, the drag gesture, the history grouping and the computer seats.

Phone-side command center rather than a web-UI mirror: dispatch tasks into isolated git worktrees from a PWA, tool-approval push notifications with phone/desktop first-answer-wins racing (never auto-approved), a multi-machine session board, and an end-to-end encrypted zero-knowledge relay you can self-host.

Conflict diagnosis and repair for DeepSeek Harness plugins. Builds a capability graph of the running Loader profile and of the on-disk cordis.patch.yml layers, comparing imports, peer ranges and config against the host that is ACTUALLY running rather than the profile's possibly-stale copies, and reports the conflicts that fail silently: a fiber stuck PENDING on a service no plugin provides, a browser half injecting a client module nothing provides, a tool id two plugins both register, duplicate Loader entry ids, a row disabled by one layer and re-inserted by another, an import of a host subpath the running host does not export, and a cycle among inject declarations. Every finding carries its evidence, a confidence grade for who owns a name, and a repair with a risk grade — verify it with a dry-run difference table, or take the individual .patch.yml files that --fix-out writes (never auto-loaded, so picking wrong breaks nothing).

Records the version of the edit target as an observation when the agent inspected the file with bash instead of the read tool, so the filesystem observation policy stops rejecting edits with FS_NOT_OBSERVED. Applies to edits only; blind whole-file overwrites stay guarded.

Scheduled update checks for DeepSeek Harness itself and installed plugins, applied only in idle windows — four schedule modes (daily, every N hours/days/minutes), bidirectional plugin whitelist, disk-verified installs, and a web settings panel with hot-reload config.

Enforces a check-fix-recheck loop when a task is wrapping up: it auto-runs your tests/lint/audit, blocks any round that still has unfixed problems, and only calls the task done after three consecutive clean full checks, then notifies the user.

Turn-handoff reminders in the DSH Web UI with a modal or top banner, six browser-synthesized chimes, configurable auto-dismiss, and a sidebar speaker toggle with an unread session list.

An audit workspace for DeepSeek Harness: a multi-agent consultation venue where each review seat is filled by an agent, every judgment is routed to a named review face, and the whole run is kept as a traceable record. Works out of the box: the service endpoint is built in, a workspace is provisioned automatically on first launch, and review scenes come with their seats and agents listed.

Agent preset: one session runs a three-phase auto-development pipeline — interactive design with parallel research subagents, goal-driven development with reviewer/developer subagents and per-package budget ledgers, then an acceptance fix loop.

Open the extension side panel and it takes over the page you are browsing right now. On top of upstream it adds: hover, coordinate clicks, drag, batched action chains, whole-page screenshots, local file upload, image listing, and switching between several connected browsers. Pages reach the model as structured text with a numbered element list; actions wait for your approval and sensitive fields stay masked. Ships as the bridge plugin, with the extension in the same release. This project is a fork of omdsh-dev/dsh-browser: https://github.com/omdsh-dev/dsh-browser

White-box memory in two parts: four user-authored long-term tiers (must-follow rules, behavior settings, user profile, optional rules) injected as one system-prompt section, plus a separate temporary working set (cross-session handoffs, stage goals, waiting items) with its own 1200-character budget that stops being injected once an entry is done. The long-term tiers are plain Markdown files the user can read and edit; the agent can only propose them, and nothing is written until the user accepts in the Chinese panel. Temporary entries are written only when the user explicitly asks, and live in <DSH_HOME>/temp-memory.json (created on first write), not in the memory directory. No auto-capture, no background writes, no network.

A context usage ring with configurable character-based automatic compaction, manual compaction, protected user requirements and recoverable original history for DSH 0.2.0-rc.2.

/compact and auto-compaction summarize with the model selected in the session, not the model that finished the last turn.

Starts the WorkBuddy Panel backend (wb2api.exe from workbuddy2api-panel, Windows) with DSH and on exit stops only the process it launched; optionally syncs the backend's /v1/models into the workbuddy provider, and its settings card picks models, shows credit multipliers and installs, updates or rolls back the backend from checksum-verified GitHub releases.

Text-to-image and image-to-image for a model that cannot draw, through any OpenAI-compatible image API, with multiple providers and an automatic fallback model.

Auto-expand reasoning and tool cards, tune code-block font size and line spacing, and choose the model output language (auto, Chinese or English).

Realtime token counter beside the deep-thinking indicator in chat, with merged or split input/output display, per-step operation counts, and auto-scaling K/M/G/T units.

Tired of going fullscreen by hand every time you open Harness? This plugin fills the screen for you - auto-maximize (keeps the window buttons) or true fullscreen on launch, then maximize / restore / minimize / always-on-top anytime. It quits only after a native confirmation dialog - Esc, double Esc, or Ctrl+Q; in fullscreen, Esc leaves fullscreen first. The window channel installs itself, so no script or Python is needed; the first install takes effect after two DSH restarts.

Pasted screenshots become numbered references: each Ctrl+V image is stored in the attachment library under a stable number, listed in a composer-dock thumbnail panel with an image source in the @ menu, and inserted as a reference chip at the caret — automatically after paste when the auto-insert switch is on.

A prompt optimizer in the composer input tool row: pick a category and a template, then ✨ rewrites the draft in place with one-click undo. Pick from the Basic, Context and Image categories; you can cancel a run, and it shows elapsed time and token usage. Ships 15 templates covering task-instruction rewriting, step planning, safety-research framing, system-prompt role cards, and text-to-image / image-to-image prompts; context templates read the recent turns of the session for coreference resolution. Calls go through the host model service, and a settings section exposes the model and the budgets. Output guards check that user-written constraints survive, warning rather than auto-retrying. Adapted for dsh 0.1.7 and 0.2.

An always-last, collapsible Recent tasks workspace group in the DSH sidebar: a sidebar entry and the Mod+Alt+N / Mod+Shift+N shortcut start a chat in a dedicated folder, so it lands in that group instead of 未分组. The group is a genuine workspace record rather than a plugin-drawn look-alike, so collapse, rename, search and drag order behave normally, and its folder, group name, pin-last and auto-repair are live settings.

Auto-pairs brackets and quotes in the DSH chat composer, inserting the closing half with the caret in between; it also wraps selected text with the typed pair and handles brackets committed by an IME.

Quote text selected in a DSH Web conversation, then either attach it to the current composer or dispatch it to a subagent session: the quote sits on a bar above the composer, or opens that subagent in a new pane on the right. When the target has no subagent yet, the quote is held and the composer is seeded with a spawn request, then picked up automatically once the new session appears. Client-only.