Plugins

App Updater for DeepSeek Harness: detect every installed app that has a newer version and update it with one click by downloading the vendor's full installer from its official website and installing it silently — without launching the app. Windows (winget

B站 400+ 收藏的守岸人桌宠，现在来陪你了。《鸣潮》的守岸人陪你工作，也陪你等待。任务中换表情，完成后用熟悉的语音回应；支持摸头互动、自选表情与语音台词。适用于 Windows x64 本机 DeepSeek Harness，首次下载约 229 MiB 完整程序。

A Storage settings page for DeepSeek Harness: a donut of what dsh occupies on this machine (install, sessions, attachments, runtimes, plugins, temp), a drill-down that lists archived sessions and can delete them, and a clean action that only touches rebuildable caches. Deleting to the system Recycle Bin and Open folder are Windows-only; scanning works everywhere. Host routes accept loopback connections only and are CSRF-guarded; nothing leaves the machine.

Connects DSH to timestamped video reading, shared queues/history and Scroll personal Bilibili workflows through an existing Video Reader installation. Windows x64 only: install the core and set VIDEO_READER_ROOT before starting DSH; the bundle does not install Python, FFmpeg, models or Bilibili credentials.

Windows-only guard against the desktop shell locking itself out: it counts the dsh-auth-* launch cookies the shell has accumulated, reports how much of the 16 KiB request-header budget they consume, and once the count passes 40 it backs up the whole Cookies database and lets DSH rebuild it, so every cookie in that profile is cleared. Install is one command: on load the plugin registers its own weekly scheduled task pointing at the scripts inside the package, and uninstalling it removes that task — nothing to copy into your home directory and no schtasks line to run by hand. The check itself runs while the app is closed (it waits up to 3 hours for the shell to exit). It does not raise the header budget or keep a floating panel; scripts/ can also be run standalone without the app installed.

Adds a sidebar card to DeepSeek Harness that runs a chosen action once every task finishes and the card is armed — shut down, restart, sleep, hibernate, lock, sign out, or a script you uploaded to its shared library; it holds back with a stated reason while background jobs, errored sessions or a manual interruption are still in play. Verified on Windows, macOS and Linux.

启动 / 显示 / 隐藏 / 退出鲸鱼娘桌面宠物（DSH 斜杠命令，macOS + Windows）

WEB ONLY: designed specifically for the Web profile, NOT Electron Desktop. Windows support means Web on Windows, not the Desktop application; installing into Desktop can break startup or restart. Refresh immediately after installation or open /login; HTTP 401 on an old page means sign-in is required, not installation failure. Only an uninitialized data directory displays the temporary password; existing passwords survive reinstalling. Initialize in a trusted network and change the publicly displayed initial password immediately; passwords are never printed in terminal logs. Web lock screen, password/OTP/Passkey, persistent sessions and wallpapers; Windows Web power services can be enabled from the page. Linux/macOS need the bundled controller; npm updates require a dedicated managed install. Stopping interrupts active tasks. Auth kernel adapted from xbzbing/dsh-auth-gateway (MIT); do not co-install.

Checks installed plugins against a DSH update before you install it, and reports the shared UI members and host services they use that the new version no longer exports — the case where an update installs cleanly but leaves plugins failing to load. Includes a read-only diagnose command. Windows only, DSH desktop, Node.js 18+.

Qoder-style workspace mode and branch chips on the session row; picking a branch arms it, and the first message creates a dedicated git worktree and moves the session into it. Windows only: the write grant runs PowerShell Set-Acl; elsewhere Worktree mode reports an error and stays in the main checkout.

AI-native text editor for DeepSeek Harness: tabs, encoding-safe saves, selection/document AI with diff review, Markdown preview, and Windows file associations.

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Drive the NI Multisim 14.3 install on a Windows machine through nine msim_* tools: open and save .ms14 designs, read and edit component values and circuit parameters, run DC operating point, AC sweep, single-frequency AC and transient analyses, export schematics, BOM and netlists. A Win32 channel drives the visible window to run the Analyses dialog and capture Multisim's own schematic view and waveform plot; a SPICE command-file engine handles designs that expose no probes; an offline reader unpacks the .ms14 container without starting Multisim at all. Requires Windows, NI Multisim 14.3, and a 32-bit Python 3.11-3.13 with pywin32.

Whole-disk file search on Windows: ask for files or folders by name, path, extension, size or modified date and get matches from the local voidtools Everything index in milliseconds, with full paths, sizes and modified times. A second card reports whether Everything is reachable and how many items it indexes. Ships the official Everything SDK, so no es.exe or HTTP server is needed; Everything 1.4+ must be installed and running (the plugin can start it).

Turn a script into a narrated explainer video: text-card slides by default (fast and exact for tutorials) or AI-generated footage per segment (needs AGNES_API_KEY); 14 online neural Chinese voices plus 3 offline Windows voices, with a one-command sample pack for picking a voice by ear. Requires ffmpeg, and the bundled video-remix skill copied to <workspace>/.dsh/skills/video-remix with npm install run there for the online voices.

Adds seven `art_*` agent tools plus a right-sidebar drawing workbench (series, pages, revisions, regions, camera blockout) that submits ComfyUI graphs to a ComfyUI instance you host, for MOSS/K2 text-to-image, inpaint, character references, region editing and Qwen-Image edits, with up to four caller LoRAs stacked per request. Requires a local checkout and one adapter step: after a marketplace install, run `install/adapt.mjs` (or use `install/install.ps1` on Windows) to replace the `__MOSS_*__` placeholders with an absolute `workspaceRoot` and a ComfyUI origin; until then the Host refuses to load the preset with `MOSS_CONFIG_*`.

Drives Siemens NX 2406 and 2506 from DeepSeek Harness, plus NX 12: an executor that judges a journal run from its log rather than its exit code (NX returns 0 for a journal that swallowed its exception, and 0xC0000409 after a clean one), 16 typed tools over a resident batch NX, and a probe that keeps the three releases apart. Windows only; NX 2406 is the reference release, 2506 expected. Requires a local Siemens NX install and a free NX licence seat; run `dsh-nx install` once, and the 16 MCP tools stay off until `NX_ENABLE_MCP=1` is set (the skill route works without it).

An intercom between already-open DSH windows. No teams, no new sessions, just peer-to-peer messages with a hop limit.

Read-only export of a chat.deepseek.com conversation into a new DSH session: builds a hand-off pack with the selected rounds kept verbatim and earlier rounds collapsed to one line each, then pre-fills the composer without sending it. Windows only as published (package.json os=win32); requires Edge or Chrome and a one-time chat.deepseek.com login.

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.

Windows XP Luna skin for the DeepSeek Harness Web UI: a blue taskbar sidebar, Luna title bars, translucent conversation and plugin windows with adjustable opacity and blur, and a settings page for importing a wallpaper. Light mode only: the skin removes itself when the host switches to dark.

Native DSH /side conversation tabs with a clean transcript and inherited context, hidden from the main session list using independent Session forks and the official chat UI, with timestamps, token usage, streaming and the command menu. Extracted from dsh-better-sidebar 0.29.0 (MIT); do not enable it alongside dsh-better-sidebar's own /side entry — the two command entries conflict, so stop one before using the other. Requires Windows DSH Desktop 0.2.1-rc.5 and dsh-delete-session for confirmed permanent cleanup.

Region screenshot for the composer on Windows: a full-virtual-screen selector frames the region (drag the frame, eight grips, Ctrl+drag to annotate), and the finished PNG lands in the composer as a pending attachment.

Opens chat.deepseek.com in the right sidebar pane from one row in the left sidebar, leaves the current conversation untouched, expands to fullscreen on demand, and shares the sidebar browser cookie jar; a bundled script makes the login survive restarts. Desktop (Electron) only; keeping the login across restarts needs the bundled PowerShell patch, which is Windows-only and must be re-applied after every DSH upgrade.