Plugins

Composer prompt enhancement for DSH Web: a ✨ button rewrites the current draft in place after asking only about genuine ambiguity, and an empty composer shows a grey next-message ghost that Tab or a click fills into the draft without sending.

Model quick picker for DeepSeek Harness: a button left of the model dropdown opens a full model-selection dialog with provider grouping, live search, provider filter, capability tags read from the user's own input config, reasoning badges, recent-model shortcuts and a reasoning-effort picker; the choice writes back to the native dropdown immediately.

Keeps the DSH desktop window the size you left it: records the last outer frame of the main window in physical pixels and restores it, centred on the work area, on the next start - and it acts before the window is ever shown, so the boot animation plays at the right size. The settings page offers 12 presets (1024x768 to 3840x2160), free-form custom width and height, a centre-on-restore switch and an apply-now action; a choice takes effect immediately and persists. Resizing goes through a small helper executable compiled on the user's own machine: the C# source ships inside the plugin, is built on first run with the in-box Windows csc.exe (measured ~110 ms once, cached next to the state file, ~90 ms to start), and falls back to a short-lived powershell.exe process when that is not possible. The package ships no binary, declares no npm dependencies and makes no outbound network request. Windows only.

Bilingual Chinese and English typing practice with timed passages, IME-aware scoring, per-character feedback, and locally stored records.

Opens STL meshes in the right-Sidebar document preview: binary/ASCII parsing in the browser, a WebGL viewport, and size, volume, surface-area and watertightness statistics.

DSH guard against self-repetition in streamed model output: detects a degeneration loop in reasoning or visible text, aborts the runaway turn and wakes the agent with a corrective notice.

A DeepSeek Harness plugin that freezes tool declarations to improve prompt cache stability.

轻量化的QoL插件，可在助手消息元数据行追加本轮 token 费用估算（¥）。

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.

Connects the DeepSeek Harness agent running on your own computer to the HarnessMate platform, so you can chat with it, exchange files and approve its tool calls from a phone or a browser.

Adds a local phone pairing, gateway control, and diagnostic panel for Pocket Bridge in DSH Settings.

Hermetic composition lock: fingerprints the profile's dependencies, bundle order, lockfile and patch layer; booting a drifted composition warns, or fails under strict mode (the --frozen posture for CI).

Rewrites agent-issued delete commands (PowerShell `Remove-Item` and its aliases, Bash `rm`/`unlink`/`rmdir`, CMD `del`/`erase`/`rd`/`rmdir`) into system recycle-bin operations on Windows, Linux and macOS, best-effort checks scripts for the same operations before they run, and keeps no permanent-delete fallback.

Prints every plugin in the DeepSeek Harness loader tree at boot, with the exception text for anything that failed, and checks dependency version drift, profile config validity, web port reachability and registered tools.

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).

Agent Studio for DSH Web: configure models, prompts, per-plugin tool bindings and Skills; trial-run with editable tool results and run history; preserve session capability snapshots; export standalone presets; draft Agents with a guided creator preset.

DSH Cordis computer-use provider for the ZTE Nde desktop. npm install auto-fetches the musl binary built by computer-use-linux-zte-nde (v0.7.7-nde.3) into the package's own bin/ via postinstall; resolveCommand() resolves the cordis command path against import.meta.url so the mount works regardless of dsh web's cwd. Reserves the shared computer-use slot via ctx.computerUse.register and exposes MCP tools under mcp__computer-use-linux-nde-mcp__* (screenshot, list_windows, click, type_text, doctor, etc.). Two notable Nde fixes upstream of this provider: KWin caption+coords fallback for window targeting, and SnapshotCache that keeps AT-SPI single-wake per (app, pid) so Chrome is not repeatedly disturbed.

VSCode-style Source Control page in the DSH Web right sidebar: a paged commit lane graph with ref markers and per-commit diffs, grouped working-tree changes with stage/discard/unstage, a commit box with amend and AI-generated messages, a side-by-side and unified diff page, GitHub repository and pull request creation through the gh CLI, and bidirectional HTTPS/SSH remote switching.

Agent-facing GitHub repository tools: binds an account through a first-run prompt, then clones into the workspace and reads, exact-replaces, commits and pushes files, with writes off by default.

Live skill provider that reads every Xiaomi MiMo (MiMo Desktop / MiMoCode) skill into the DSH session catalog: the engine-bundled skills under engine-config (unpacked from app.asar when that directory is absent), the MiMoCode global and project roots, extension-contributed skill directories declared in extensions.json, and the brand compatibility roots MiMo's own skillPathCompat setting enables.

C++ audit skill: detects the target project's actual C++ standard before making any recommendation, then reports findings across RAII and ownership, move semantics, exception safety, performance and memory, containers and algorithms, concurrency, templates and compile-time, standard boundary, and type safety, ABI and interface design, each with a checkpoint, a reason, a bad-to-good example and the minimum standard.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

Generates release material from what a local repository can actually support: a hero image, a feature grid and bilingual copy rendered as SVG and HTML from `README.md`, `package.json` and optional screenshots. Facts are quoted from those files — name, version, license, summary, features, install snippet — and a field that is missing is left unrendered rather than filled with placeholder text. Every feature carries a source citation such as `README.md#L42`, and a claim the repository cannot substantiate is linted out before anything is written, with the reasoning left in `lint-report.json`. `manifest.json` records a sha256 for each input and output, and `--now` or `SOURCE_DATE_EPOCH` makes a run byte-identical. Also ships a GUI panel that regenerates from inside a session.

Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.