Plugins

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.

Matrix-style binary (0/1) digital rain for the Harness interface: columns spawn only while a task is running, fall off screen when it stops, and leave a blank canvas; frosted-glass token layer with adjustable digit and panel opacity.

Session cost meter forked from dsh-cost-meter, retargeted at OpenDesign Cloud: per-session and per-day cost, a 39-model OpenDesign price catalog, OpenDesign Cloud quotas as rolling 5-hour and 7-day used/total bars read from the official funding-check endpoint, Coding Plan quotas, provider balances, peak/off-peak notices, bilingual UI. The quota card needs an OpenDesign Cloud account (the plugin has a built-in login), and it provides service:cost-meter like Han-1413141/dsh-cost-meter and the other dsh-subscribe-meter variants, so install only one cost meter: it replaces dsh-cost-meter rather than running alongside it.

Session cost meter forked from dsh-cost-meter, retargeted at OpenCode Go: per-session and per-day cost, a 90+ model price catalog with automatic matching, OpenCode Go subscription usage as rolling 5-hour / weekly / monthly percentages with progress bars, Coding Plan quotas, provider balances, peak/off-peak pricing notices, bilingual UI. It provides service:cost-meter like Han-1413141/dsh-cost-meter and the other dsh-subscribe-meter variants, so install only one cost meter: it replaces dsh-cost-meter rather than running alongside it.

Session cost meter forked from dsh-cost-meter, retargeted at a self-hosted gateway: per-session and per-day cost, a 90+ model price catalog with automatic matching, gateway quota (one-api / new-api / sub2api, auto-detected) shown as used/total bars for the provider configured in DSH settings, Coding Plan quotas, provider balances, peak/off-peak pricing notices, bilingual UI. It provides service:cost-meter like Han-1413141/dsh-cost-meter and the other dsh-subscribe-meter variants, so install only one cost meter: it replaces dsh-cost-meter rather than running alongside it.

Session cost meter forked from dsh-cost-meter, retargeted at Command Code GOAT: per-session and per-day cost, built-in 90+ model price catalog with automatic matching, GOAT subscription quotas (5-hour / weekly / monthly pool) as used/total bars, Coding Plan quotas, custom provider balances, peak/off-peak pricing notices, bilingual UI. It provides service:cost-meter like Han-1413141/dsh-cost-meter and the other dsh-subscribe-meter variants, so install only one cost meter: it replaces dsh-cost-meter rather than running alongside it.

A Settings page for the memo plugin suite in DSH Web: edits the memo Host's AI route, archived-session summary language, length, transcript budget, template and prompt, and repository URL, adds a GitHub intake section for the claim label, per-run issue cap, autopilot switch and its working directory, preset, time zone and dispatch prompt, with per-field reset and saves that reach the running services without a restart, and carries an update entry that checks the npm registry and can install a newer release through the deployment's plugin manager.

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).

Install, update and remove DSH plugins from a tab in the Plugins page. Installs call the profile's in-process pluginManager service, so a plugin can be added while the desktop app is running instead of only through the CLI. Updates are delegated to dsh-market's public update API v1 (required for that section) and show the reported phase, percent and downloaded bytes as a progress bar, with rollback when the market reports a restore point. When removal is refused because the bundle is in use, it disables the bundle, drops it from the profile manifest, and queues the leftover files under the profile for a sweep after the next start.

Loopback HTTP/SSE service that lets an Obsidian plugin drive DSH sessions (list, create, send) and inject up to ten vault notes into the system prompt; needs the companion Bridge plugin running inside Obsidian.

A sidebar panel that moves, rebuilds, merges, renames and deletes whole workspaces: a move re-publishes each session log with the new directory in its header, repairs the workspace record, refreshes the cached title, and every card shows whether its sessions are running or only open.

Adds folders to a running DSH Web workspace from the Windows Explorer context menu and starts dsh web automatically when needed; the menu itself requires a one-time per-user PowerShell installer run from a repository clone (no admin rights).

A cut-out whale-girl maid desktop pet in the corner; click her to see your DeepSeek account credit and this session's running state.

Controls an already-running NetEase Cloud Music desktop client over CDP (the client must be started with --remote-debugging-port=9222) and searches songs through NetEase's public web API; no API key or extra login, and member-only features use the client's own signed-in account.

Reviews destructive shell commands with a model before they run, asks you to confirm or blocks them, and aborts a running command once it has deleted too many files.

Cursor-style mode switching for the dsh web UI: plan mode with a delegation gate, multitask mode with a tool-call quota, and the create_plan / request_more_edits / list_running_agent tools. Adds a plan card with Build buttons and compacts the subagent dropdown to running rows.

Windows-only: per-session auto-shutdown switch in the session header — once every armed session has no turn, job or subagent still running (by default every other live session must be idle too), a two-minute countdown starts and the machine powers off; clicking the countdown cancels it, and sessions without the switch never start one.

Manage subagents and Agent Teams teammates in DeepSeek Harness: stop running instances, then really remove them by retiring their catalog and roster records with seq-preserving log tombstones and moving their session directories to a recoverable trash; model tools, a conversation-header panel and an offline CLI.

Five DSH utilities in one plugin: drive existing sessions over QQ (needs an OneBot 11 implementation such as NapCat running alongside), ask another session a question with a context guard, pause the running turn, restart DSH on Windows with optional auto-resume (via the install-restart.ps1 scheduled task), and inject peak-hour token discipline.

Connect DSH to a local BiliMemory backend for Bilibili search, collection, status and login tasks, A-Memorix shared memory health checks, plus QQ link status, QQ user allowlists and QQ watcher restart. The repository includes a Windows one-click installer that installs or repairs MaiBot A-Memorix when missing, then configures local-bge-small-zh, embedding and shared memory. It also provides install-memory.cmd for memory-only repair. Requires Windows, DSH Desktop 0.2.1-rc.2+, Node.js 22.19+, Python 3.12, Playwright/Edge, FFmpeg, a running BiliMemory API at 127.0.0.1:8765, a local embedding service at 127.0.0.1:11435, a Bilibili login, and MaiBot/NapCat for QQ. Voice, RVC and cover features are excluded.

Reads the local NTQQ (QQ 9.9.x) message database on Windows and Linux and exports group and private chat history to txt, csv, json, md, html or sqlite. Ships sixteen model tools: qqnt_status and qqnt_doctor for environment and blocker checks, qqnt_extract_key, qqnt_index to build or inspect the sidecar index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats for totals and monthly counts, qqnt_export_group, qqnt_export_chat and qqnt_export_batch (a chat can be named the way the user says it, and ambiguity refuses instead of guessing), qqnt_jobs for OCR, speech-to-text, chunking and model downloads, qqnt_media for a chat's downloaded images, qqnt_storage for disk usage and allow-listed cleanup, and qqnt_ask plus qqnt_recall for retrieval with citations. The local web UI on 127.0.0.1:46728 adds an incremental SQLite index, six views (chats, export, statistics, ask, settings, models), a task panel, a single-pane layout on narrow screens, sender redaction, media bundling, per-day splitting, export presets and AES-256 password ZIPs; OCR, speech and embedding components install into the plugin's own virtualenv on demand. Needs python3 with sqlcipher3 (the settings page can create a private virtualenv), and the database key is read from the running, logged-in QQ client.

Connects AutoCAD, ZWCAD, GstarCAD and BricsCAD to DeepSeek Harness over MCP, bundling the CAD server and building a private Python environment on first run. Requires Windows, one of those CAD applications installed, Python 3.10+ on PATH, and CAD running as the same Windows user and at the same privilege level as DSH.

Asks before archiving a DeepSeek Harness session, then backs the archived copy up to a directory you choose — one folder per session with the session log, its attachments and the metadata, plus a manifest, a restore note and a Markdown ledger. Adds a right-sidebar browser for archived sessions and a double-click restart button (Windows only; disabled while a session is running).