Plugins

A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).

Material library for dsh: collect a folder, file or note from a conversation, keep it in real folders with tags, browse it Finder-style, reopen the source chat's output in one click. Ships a materials_archive tool plus auto-filing rules: file a task's deliverable once, and every later scheduled run files the new documents by itself.

Turns "restarting the host" into one interrupt that many sessions can share. Several sessions queue onto the same restart (8 by default, configurable, joinable at any time including mid-wait); the host is closed once and relaunched once; then each waiting session is woken separately with its own reason and starts running its own work without waiting for the others. Each session decides independently whether to resume, one failed delivery never affects the rest, and a session can drop only itself without cancelling everyone else's restart. Windows desktop only.

Actually delete DSH sessions instead of archiving them (Windows only). Clears all six on-disk locations (transcript, title cache, billion-context SQLite index with VACUUM, workspace registry, cost-meter ledger, bridge logs) with a dry run, a backup, byte-for-byte rollback, and an automatic quit-delete-relaunch flow.

Turn on the built-in session full-text search backend (session-query-sqlite, SQLite FTS5) that dsh ships disabled by default, so the sidebar magnifier searches message bodies with snippets instead of titles only.

Persona slot for DeepSeek Harness: each session holds exactly one persona that a later write replaces, a global persona covers every session without its own, a /persona command edits both in conversation, and the Installed page exposes a multi-line panel for the global persona. Persona length is unbounded. Supports DSH 0.2.1-rc.2 through rc.5.

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.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

Connects Qoder models to DeepSeek Harness through the official Qoder CLI over native ACP stdio (no reverse-engineered model API), with qoderclicn (China) having a verified real ACP tool loop; qodercli (international) is selectable but its real inference path is not yet verified. Requires Node.js 22.18+ and the chosen Qoder CLI installed and logged in on the same machine; the plugin does not install or manage accounts.

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.

Antigravity provider for DeepSeek Harness: resolves the OAuth client from the locally installed official desktop app and supports multiple accounts with quota-based automatic switching.

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.

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.

DeepSeek balance, today's spend, peak/off-peak countdown and per-turn cost rendered as one text line embedded in the DSH sidebar footer, plus a low-balance alert. A text-only derivative of dsh-whale-widget (MeteorNOX/DeepSeek-Balance-Whale-Widget); do not install both - they register the same /dsh-whale/* routes and share the same ledger files.

A floating whale-girl pet in the DSH web GUI: every hour it takes one article from a bundled 33-essay corpus of Mao Zedong's selected works and puts a cited line with its source link, one of six business angles (customer, project, organisation, cash flow, decision, self-discipline) and a one-line nudge for a founder into a bubble capped at 200 characters. Ships the maoxuan-pet preset and a maoxuan-vademecum skill over the same corpus, four poses, quiet hours and a daily cap.

A Workspaces-native Recent sessions section for the DSH left sidebar: favorites, running, waiting-for-you and unread sessions at a glance, with a one-click ☆ on every session row, one-line collapse and in-section search. It takes over the sidebar shell (the shipped sidebar package is disabled) and renders the official workspace/session browser inside it; its recent-sessions panel id conflicts with huangxp12/whybebabo, so do not install them together.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

A local overview of installed DSH plugins. It does not install packages — pair it with a plugin market. Fold third-party settings, organize notes/groups with AI, check health and toggle plugins, so nothing gets lost in clutter.

Reads a few lines of a txt or epub novel inside the sidebar bottom panel, styled to pass for scratch notes; pages with Ctrl+Alt+J/K and keeps progress locally. Requires dsh-better-sidebar 0.26+ - the reader exists only as a tab in its bottom panel.

Transparentes, immer oben liegendes Desktop-Tier, das über das Hostmodell chattet, beim Klick Animationen abspielt, zeitgesteuert flüstert, Aufgabenfortschritt ansagt und den Kontostand zeigt. Läuft in DSH Desktop mit der enthaltenen Electron-Laufzeit (~/.dsh/electron); fehlt sie, erscheint das Tier nicht. Nur Windows.

Ermöglicht dem Telefon den Zugriff auf den DeepSeek-Harness-Desktop über LAN-Adresse oder Cloudflare quick tunnel, mit QR-Kopplung, Live-Sitzungsfeed, Genehmigungsabfragen und schwebendem Desktop-Widget. Beide Zugänge (LAN und Cloudflare quick tunnel) sind standardmäßig aktiviert; jedes Telefon erhält ein eigenes Token.

Durchsucht medizinische und biowissenschaftliche Literatur nach Thema, Stichwort oder DOI über Europe PMC, PubMed, OpenAlex und Crossref. Ermittelt Open-Access-Status über Unpaywall/OpenAlex/Europe PMC; wenn ein OA-Weg existiert, lädt er das PDF nach Prüfung von Magic Bytes und Seitenzahl herunter. Sonst erstellt er eine Entscheidungskarte mit dem genauen Fehlergrund und vier manuellen Alternativen: AbleSci assistance, Sci-Hub, SciDown und X-MOL. Das enthaltene Python-Tool verwendet nur die Standardbibliothek.

Vollständig lokale Push-to-talk-Spracheingabe für macOS: globale Taste halten, sprechen, loslassen; die Transkription wird am Cursor eingefügt. Local-first-STT (standardmäßig Qwen3-ASR 0.6B 4bit auf MLX/Metal, Ausweichmodelle SenseVoice und mlx-whisper), keine externen APIs, selbstheilender launchd-Dienst und 8-Punkte-Diagnoseskript. Der enthaltene Skill lässt den Agenten die gesamte Toolchain installieren, konfigurieren (Karabiner-Hotkey-Verknüpfung, launchd, Engine-Wechsel) und Fehler beheben.

Bereitet Dateien vor, bevor read, read_image und Vision-Tools sie öffnen. Verkleinert Bilder über 2048 px oder 8 MB (ein erneuter Versuch mit 1280 px im selben Turn), wandelt BMP/TIFF in PNG um und erkennt falsch bezeichnete Uploads anhand ihrer Bytes. Konvertiert docx/xlsx/pptx, PDFs mit Textebene, csv/tsv und html ohne externe Programme in Markdown.