플러그인

Adds an ARIS agent preset that loads the 84 ARIS research-workflow skills and runs their reviewer as an in-harness subagent from a different model family than the session model. Other presets are unchanged. A fork of wanshuiyin/Auto-claude-code-research-in-sleep's dsh-aris branch: install it instead of the upstream dsh-aris plugin, not alongside it - both register the mcp__codex__codex reviewer tools and the same ARIS skills.

Two-way sync between a local LaTeX folder and an Overleaf project over the Overleaf Socket.IO + OT channel instead of a Git bridge: pull with automatic git init, dry-run-first push, three-way diff, background watch, and conflict copies that never overwrite.

Operate the Edge or Chrome window that is already open, without restarting it and without closing it: choose a window once, reuse a tab that already shows the URL, read page text or DOM state, click by accessible name or visible text, type, scroll, wait for content and batch steps. 22 tools over UI Automation, SendInput and an optional Tampermonkey bridge. Windows only.

Bilibili companion for DSH (MIT fork of Alterssss/dsh-bili-whale; do not install alongside the upstream — both register the same `/dsh-bili/` settings routes and share `~/.dsh/bili-whale.config.json`): wakes on a schedule, reads videos through subtitles, danmaku, hot comments and covers, writes two diaries, and shares at most one pick per wake by commenting on the video and @-mentioning the owner (daily quota 3; DM when `share.via=dm`). Inbound DMs, commenter names, summary requests and live danmaku are normalized and scanned for injected instructions before they reach the model; only the owner DM channel can carry an authorization prefix.

Lingshu (灵枢) is a brain-inspired persistent memory, persona and growth system for AI coding agents: pure Python standard library, zero dependencies, local-first, requires Python 3.9+. Hippocampus/cortex layered memory with forgetting curves, dream consolidation, fuzzy associative recall, emotion system, persona drift protection, knowledge base, self-authored skills, and a local web panel. Ships as a DSH bundled skill; the separately installable cordis startup-injector plugin auto-injects sessions only when Lingshu is installed at ~/.dsh/skills/lingshu (or brainPy is configured) and Python 3 is available; the optional update check contacts GitHub/Gitee.

Material library for dsh: collect a folder, file or note from a conversation, keep it in real folders with tags, browse it Finder-style, reopen the source chat's output in one click. Ships a materials_archive tool plus auto-filing rules: file a task's deliverable once, and every later scheduled run files the new documents by itself.

One dedicated folder per conversation: archives the transcript, auto-categorizes research output by type once the conversation has been idle for 10 minutes, adds a delete action to the session menu, and permanently removes the folder with the conversation.

Actually delete DSH sessions instead of archiving them (Windows only). Clears all six on-disk locations (transcript, title cache, billion-context SQLite index with VACUUM, workspace registry, cost-meter ledger, bridge logs) with a dry run, a backup, byte-for-byte rollback, and an automatic quit-delete-relaunch flow.

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.

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.

Antigravity provider for DeepSeek Harness: resolves the OAuth client from the locally installed official desktop app and supports multiple accounts with quota-based automatic switching.

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.

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.

Local text-to-image automation for DeepSeek Harness: captures the conversation, sends it to a prompt session, renders with your own ComfyUI, and brings the images back to a sidebar tab, a floating frame and a gallery.

Mouse gestures for files in the DSH Web GUI: Ctrl+click a file-tree row, a file mention in a chat message or a file link to open it with the desktop default application; right-click opens a menu with open, the operating system own Open With chooser, save a copy, copy the absolute path, copy the file contents and reveal in the file manager, while a right-click on an ordinary hyperlink offers Copy Link. A plain click is left to DSH own sidebar preview and directory rows are left to the page. Open and reveal go through DSH own sessionController, the Open With chooser is the operating system dialog (Windows Shell verb, open -a on macOS) rather than an application list kept by the plugin, and file reads stop at 8 MiB.

DSH를 다시 시작해도 Auto 권한 프리셋을 유지합니다. 종료 시 auto-review 언로드 마이그레이션이 실행 중인 Auto Session을 Full 접근 권한으로 바꾸지 않으며, integration이 없어도 저장된 Auto Session을 열 수 있습니다.

DeepSeek Harness에 내장된 폐루프 개발 작업대입니다. 한 패널에서 에이전트가 STM32 보드를 빌드하고 플래시하며 디버그 검증과 모니터링을 수행합니다. 사용자는 진행 단계, 스트리밍 로그, RAM/FLASH 사용량, 디코딩된 시리얼 파형을 실시간으로 봅니다. PATH에 호스트 Python 3.10+가 필요하며 플러그인은 설치할 수 없습니다. ARM 툴체인은 첫 사용 때 자동 다운로드됩니다(약 400 MB, Windows x64 전용). STM32 보드와 디버그 프로브도 필요합니다.

read, read_image 및 vision 도구가 파일을 열기 전에 준비합니다. 2048px 또는 8MB를 넘는 이미지는 축소하고(같은 턴에서 1280px로 한 번 재시도), BMP/TIFF를 PNG로 변환하며 바이트를 판별해 잘못 표시된 업로드 형식을 고칩니다. docx/xlsx/pptx, 텍스트 레이어 PDF, csv/tsv, html을 외부 프로그램 없이 Markdown으로 변환합니다.

소유자에 관한 장기 기억입니다. 각 턴에서 일정, 선호, 비선호, 감정적 자극, 현재 집중사, 약속, 말투 선호를 추출하고 짧은 요약을 모든 프롬프트에 넣습니다. 정해진 시간에 말을 걸거나 답변에 다정한 한마디를 더하고, 짧은 메시지에서 기상/업무/수면 시간을 학습하며 기억을 자동으로 압축합니다. 플러그인 출처와 외부 도구 인식, 미검증 기억의 가중치 낮추기, 한 번 눌러 철회하기도 지원합니다.

Lingshu 시작 인젝터입니다. 새 에이전트 세션마다 brain.py startup을 실행하고 페르소나/기억/TODO를 자동으로 넣습니다. Python 3과 ~/.dsh/skills/lingshu에 설치된 Lingshu 기술이 필요하며 둘 중 하나라도 없으면 아무 작업도 하지 않습니다. 기본 저장소에는 번들 SKILL.md 진입점도 있습니다.

중국 A주, 홍콩·미국 주식, 외환, 중국 및 세계 원자재 선물과 지수의 시세판입니다. 관심 목록, 사용자 그룹, 자동 새로고침, 호스트 측 저장을 지원합니다.

Windows Explorer 컨텍스트 메뉴에서 실행 중인 DSH Web 작업공간에 폴더를 추가하고 필요하면 dsh web을 자동 시작합니다. 메뉴를 설치하려면 저장소 클론에서 사용자별 PowerShell 설치 프로그램을 한 번 실행해야 합니다(관리자 권한 불필요).