Plugins

Map a remote server directory over SSH and SFTP into a controlled local cache workspace, so the model, agent, session and memory keep running on the local machine.

Replaces the composer's model selector with a starfield popup that sets the model and its reasoning effort in one control, and remaps the current effort to the nearest level the new model declares instead of failing the switch.

Requirement-to-evidence audit for DSH sessions: maps each requirement to tool calls, files and commands, records per-requirement verification, and sends missing items back to the agent.

GIS/CAD analysis toolkit for dsh: read DXF, convert DWG to DXF, query layers/entities, export styled analysis maps (SVG/PNG/JPG/PDF, plus PSD on Windows x64), and run GIS summary/buffer/overlay on SHP/GeoJSON/KML — pure-JS parsing, no GDAL.

Shows where every session's tokens go: lifetime totals, cache hit rate, peak/off-peak cost, a calendar heatmap, a trend chart, per-model and per-workspace breakdowns, and a session tree revealing subagent sessions, with CSV/JSON export. Also ships context clear/compact actions and a prompt optimization button.

All-session token usage dashboard in the sidebar: total and peak tokens, usage streaks, a 53-week activity heatmap, 7/30-day trend, per-model usage and a session ranking. Folded locally from the profile session projection cache, so sessions written by older session formats are counted too; no network access, and the read-only summary route refuses non-loopback peers.

Renders the seven-layer SQLite store of meow-memory as a live 3D star map, with draggable nodes, layer rings and a click-through detail panel. Requires the meow-memory plugin and Node 22.5+.

Contract clause work: build the clause tree, map it against a 12-key playbook, register the playbook and export the unresolved report — 5 `legal.*` tools.

IMAP mail triage and cleanup for DeepSeek Harness: incremental read-only scan, a hard-protection rule layer plus optional local-model classification, a Markdown report and a hashed manifest, an explicit approval card, and only then a move to the Trash mailbox — no expunge.

Read-only Linux port, service and Caddy route map: listening sockets with their owning unit or container, a reverse service view, and reverse_proxy liveness checks. Requires iproute2 (ss); docker and a Caddyfile are optional.

Mail for DSH: IMAP, POP3, SMTP and OAuth2 accounts with a reading tab, API senders, scheduled and CSV bulk sends with unsubscribe handling, and mail_* agent tools. The Mail tab appears inside dsh-better-sidebar; the agent tools work without it.

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.

Token usage dashboard for DeepSeek Harness: daily totals per model, with a trend chart, a calendar heatmap and a table view.

Floating Token Burn Dock for DSH that aggregates provider usage across every session: the collapsed capsule shows the live tokens/sec rate with an inline 60-second sparkline and today's total, while the expanded panel adds a large live-rate hero, per-model and per-hour breakdowns on a real left axis, and a 30-day commit-style heatmap. The sequence-frame flame burns only while tokens are actually flowing and goes out at rate 0; day and hour buckets follow the browser's UTC offset instead of the host process timezone, and the 31-day record store is written atomically after history load so a restart no longer wipes the numbers.

Adds a mobile hotkey mode to the DSH web composer that auto-detects touch and mobile devices and switches to Ctrl+Enter for send and plain Enter for a newline while leaving the desktop keymap untouched, with a Settings toggle, a /mobilekeys command and a window.__dshMobileKeys console API.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

Belegt Enter / Ctrl+Enter / Shift+Enter im DSH-Composer neu, sodass jeder Taste genau eines der drei nativen Verhalten zugeordnet bleibt (Zeilenumbruch, Senden mit Enter, Senden mit Ctrl+Enter). In den Einstellungen anpassbar.

Ergänzt die DSH-Konversationsansicht um eine verschiebbare und zoombare Radialkarte des Sitzungsbaums, die Abzweigungen zeigt; durch Klick auf einen Knoten wird gewechselt.

Tavily-Websuche für DeepSeek Harness: `ctx.web`-Suchanbieter sowie die Tools `tavily_search`, `extract`, `crawl`, `map`, `research`; Konfigurations-UI auf der Detailseite des Plugins.

DSH-Sekretär: prüft alle 15 Minuten den tatsächlichen Status ungelesener GitHub-Meldungen und schließt bereits erledigte. Merkt genannte Termine (Rechnungen, Verlängerungen, Dokumentabläufe, Geburtstage) und erinnert; überwacht den Posteingang nur lesend. Secrets nur im System-Schlüsselbund.

Ergänzt eine Gesprächsansicht, die die tatsächlich von einer Session verwendeten Skills, MCP-Tools und Subagents abbildet: Zuordnungsbaum, Aufruftabelle und ungenutztes Inventar.

Native Schaltfläche zum Fortsetzen unterbrochener DSH-Unterhaltungen und frei belegbare Tastenkombination.

Schreibgeschützter Code-Lesearbeitsbereich mit Multi-Repository-Projekten, quellverknüpften Notizen, Codekarten und Mermaid-Diagrammen.

Beweist, dass eine lokale Bildbearbeitung außerhalb der Maske alle Pixel unverändert ließ. Eingaben: Original-, Ergebnis- und Masken-PNG. Ausgaben: grepbares Urteil `MASK_PIXEL_LOCK=PASS|FAIL|EMPTY`, Differenz-Heatmap, Kanalstatistiken, Begrenzungsrahmen, stärkste Änderungen, eigenständiger HTML-Bericht und `report.json` mit SHA-256-Dateihash, kanonischem Digest geschützter Pixel und Proof-Digest, der beide an die Richtlinie bindet. Unterstützt Maskenpolarität für Bearbeiten/Sperren, Schwelle, Toleranz und Alpha ignorieren. PNG-Farbtypen 0/2/3/4/6, 1–16 Bit, fünf Filter und Adam7. Keine Abhängigkeiten, nur lokal: keine Modellaufrufe, kein Netzwerk/Upload.