Plugins

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_*`.

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.

Read-only monitor for local DSH sessions: live task board, per-session tails, blocking reply wait, Markdown export, and optional IM push via dsh-im. Requires Python 3 with the zstandard package; IM push additionally needs the dsh-im plugin.

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.

Post-build patch for the maid-atelier skin, mounted as a bundle: the window backdrop walks six time-of-day bands on the local clock with continuously interpolated sky and interior light, and the figure moves on its own (breath, weight shift, float, blinks, optional hem and hair displacement); applied to an already-installed skin and reverted from client.js.orig when the plugin is removed.

Windows resource monitor for the DeepSeek Harness (dsh) sidebar: samples CPU, memory and clock speed once a minute, keeps a 30-day history and draws separate 24h / 7d charts for CPU and memory (with 85% / 90% alert lines) plus a frequency chart that marks load-time throttling. Reports sustained CPU >= 85% (10 min), memory >= 90% (10 min) and frequency <= 70% of maximum clock under load (5 min).

Find text inside the open conversation with Ctrl+F: matches are highlighted in the message text, previous/next step through them, clicking the count lists the matches and jumps to any of them, and the count grows while the scan runs. No collapsed block is opened and the reading position does not move.

Renders mermaid code blocks in dsh web chat as diagrams. Each block gets a toggle in its header to switch between the diagram and the source; blocks still streaming stay as code until the message settles. Mermaid loads lazily the first time a diagram is shown. The terminal UI is unaffected.

Puts Grok Bot's own face in the DSH sidebar session list: each row's status dot becomes a living GrokBot avatar whose six motions read as idle, working, waiting, blocked, thinking and done — color marks the project, motion marks the state.

Transforme une fonctionnalité réellement opérationnelle en vidéo de démonstration fiable : captures d'écran réelles, narration edge-tts avec sous-titres calés mot à mot, pipeline ffmpeg autonome et contrôle qualité déterministe (spécifications, audio, niveau sonore, détection d'écran noir, d'image figée et de silence) qui refuse toute démo fausse ou défectueuse. Inclut le précontrôle et la vérification des artefacts. Requiert Python 3.9+, ffmpeg/ffprobe dans PATH et `pip install edge-tts Pillow` ; la narration appelle le point de terminaison public edge-tts.

Sélectionnez du texte dans la transcription, faites un clic droit et citez-le dans le composeur. La citation est transmise sous forme de puce atomique et affichée dans une carte repliable ; le modèle reçoit le bloc complet avec le rôle du message, le tour, l’index du bloc et la plage de caractères.

Rendu du streaming fluide et défilement doux pour les réponses DeepSeek Harness, y compris Markdown, blocs de code, tableaux et résultats d’outils.

Horloge des tarifs DeepSeek pleines/creuses pour le HUD du composer DeepSeek Harness.

Casque de sécurité pour le code IA : niveaux d’écriture L0 lecture seule / L1 workspace seul / L2 complet, avec confinement des modifications privilégiées. Sous le niveau requis, refuse l’écriture et renvoie un bloc prêt à coller. Chaque chemin subit un contrôle raw-string de traversal et realpath, détectant aussi les échappements par junction.

Fait examiner les commandes shell destructrices par un modèle avant exécution, demande confirmation ou les bloque, et interrompt une commande en cours après suppression d’un trop grand nombre de fichiers.

Rétablit l’accès aux domaines bloqués par filtrage SNI sous Windows depuis DSH, sans serveur auto-hébergé.

Plugin de déclenchement événementiel (la sonnette du réveil dsh-proactive) : fs watchers récursifs avec fenêtres debounce et filtres glob par règle ; endpoint webhook limité à loopback avec token par règle ; règles qui réveillent une session cible via le service agents du host (follow-up direct si active, reprise préalable si inactive) et injectent un prompt avec variables paths/count/payload. Recharge à chaud le fichier des règles sans redémarrer DSH et ajoute chaque déclenchement à un historique JSONL auditable, consultable avec trigger_list et trigger_history. Route health loopback pour l’état d’installation et d’exécution. Exemples : ranger les téléchargements, diagnostiquer les alertes CI de scripts locaux, surveiller les logs. JavaScript pur, sans build, MIT.

Précontrôle des permissions graph-first pour DSH. Le modèle déclare un graphe de calcul dont les nœuds décrivent l’opération (quoi télécharger et où, quoi écrire ou supprimer). L’utilisateur approuve les nœuds un par un dans un panneau latéral ; une approbation couvre une exécution réussie. Chaque nœud conserve une trace d’audit de l’exécution réelle. Les opérations non couvertes redemandent l’accord via la carte native ; un nœud bloqué par une autorisation sans réponse est suspendu, tandis que les tâches indépendantes continuent.

Mode deliver-and-align : l’agent remet un bloc à la fois via align_deliver ; chaque bloc est immédiatement écrit sur disque pour être modifié sur place, puis l’agent relit votre version avant de poursuivre.

Recherche dans le catalogue des skills installés lorsqu’un mot déclencheur apparaît, impose une décision use/skip pour chaque candidat et bloque les autres outils jusqu’au chargement de tous les skills sélectionnés.

Windows uniquement (lie user32.dll via koffi ; inactif sur macOS/Linux). Mémorise taille et position de la fenêtre principale de DeepSeek Harness et les restaure à chaque lancement, en les réaffirmant pendant une période de grâce pour l’emporter sur la disposition par défaut. Les déplacements/redimensionnements manuels stables deviennent le nouveau verrou ; les états minimisé, maximisé et plein écran ne sont jamais enregistrés, et le rectangle posé par défaut par DSH n’est jamais adopté. Reste à l’écran lors d’un changement de moniteurs. Compatible avec DSH 0.2.1-rc.3+.

Studio de contrats API pour DeepSeek Harness : définit les sept éléments à verrouiller avant le développement, rédige et révise OpenAPI, classe les changements incompatibles selon leur effet réel sur les clients et traite les formats d’erreur, le versionnement et la dépréciation. Comprend six playbooks et un routeur.

Refuse les attentes au premier plan des agents DSH : commandes d’attente (sleep, wait, tail -f, watch, ping sans -c, boucles infinies), outils bloquants (wait_agent, job_output avec wait: true), répétition rapprochée d’une même commande de contrôle et commandes exigeant une intervention humaine (sudo sans -n, ssh sans BatchMode, connexions, éditeurs interactifs, docker -it). Propose une reprise concrète en arrière-plan ou la fin du tour. Budget et fenêtre de sondage configurables ; langue du message selon system (zh/en). Aucune dépendance à l’exécution.

Lit NTQQ (QQ 9.9.x) local sous Windows/Linux et exporte les chats de groupe/privés en txt/csv/json/md/html/sqlite. 16 outils : 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 (refuse l’ambiguïté ; nettoyage sur liste autorisée). UI 127.0.0.1:46728 : index SQLite incrémental, 6 vues, tâches, une colonne sur écran étroit, expéditeurs masqués, médias groupés, découpage quotidien, préréglages, ZIP AES-256 protégé par mot de passe. OCR/voix/embeddings s’installent à la demande dans le virtualenv du plugin. Requiert python3/sqlcipher3 ; Paramètres crée le virtualenv. Clé lue dans QQ ouvert et connecté.