Plugins

Windows x64 preview that detaches workspace/session navigation into a separate .NET Framework 4.6.2+/WebView2 Evergreen window, with grouped trees, overview/focused modes, logical drag-and-drop, activity/manual ordering and a resizable focused-view preview; no DSH Core patch and no Better Workspace runtime dependency. Derived from KannaKuron/dsh-better-workspace — do not install both.

OpenCode Go subscription usage in the DeepSeek Harness composer: 5-hour, weekly and monthly windows with a click-open details panel. Zero configuration.

Implicit session plans with Tab-completable next-message suggestions for DeepSeek Harness

Reference links panel for DeepSeek Harness: collects every URL of a conversation into the right sidebar with pins, turn counts, metadata and favicon caching. DSH 右栏「参考链接」面板。

Approval frame for DSH tool calls: a rule table with four outcomes (deny, ask, AI review, allow) across tool, command, file and network scope, then AI fast/deep review and human approval, a hash-chained audit trail and a settings UI. Target files are inspected by metadata only (no file contents are opened); the reviewer sees the command, targets and clipped write payloads, with secrets redacted before anything leaves the machine.

Manage Oracle, PostgreSQL, MySQL, MariaDB, SQL Server and SQLite connections with driver diagnostics, column defaults/comments, and opt-in metadata browsing for agents; requires a separate Python 3 environment with the per-driver packages (SQLite needs only the standard library).

Drive existing DSH sessions from QQ (needs an OneBot 11 implementation such as NapCat running alongside): ask another session a question, manage share/team slots with a guard, pause a running turn, restart DSH on Windows and resume (via the install-restart.ps1 scheduled task), and inject peak-hour discipline. Plugin detail page has per-feature switches.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Adds a "Delete session" item under "Archive session" in the sidebar session menu: it detaches the session from memory, deletes its on-disk record and projection cache, and removes the row from the sidebar immediately. Permanent - there is no trash bin.

Injects a configurable whale-girl persona into every DeepSeek Harness system prompt.

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.

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.

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.

MetaOnticVideo｜Plugin de creación de vídeo con IA para DeepSeek Harness. Usa Seedance 2.0 / Mini / Fast para continuar la generación por segmentos y crear vídeos de más de 15 segundos. Admite texto a vídeo, imagen a vídeo, revisión de guion y storyboard, vista previa por segmento, reanudación desde el punto interrumpido y unión con FFmpeg. Plugin de generación y continuación de vídeo con IA.

Panel de uso para planes de proveedores: muestra cuánto queda en cada ventana de cuota (GLM Coding Plan y OpenCode Zen) como chip compacto junto al selector de modelo, con un popover de detalle.

Entrada de voz push-to-talk totalmente local para macOS: mantén una tecla global, habla y suéltala; la transcripción se pega donde está el cursor. STT local-first (Qwen3-ASR 0.6B 4bit en MLX/Metal por defecto; alternativas SenseVoice y mlx-whisper), cero APIs externas, servicio launchd autorreparable y diagnóstico de 8 puntos. La Skill incluida permite al agente instalar, configurar (conexión de tecla Karabiner, launchd, cambio de motor) y resolver problemas de toda la cadena.

Muestra herramientas compactas arriba, una bandeja para sesiones sin título y estantes Working/Settled abajo. Incluye menús nativos, resaltado de búsqueda, navegación por teclado, copias de seguridad de metadatos y un cambio para volver al diseño original. Verificado en macOS; interfaz en chino.

Añade un control de esfuerzo de razonamiento al menú de modelos de DeepSeek Harness, también para proveedores y modelos sin metadatos de esfuerzo declarados. Basado en Microqian2th/dsh-codex-effort-slider: desinstala ese plugin upstream antes de instalar este.

Memoria local por capas para DeepSeek Harness: un índice Markdown se inyecta automáticamente en el system prompt, una capa de rutas se lee bajo demanda y los detalles están en archivos de evidencia. Solo archivos, sin dependencias de runtime.

Memoria de largo plazo entre workspaces: almacén local compartido, índice compacto inyectado al inicio de sesión y herramienta de búsqueda de detalles.

Búsqueda web Tavily para DeepSeek Harness: proveedor de búsqueda `ctx.web` y herramientas `tavily_search`, `extract`, `crawl`, `map` y `research`; la configuración está en la página de detalles del plugin.