Plugin

Image Editor separates uploaded images into editable layers through Shenhuo MCP, with confirmed credit quotes, browser editing and local PSD downloads.

Windows multi-drive dashboard that labels cleanable, caution, and system space in green, yellow, and red, audits download folders, and suggests how to split data across drives.

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.

Turn a logged-in DeepSeek web account into an OpenAI and Anthropic compatible endpoint, with tool calling, image input, an account pool and a local admin console. First use needs a one-time `node scripts/fetch-assets.mjs` in the installed plugin directory to download DeepSeek's PoW runtime from the vendor CDN; without it the proxy starts but every upstream request fails.

Adds a Share to chat action under each reply: converts the answer to WeChat or WeCom text, ordered segments or a long image, editable-table email HTML, or a downloadable Word document.

Installa, aggiorna e rimuove plugin DSH da una scheda nella pagina Plugins. L'installazione chiama il servizio pluginManager in-process del profilo, per aggiungere plugin mentre l'app desktop è in esecuzione senza passare solo dal CLI. Gli aggiornamenti usano la update API v1 pubblica di dsh-market (necessaria per la sezione) e mostrano fase, percentuale e byte scaricati in una barra; rollback solo quando il market segnala un restorepoint. Se la rimozione di un bundle in uso viene rifiutata, lo disattiva, lo elimina dal manifest del profilo e mette in coda i file residui per la pulizia al successivo avvio.

Cockpit di sviluppo a ciclo chiuso integrato in DeepSeek Harness: da un pannello l'agente compila, flasha, verifica tramite debug e monitora schede STM32; l'utente segue ogni passaggio dal vivo, con fasi di avanzamento, log in streaming, uso RAM/FLASH e forme d'onda seriali decodificate. Richiede Python 3.10+ dell'host nel PATH (il plugin non può installarlo). La toolchain ARM si scarica automaticamente al primo uso (~400 MB, solo Windows x64); serve una scheda STM32 con debug probe.

Cerca letteratura medica e delle scienze della vita per argomento, parola chiave o DOI tramite Europe PMC, PubMed, OpenAlex e Crossref. Determina l'accesso aperto con Unpaywall/OpenAlex/Europe PMC; se esiste una via OA, scarica il PDF dopo aver verificato magic bytes e numero di pagine. Altrimenti crea una scheda decisionale con il motivo preciso del fallimento e quattro alternative manuali: AbleSci assistance, Sci-Hub, SciDown e X-MOL. Lo strumento Python incluso usa solo la libreria standard.

Image Designer collega DSH ai designer Shenhuo AI con OAuth personale, caricamento dei materiali, proposte, conferma del preventivo crediti e download locali.

Strumenti agente per un downloader Gopeed locale: crea, ispeziona, sospende, riprende e rimuove download; diagnostica o avvia il processo Gopeed; riceve eventi di completamento tramite un job DSH in background che risveglia un agente inattivo. Diagnostica e avvio del processo sono solo per Windows; gli strumenti di download funzionano ovunque giri Gopeed.

Aggiunge a DSH Web GUI caricamenti a blocchi con avanzamento e ripresa, e download nativi dei file workspace e dello ZIP del log sessione, anche per sessioni raggiunte tramite collegamento remoto associato.

Browser ed esportatore di asset Unreal Engine 4/5 (UE4, UE5) per Windows x64: esplora, mostra in anteprima ed esporta asset cooked da archivi PAK locali tramite CUE4Parse. Include anteprima mesh 3D, riproduzione animazioni e indice ricercabile. Gli archivi Oodle richiedono la DLL oo2core di Epic, non inclusa ma scaricabile da Settings.

Plugin di trigger basato su eventi (il campanello accanto alla sveglia di dsh-proactive): fs watcher ricorsivi con finestre debounce e filtri glob per regola; endpoint webhook solo loopback con token per regola; regole che risvegliano una sessione target tramite il servizio agents dell’host (follow-up diretto se attiva, prima ripresa se inattiva) e inseriscono un prompt con variabili paths/count/payload. Ricarica le regole senza riavviare DSH e aggiunge ogni trigger a una cronologia JSONL verificabile, consultabile con trigger_list e trigger_history. Una route health loopback riporta stato installazione/runtime. Esempi: riordinare Download, diagnosticare allarmi CI/monitoraggio da script locali e sorvegliare errori nei log. JavaScript puro, senza build, MIT.

Preflight dei permessi graph-first per DSH. Il modello dichiara un grafo di calcolo con nodi che descrivono l’operazione (cosa scaricare e dove, cosa scrivere o eliminare). L’utente approva i nodi uno alla volta nel pannello laterale; ogni approvazione vale per una singola esecuzione riuscita. Ogni nodo conserva un audit trail di quanto eseguito davvero. Le operazioni non coperte richiedono comunque approvazione tramite la scheda nativa; un nodo bloccato da un’autorizzazione senza risposta viene sospeso, mentre il lavoro indipendente può continuare.

Aggiunge uno strumento che acquisisce il desktop Windows in PNG e passa il percorso al modello, oltre a un pulsante fotocamera nel composer per visualizzare, scaricare o copiare la cattura.

Browser in-app per DSH: Chromium dedicato con profilo persistente affinché gli accessi Feishu o SSO resistano ai riavvii, controllato via CDP. Espone sette strumenti agent (status, open, eval, read, feishu, screenshot, tabs) e mostra la pagina in tempo reale in un pannello destro aperto automaticamente dalle chiamate. Converte anche documenti Feishu in Markdown scorrendo il contenuto virtuale. Richiede Chrome, Edge, Chromium o una build Chromium di Playwright installata localmente (non ne scarica); specifica il binario con DSH_IAB_CHROME.

Scarica video e crea GIF da link o clip locali su Windows x64, con limite di dimensione facoltativo.

Ambiente di lavoro per dispositivi HarmonyOS in DSH NEXT Desktop su Windows x64 (testato con DSH NEXT 2.0.21-next e Better Sidebar 0.28.2). Lo specchio flottante riutilizza Electron di DSH oppure scarica circa 140 MB al primo utilizzo.

Cerca in quattro biblioteche gratuite da un’unica finestra: Project Gutenberg tramite catalogo OPDS, Shuge tramite ricerca WordPress e link brevi s.shuge.org nelle pagine dei libri, NCPSSD tramite endpoint basato su Solr. Chinese Text Project è solo collegato perché i termini vietano l’accesso automatizzato. Due strumenti: readbook_search e readbook_open; il secondo restituisce URL di download reali per Gutenberg e Shuge e solo il link alla pagina per NCPSSD.

Libreria locale di documenti per DSH Desktop (solo Windows, installata con lo script PowerShell incluso). Carica i file una volta e ogni conversazione può cercarli e leggerli tramite quattro strumenti: library_list / library_search / library_read / library_save. Caricamento, download e download in batch sono nel pannello Settings. I file restano sul computer salvo attivare il modello vision opzionale, che invia le immagini all’endpoint configurato.

Legge NTQQ locale (QQ 9.9.x) su Windows/Linux ed esporta chat di gruppo/private in txt/csv/json/md/html/sqlite. 16 strumenti: qqnt_status, qqnt_doctor, qqnt_extract_key, qqnt_index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats, qqnt_export_group, qqnt_export_chat, qqnt_export_batch, qqnt_jobs, qqnt_media, qqnt_storage, qqnt_ask, qqnt_recall (rifiuta l’ambiguità; pulizia solo su lista autorizzata). 127.0.0.1:46728: indice SQLite incrementale, 6 viste, task, colonna singola su schermi stretti, mittenti oscurati, media raggruppati, divisione giornaliera, preset, ZIP AES-256 con password. OCR/voce/embedding si installano su richiesta nel virtualenv del plugin. Richiede python3/sqlcipher3; Impostazioni può creare il virtualenv privato. Chiave DB dal client QQ attivo e autenticato.

Un’unica installazione aggiunge animazione di avvio whale-girl, sfondo video cyber code-eye e tema scuro olografico. Skin e video (CC BY-NC-SA) si scaricano dal repository upstream al primo avvio; l’animazione si installa solo se è già presente `@ljwei-stak/dsh-boot-animation`.

Nasconde il badge di aggiornamento integrato DSH Desktop (pill freccia download “新版本” accanto all’account): regola CSS per build attuale e match della label accessibile con MutationObserver limitato per restare attivo dopo aggiornamenti DSH. Non tocca controllo aggiornamenti, menu manuale “Check for updates” o indicatore di connessione.

All’avvio DeepSeek Harness apre il sito ufficiale di Genshin Impact e scarica il launcher ufficiale.