플러그인

Compress every idle session's context at a fixed time each morning on DeepSeek Harness: a daily run (08:30 by default), a catch-up run on the next launch after a missed slot, and a /compact-all command for on-demand compaction, with per-session outcomes reported.

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.

Public chat rooms with quoted replies and opt-in encrypted private text chat inside DeepSeek Harness, using a shared Nostr relay and locally protected identities (macOS Keychain or Windows DPAPI; Linux has no identity store, so posting is unsupported).

Multi-select system-prompt picker behind one bolt icon in the composer: check saved rows to inject in order, each scoped to main agent, sub-agents or both; every row (the built-in 「火力全开」, "Full Throttle", included) can be edited and deleted, and Clear all only unchecks every row without deleting anything.

Community fork of kingcharleslzy-ai/dsh-purge (do not install both - both register the same `dsh-purge` row as the `dsh-purge-community` package): the community '破甲' (unrestricted-mode) control for DeepSeek Harness - host-policy patches, prompt and rule settings, diagnostics, verified updates, and local backup and rollback, plus a three-layer bootstrap installer (engine, code and prompt layers) with its own verification pass.

Manages the lifecycle of the local UM GenAI proxy (127.0.0.1:8788) that DSH's um-genai provider talks to: wakes it on demand for llm/stream calls, stops it after an idle period, and reports health plus a read-only status endpoint. Also ships a DSH settings page for port, always-on mode, idle minutes, interpreter and paths, plus the UM account and proxy API key, and a button that writes the providers.um-genai entry into the profile patch and fills in its model list, since a fresh profile has no provider and the model picker would otherwise stay empty. A renewal watchdog logs in to the campus gateway on a hidden Windows desktop when the upstream token expires. The proxy itself is um_opencode_setup.py, a single-file tool distributed by the University of Macau; a copy is vendored in vendor/ so a fresh install works out of the box, while a copy in ~/.um-opencode/ takes precedence when present. The plugin still does not produce tokens: those come from logging in to the campus gateway. Requires Windows (process discovery and idle shutdown use netstat/taskkill; renewal uses PowerShell and a hidden desktop), Python 3.10+ and a University of Macau account.

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.

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.

Talks to the two public Hugging Face Spaces (MiniMax-VL-01 and Llama-2-7B-Chat) that grok3ai.org only embeds in an iframe, presenting them as OpenAI-compatible models.

Runs a local OpenAI-compatible relay that forwards DSH chat requests to grok.online, exposing its two chat models in the model picker without an API key.

Turns the DSH web UI into the H.D.D Hollow Deep Dive terminal from Zenless Zone Zero: the sidebar and composer are reskinned. Ships a small read-only host half plus the web skin; switch it off and DSH returns to its native light UI.

WeChat-style skin for the Harness web UI: grey chat list, green outgoing bubbles, white incoming bubbles, a green send button, and a 已归档 tag on archived sessions.

CGSS idol theme with multi-character Web colors and card artwork, immersive reading, and an optional Windows desktop companion.

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.

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.

Trims the GenUI card component prompt per global, workspace, or session scope; the built-in presets cut 24% to 61% of the prompt.

Appends the current turn's estimated token cost in CNY to the assistant action row, right after the usage/time indicator. Prices come from a built-in DeepSeek peak/off-peak CNY table (Beijing time, Monday-Friday 9:00-12:00 and 14:00-18:00) and can be overridden from the profile's cordis.patch.yml; a model without a configured price shows a dash instead of a made-up amount. Follows the shipped Performance & usage - Compact setting and hides together with the usage pill. Token cost only, per turn only.

OpenCode Go subscription usage beside the composer: the rolling 5-hour, weekly and monthly windows each as a small ring with the used percentage (amber at 70%, red at 90%). Clicking the meter opens a detail card with per-window progress bars, reset countdowns and a refresh button, and when it is not clicked nothing floats over the conversation. The API key stays in the Host process and never reaches the browser.

Balance, remaining tokens and token/money usage waves for DeepSeek Harness: a sidebar footer card plus a panel docked in the empty gutter left of the conversation, with 1h/6h/24h/7d stacked token-or-currency waveforms, a live tok/s strip and a per-command cost breakdown.

Adds a Share to chat action under each reply: converts the answer to WeChat or WeCom text, ordered segments or a long image, editable-table email HTML, or a downloadable Word document.

A composer control: shows the current model's context window, the tokens in use and a rough system / tools / messages breakdown, switches the model's reasoning effort in one click (writing reasoningEfforts into the model config when the provider declares none), and edits the model's contextWindow from the same panel so custom-provider models stop silently inheriting the adapter default. Makes no model calls; reads only the official session projections, model directory and config-forms services.

Adds a space-key Quick Look preview to DSH deliverable cards. Hovering a card and pressing Space opens the native macOS QLPreviewPanel for the file, which covers docx, xlsx, pptx, pdf, images and media that the sidebar preview cannot render. The panel zooms out from the card's position, returns focus to the composer when closed, and exposes hover delay, focus-return and double-click behaviour in Settings > General.

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.

Optional source-preserving chat rendering with selectable themes, offline Uiverse component tools and a report-local evidence workspace. Preview for DSH 0.2.1-rc.2.