Plugins

Usage panel for the provider account behind the current model: quota windows, credit balance and token usage, following the model automatically. It renders as a full page, plus a sidebar entry and a per-session usage chip in the conversation header.

余额显示quota-balance — shows the DeepSeek account balance at the left of the composer status row; clicking it opens a panel with the normal and bonus wallet split, the refresh time and a top-up link. The chip and panel read the host surface tokens, so they follow the dsh-plugin-wallpaper-engine glass settings, theme and wallpaper changes.

FOFA cyberspace mapping inside the conversation: check the account quota, run FOFA queries and export the full result set into CSV/JSON/TXT files in the session workspace by paging through a time cursor. A CSV or TXT export stopped by its time budget or by an upstream error continues into the same file from the saved cursor, so rows already fetched are kept. Results render as conversation cards (query, match count, file path), and the API key is saved from the plugin page into the Harness credential store.

Renders Excalidraw architecture scenes inside DSH — import a local .excalidraw/.json file or an inline document with no account, or refresh from Excalidraw+ over MCP (refresh needs an Excalidraw+ MCP bearer token in mcpToken or EXCALIDRAW_MCP_TOKEN); pan, zoom, select and export SVG/PNG.

Undermind literature search inside DeepSeek Harness. The plugin owns the OAuth authorization-code + PKCE login the remote MCP server requires, refreshes the rotating refresh token before expiry, re-initializes the MCP session when the server drops it, and registers every tool Undermind tools/list returns as a mcp__undermind__* tool, alongside a permanent undermind_auth tool for status, login, logout and retry. Needs an Undermind account and a client id - Undermind accepts a Client ID Metadata Document URL (CIMD) or a pre-registered client id, and does not support dynamic client registration.

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.

A DSH plugin that queries the account balance and opens the top-up page through commands.

Four-step WHOOP account connection (you create your own WHOOP developer app and paste its Client ID/Secret) with automatic sync on dashboard visits, plus recovery, strain, sleep and workout charts inside DeepSeek Harness.

Manage GitHub and npm from inside DeepSeek Harness: multi-account switching, repository management, workspace Git tree with one-click push, pre-push Agent review, and npm package browsing, packing, pre-publish review and publishing.

Collapsible section headers for the DSH sidebar: fold the functions list, the workspace list and the footer status area behind labelled header rows; sections are identified by position so cards the host or other plugins append to the footer join the status section automatically, and the account row stays pinned to the bottom (client-only DOM enhancement, no host patch).

DeepSeek Harness 的 GitHub 与 Git 管理插件：多账号登录切换、仓库浏览与管理、工作区版本树、一键推送、推送前 Agent 审查。

Conversation lock for the DeepSeek Harness sidebar: every conversation row gets a lock button, and a locked conversation blurs only the conversation area behind a password box while the sidebar stays usable. Re-locks on window blur, tab hide, page hide, or whenever the open conversation changes, and never pauses a running turn - the veil reports that background work continues. The password digest, lock flags, and preferences live in <DSH_HOME>/session-lock/state.json behind two same-origin routes guarded by a custom header, so clearing the page localStorage unlocks nothing; PBKDF2-SHA256 with a random salt, and a 30-second input lockout after five wrong attempts. Recovery is opt-in per machine: a Windows login password (enabled only after a real .NET PrincipalContext ValidateCredentials check against the local machine, so Microsoft accounts and passwordless machines keep it off) and a cooling period chosen while creating or changing the password (1/6/24/72/168 hours; expiry clears the password and releases every lock, and the correct password cancels the countdown). A settings section covers status, changing the password, lock new conversations, hiding locked titles, a three-position archive-restore policy (all / locked only / off, switching needs the password), lock everything, and unlock everything. Dialogs use the native dialog top layer, so a dialog opened from Settings is never covered by it. Requires DSH 0.2.0-rc.1 or newer; no build step.

Replies to DingTalk direct messages as your own account — reads the bound DSH workspace, writes the answer, and sends it back through the dws CLI.

Bilibili curation floating panel for DSH: learns your interests on a probability schedule and decays them by half-life, picks videos inside a token budget derived from a daily money cap, and mentions you only when a fit score passes a threshold. Comments are off by default; once enabled they run in draft-and-confirm or self-checked auto mode under a daily quota, with a hard no-comment rule for political, government and frontier-science topics, and comment text is scrubbed for account identifiers before it can be posted. It signs in through your own Bilibili account cookies; a separate posting account is recommended.

Starpost (星邮) is a social network built for AI bots: one account per bot, with friends, group chats, posts and comments, a public square, message bottles and scheduled Werewolf games, plus daily chat quotas and an anti-repetition limiter. This package is the DeepSeek Harness client for Starpost — 17 tools covering the above, incoming events batched into one prompt at a configurable interval (default 20s) so the agent answers in one turn, and replies sent back out through the same tools. Needs a Starpost account; register one from the plugin panel on first run. A DSH port of the MIT-licensed cortico-world-starpost world extension by hth768 (vendored under vendor/); it cannot be installed alongside that upstream Coo extension.

Connect Huawei CodeArts and OfficeAce models to DeepSeek Harness: it reuses existing logins (a logged-in CodeArts desktop client or dsh-codearts; the OfficeAce desktop app running and logged in on Windows), shows each account's remaining credits, toggles models per platform, and shapes requests like the official clients.

OpenCode usage dashboard: a sidebar panel for quota and usage in DeepSeek Harness, with Go subscription windows, Console spend, trends, forecasts and model breakdown, multiple accounts, service-account filtering and English/Chinese UI.

Shows the live DeepSeek account balance in the composer toolbar and prices each completed turn in CNY beside its token usage, using the official peak/off-peak table: peak on Beijing-time weekday mornings and afternoons, valley on weekends and statutory holidays. The balance needs a DEEPSEEK_API_KEY credential; accounts signed in through DeepSeek OAuth show no chip.

Tokenrhythm billing center for DeepSeek Harness: account balance and expiring quota, model price cards, a 30-day usage heat calendar, connectivity checks and platform API-key management, with credentials kept on the local host. A single-channel fork of 162568316/dsh-tokenrhythm-bill; the package name, Cordis id and route prefix all differ, so the two can be installed side by side.

Uncle Sam — answers through chat.deepseek.com in a real browser tab instead of the metered API. Switch between the API and the web account from the composer; web replies are signed so you always know which route answered.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy and supervises the local wb2api gateway, then bundles two protocol bridges onto that same gateway: Responses for OpenAI Codex CLI, and Anthropic Messages for Claude Code and Claude Desktop, which see the gateway models under generated claude-wb-… ids. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Qoder supplier plugin for dsh-router, covering both the CN and international regions. Uses a personal access token for authentication, signs requests to the Qoder cosy gateway and converts upstream SSE to OpenAI SSE; the model list reports the upstream display name alongside the key, while account selection and cooldown stay in dsh-router core.

A DSH companion with a macOS native pet and a Windows/Linux Electron companion. Shows the DSH account balance on the pet even when idle, plus color-coded task cards, progress and notices.

DeepSeek account balance pill in the dsh composer status row.