Plugin

Failure memory for DeepSeek Harness. Captures tool failures as they happen, classifies them with 16 built-in rules into lessons pairing a symptom with a fix, adds session/daily/weekly summaries, and injects a short briefing into later sessions through systemPrompt context. Ships 5 pitfall_ tools and a web settings page.

Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.

Local Ollama worker tools for DeepSeek Harness: model inventory, a single unverified ask, and a batch runner that chunks long text, checks every item deterministically, returns a small verbatim sample for review and can optionally write the labelled result inside the session workspace.

Named model routes for subagent delegations, configured from a settings page: each alias binds a subagent provider, model and optional reasoning effort, token cap, agent preset, tags, plus a "when to use" line the model reads to pick it, so a delegation names only the alias. Adds five tools (delegate, list routes, edit config, wait, release), shows the route a child actually ran on in its session header, lets each UI element be switched off, and keeps all configuration in one local JSON file instead of YAML.

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.

WYSIWYG Markdown notes editor in the DSH right sidebar, with tabbed documents, table editing, chat integration, assistant read/write tools, and local file export.

WeChat Reading (WeRead) right-sidebar bookshelf and chapter reader: QR or Cookie login, store search, resume reading, and weread_shelf / weread_search / weread_book / weread_chapter agent tools.

A composer control: shows the current model's context window, the tokens in use and a rough system / tools / messages breakdown, switches the model's reasoning effort in one click (writing reasoningEfforts into the model config when the provider declares none), and edits the model's contextWindow from the same panel so custom-provider models stop silently inheriting the adapter default. Makes no model calls; reads only the official session projections, model directory and config-forms services.

Optional source-preserving chat rendering with selectable themes, offline Uiverse component tools and a report-local evidence workspace. Preview for DSH 0.2.1-rc.2.

Anteprima visiva che trasforma tutte le conversazioni con l'IA in un mare di stelle.

Gestore di server Linux remoti nella Web UI Harness: esplora e modifica file, controlla lo stato host, avvia/arresta/riavvia container Docker, esamina immagini, configura mirror del registro Docker, gestisce regole firewalld/ufw, cambia sorgenti apt e rileva strumenti di sviluppo o li installa/aggiorna con apt.

Aggiunge un chip Git accanto al composer per aprire un workbench centrale (modifiche, cronologia, file, tag, stash) e una sezione Git nelle impostazioni. Supporta OAuth device flow multi-account e PAT con permessi per repository (full/read/none). Un interruttore globale regola le scritture; le letture sono limitate a una lista di directory consentite. Rifiuta il push se nessun account può scrivere sul remote di destinazione. Diff in linea con numeri di riga, 4 layout, enfasi parola per parola, evidenziazione sintattica e ricerca Ctrl/⌘+F; Markdown e immagini renderizzati inline. I messaggi di commit sono ricercabili e generabili dal diff staged tramite il servizio LLM host. 8 strumenti Agent, 51 endpoint HTTP locali, 8 lingue; token cifrati a riposo con AES-256-GCM.

Preset del flusso di consegna per DeepSeek Harness: protocollo agente e 7 strumenti conservano alla lettera le richieste dell'utente, registrano le decisioni sui feedback, pianificano attività con criteri di accettazione, annotano comandi di verifica reali e codici di uscita e scrivono riepiloghi finali in file JSONL per progetto.

Input vocale push-to-talk completamente locale per macOS: tieni premuto un tasto globale, parla, rilascia; la trascrizione viene incollata al cursore. STT locale (Qwen3-ASR 0.6B 4bit su MLX/Metal per impostazione predefinita, alternative SenseVoice e mlx-whisper), zero API esterne, servizio launchd autoriparante e script diagnostico a 8 punti. La Skill inclusa consente all'agente di installare, configurare (collegamento hotkey Karabiner, launchd, cambio motore) e risolvere problemi dell'intera toolchain.

Prepara i file prima che read, read_image e gli strumenti vision li aprano. Ridimensiona immagini oltre 2048 px o 8 MB (un nuovo tentativo a 1280 px nello stesso turno), converte BMP/TIFF in PNG e riconosce upload etichettati male esaminandone i byte. Converte docx/xlsx/pptx, PDF con livello di testo, csv/tsv e html in Markdown senza programmi esterni.

Una singola installazione aggiunge due strumenti PDF alla barra laterale DSH: salta a una pagina e sfoglia tutto il documento con pagine e miniature renderizzate localmente, oppure apri un PDF nell'anteprima nativa DSH. Include anche il comando /pdf.

Generazione di immagini senza chiave con due strumenti: generate_image (nessuna API key, una chiamata alla volta, tentativi limitati sui rate limit) e list_image_models.

Avvia il workspace locale pubblicato BeatDesign 0.2.5 e collega 30 strumenti MCP per Projects, Canvas, Assets e Timeline; include una Skill per progetti condivisi e indicazioni di approvazione per la generazione remota. Richiede Node.js 22.12+ e una porta libera 3020. Estrazione dei frame e rendering della timeline richiedono anche ffmpeg/ffprobe nel PATH; l'esportazione dal browser no.

Cerca le scadenze di invio agli eventi CCF con gli strumenti ccf_deadlines, ccf_venue e ccf_update, il comando /ccf e un pannello desktop che esporta l'elenco come calendario. Le date provengono da una sincronizzazione live (CCFDDL come fonte principale, verificata con una seconda; differenze di almeno 36 ore sono segnalate come conflitto tra fonti). Nessun dato è incluso; i prossimi 30 giorni restano nel system prompt.

Strumenti VPS con priorità di lettura: stato e azioni systemd, uso del disco, stato Docker, ultime righe dei log, backup configurati e pianificazioni delle ore di quiete.

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.

Lista di blocco strumenti deny-only per preset agente. Disattivare uno strumento in Impostazioni lo rimuove dallo schema di quel modo e ne rifiuta le chiamate. Non si può attivare nulla né aggiungere elementi a una whitelist; gli strumenti non bloccati restano invariati. Ogni riga mostra la descrizione dello strumento e le regole risiedono in un solo JSON fuori dal profilo.

Memoria per DeepSeek Harness con cinque sezioni (ricordi, albero, profilo, grafo, posta in arrivo), politica di acquisizione basata su regole per decidere cosa conservare o scartare e recupero ibrido BM25 più vettori su blocchi padre e figlio. Include dodici strumenti agente che leggono e scrivono gli stessi file locali.

Kit di ricerca locale prima di tutto per DSH: registra gli strumenti modello kb_grep, kb_list e kb_save. kb_grep cerca nella base Markdown con ripgrep se disponibile e ripiega su grep; kb_list e kb_save usano il servizio file ctx.fs con ambito limitato. Il percorso predefinito è ~/dsh-kb. Il repository include anche le skill local-first-research e session-memory, da copiare manualmente in una directory skill DSH: il bundle del plugin non le installa. Node ESM puro, senza dipendenze npm runtime, con harness di test node senza framework. Installabile con plugin_manager install_bundle; nessuna UI client inclusa.