Plugins

Adds a Chats/Files switch to the left-sidebar Workspace header that swaps the session list for a lazily loaded tree of the current session's workspace. Files and folders can be dragged into the composer as @path references; clicking a file opens the built-in preview; the right-click menu reveals a file in the system file manager or copies its path; entries carry VS Code-style Git status (modified, untracked, added, deleted, conflict, ignored) relative to the last commit.

Embeds a full calendar app as a sidebar panel and adds a draggable, resizable scheduled-task widget on the DSH page. Registers six agent tools (status, list, create, update, delete, summarize) that read and write the same SQLite database. The calendar's own AI is routed to the DeepSeek route already configured in DSH, and each reply shows token usage and cost, accumulated per day.

Adds an Archive workspace item to the workspace row menu: archives the sessions under that workspace through the official command, leaving the one you are currently viewing open, and refusing the batch while any session is still running. The host hides archived sessions but keeps the emptied workspace row in the sidebar; this plugin hides that row too, and restores the whole group from a footer panel backed by a ledger under $DSH_HOME/storages written behind a cross-process lock. Its count badge can be set to always, on-new-only, or never.

Adds a drag handle above the chat composer so its height can be set by hand at any content length, with double-click to restore auto-grow capped at 168px.

Reference other conversations from the current one — type @ to attach a session's record, drag a sidebar conversation into the composer, or open any conversation, tick single messages and insert them into another one.

A Storage settings page for DeepSeek Harness: a donut of what dsh occupies on this machine (install, sessions, attachments, runtimes, plugins, temp), a drill-down that lists archived sessions and can delete them, and a clean action that only touches rebuildable caches. Deleting to the system Recycle Bin and Open folder are Windows-only; scanning works everywhere. Host routes accept loopback connections only and are CSRF-guarded; nothing leaves the machine.

Adds custom task groups and an activity bell to the sidebar: drag sessions into or out of a group, reorder them by hand, collapse groups, and see running, waiting and unread sessions in one place.

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+.

Fold the sidebar plugin-panel list to three entries, drag them to reorder, and keep every other panel one click away in a More menu — order and pins persist in localStorage.

Rearranges the panel entries at the top of the DSH sidebar: drag to reorder or sort alphabetically, hide an entry without unloading its plugin, and split entries into named groups that render as titled separators; group headers collapse on click. A layout guard caps the entry list height and makes it scroll, so a growing list no longer squeezes the session and workspace panes out of view. An optional switch lets the profile's default model propose groups, and the host whitelists the returned ids and labels before they are stored locally.

A project kanban in the dsh sidebar. Every project gets its own section with four fixed columns (todo, in progress, feedback, done); add, rename, recolor, reorder and delete projects and tasks, advance a task with one click, reorder by drag and drop or with the card menu, undo a deletion, and collapse a project. Clicking a project opens a page for its key data and results: two trees (data on the left, results on the right) you arrange by drag and drop and merge into chapters, lines that show which result came from which data, stars with a star-only view of the same tree, relations between results, colours by category, and undo or redo with Cmd+Z. Colours, radii and shadows come from the dsh theme, so it follows light and dark, and the layout reflows from four columns to two to one.

Group skills into named sets, toggle any combination, drag to reorder, and preview each group catalog token cost.

Workspace conversation categories with drag-and-drop ordering, collapsible groups, activity indicators, and workspace registration by directory path.

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.

Provider-first model picker for the composer. Every provider is listed in the left rail and its models in the right pane. Providers, models within a provider, and pins reorder by drag or Alt+Arrow; providers take a local display alias; one provider can be the panel default; a model's reasoning levels expand inline; search matches model names, provider names and aliases. Switching goes through the shipped model directory service, so the /model popup and this panel always agree.

In-chat image viewer for DeepSeek Harness: wheel and trackpad pinch zoom at the pointer, two-finger and drag panning, gallery navigation, downloads named from the image description and timestamp, and opening workspace originals in the system default app.

Region screenshot for the composer on Windows: a full-virtual-screen selector frames the region (drag the frame, eight grips, Ctrl+drag to annotate), and the finished PNG lands in the composer as a pending attachment.

A Web3D energy orb decoration for the DSH Web GUI: a particle core wrapped in three mechanical rings that shrinks and falls silent while the session is idle and pulses in a double-beat heartbeat while a turn runs. UnrealBloom glow, draggable with its corner, position and size remembered, and three.js served locally by the plugin instead of a CDN.

Neuron-inspired memory for dsh: turns buffer into a hippocampus, a nightly patrol classifies fragments into pools, and each turn injects a minimal auto-compacted handoff, the live mood (via dsh-feiyu-mood), and only relevance-filtered memories (Ebbinghaus half-life decay; recalled memories are reinforced like spaced repetition). Hard caps bound storage; past-session original text is searchable over multi-frame zstd; dsh-fish-memory stores can be imported. Optional vector retrieval (off by default, keyword fallback). The 3D panel offers four themes and pulses a signal from the center to each recalled memory.

Search every DSH chat session and jump straight to the matching message: multi-keyword AND search, scoped to the current session, all sessions or one project, anchored by call id for tool hits, with a draggable panel for previous and next.

Free ordering for the DeepSeek Harness Web Settings navigation: drag, Alt+Arrow or the footer's ↑/↓ controls reorder the Settings dialog's left column, persisted in the host profile configuration. 设置左列自由排序：拖动 / Alt+↑↓ / ↑↓ 按钮，写入宿主 profile，跨浏览器生效。

Flowspot — Charles-style HTTPS capture for DeepSeek Harness (Windows): an in-plugin MITM proxy, system-proxy and CA automation, flow storage, and agent tools. Flowspot：面向 DeepSeek Harness 的 Charles 式抓包插件——插件内 MITM 代理 + Windows 系统代理/CA 自动配置 + 流量存储 + agent

Restart and quit controls for the DSH desktop GUI, in two independently switchable places: a draggable floating button that snaps to a screen edge and collapses into a thin strip, and a power button in the sidebar footer.

分层记忆与混合召回知识库插件：把「记得住人、能召回可靠信息」的记忆系统接进 DeepSeek Harness，附带来源标注、置信度兜底与画像管理