플러그인

Offline civil-service exam study panel integrating 15 upstream open-source question banks with SRS wrong-book, mock exams, essay grading, interactive knowledge graph and whitebox observability. The npm package ships no question-bank data: after install, the required set (~363 MB) is cloned from the question-bank manager (all 15 upstream repos are about 2.2 GB).

For the DSH Go phone app (https://go.dshtui.com): watches the quiz screen and pushes each answer as a heads-up notification, using an optional local answer bank.

Codex-inspired lifecycle command hooks for DSH, with explicit tool-input sharing, pre-tool deny policies, notifications, and local audit examples.

DeepSeek account-backed web search and page fetching for DeepSeek Harness sessions whose chat model runs through a third-party subscription or gateway (for example OpenCode Go): registers deepseek-account-search and deepseek-account-fetch providers that call the official Search and Fetch APIs with the signed-in DeepSeek account token, so the built-in web_search and web_fetch keep working without a DEEPSEEK_API_KEY.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

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.

Looks up English words in chat replies by click or selection, showing part of speech, Chinese meaning and exam tags; selecting a pure-English sentence translates it. Ships an offline dictionary: 20,499 entries, 8,960 with bilingual examples, 6,374 with root analysis.

복사해서 시작할 수 있는 스타터 플러그인입니다. 오른쪽 사이드바 탭 하나, 2개 언어, 실제 번들을 마운트하는 동작 테스트, manifest 사전 검사를 실행하는 CI를 제공합니다.

DSH 대화에서 Obsidian 볼트 파일을 일반 클릭하면 노트는 Obsidian 앱에서, .tex 등 설정된 형식은 프로젝트 폴더를 workspace로 삼아 VS Code에서 엽니다. Cmd/Ctrl-클릭은 앱 내 미리보기를 유지합니다. open_vault_file 도구도 같은 방식으로 연결하며 모든 열기 작업은 설정된 vaultRoot 안으로 제한됩니다.

절대 INDEX 경로와 version이 포함된 짧은 규약 안내를 session과 version 조합마다 한 번 주입합니다. 규약 version이 바뀌면 다음 turn(chat turn 포함)에 다시 주입합니다. 선택적 hard guard는 operation형 turn에서 session이 index를 읽을 때까지 write/edit 도구를 거부합니다(chat turn과 shell은 기본 차단 대상이 아님). 예제 checklist 또는 사용자가 지정한 디렉터리를 쓰며 의존성 없이 경로를 설정할 수 있습니다. 작업 시작 시 규약이 불러와지지 않는 문제를 해결합니다.

투자 리서치 bundle입니다. 검색, 페이지 가져오기, 출처 감사, 주장 검증, 수치 엄밀성, 채널 상태, workflow loader, chart engine, PDF renderer, PDF gate 등 도구 10개와 ai-berkshire에서 조정한 skill 23개를 제공합니다. 6단계 workflow에서 병렬 agent 4명(단융핑, 버핏, 멍거, 리루)이 기업을 조사하고 서로 검증한 뒤 표지·표·캡션·페이지 번호가 있는 차트 중심 PDF를 만듭니다. Python 3.10+ 필요. chart/PDF 도구에는 python-docx와 matplotlib도 필요합니다.

skill에 tag를 지정해 필터링합니다. boolean tag expression이 선택한 하위 집합만 workspace나 대화에 전달합니다(예: `pdf + docx`, `aegis * plugin`). 제외된 skill은 설정 UI에서 숨기는 데 그치지 않고 model catalog에서 deny-shadow 처리됩니다. expression 밖의 skill은 수동으로 추가하거나 강제 비활성화할 수 있습니다. 내장 `tagging-skills`는 실행 중인 머신을 바탕으로 agent가 tag 집합을 도출하도록 안내합니다.

DeepSeek Harness에 `principles_audit` 도구를 등록해 원칙 라이브러리의 principle_id 충돌·이전 ID, 인과 설명·경계·반례·근거 누락, 중복·유사 원칙, status와 confidence 불일치, 오래된 항목, 차원별 범위 누락을 검토합니다. 발견 사항은 심각도순이며 hard gate가 pass/warn/fail로 판정합니다. 모든 critical 항목은 유효하고 만료되지 않은 예외로 처리되어야 합니다. 라이브러리는 읽기 전용입니다.

중국 대학원 입학시험 Mathematics I용 SymPy 정확 계산 및 독립 검증이다. 도구 14개가 연산자 214개를 다루고 기본적으로 정확한 기호 결과를 내며 매 결과를 별도 방식으로 재검증한다. Python 3.10+, sympy, mpmath 필요.

노드 기반 GLSL 워크벤치입니다. 캔버스에서 셰이더 그래프를 연결해 실시간 미리 보고, 멀티패스 버퍼(BufferA–D)가 있는 Shadertoy 호환 GLSL로 컴파일하며 편집 시 핫 리로드합니다. HLSL / MSL / SPIR-V로도 교차 컴파일하고 프로젝트, 머티리얼, 스냅샷, 이미지·오디오·가사 리소스를 로컬 워크스페이스에서 관리합니다. 내장 노드 57개, 예제 8개, 에이전트 도구 11개를 제공하며 런타임 의존성이 없습니다.

DSH Agent 실행 중 대기열에 들어간 사용자 메시지를 공식 큐 도크 안에서 재정렬합니다. 드래그 핸들과 각 행의 ↑/↓ 버튼으로 옮기며 호스트에서 동시성 검사를 거친 inbox splice로 적용합니다. 도크를 교체하지 않고 장식하므로 미리보기, 인라인 편집, steering, 제거, 첨부 기능은 그대로 유지됩니다. 마지막으로 본 뒤 큐가 바뀌었거나, 행이 사용자 프롬프트가 아니거나(예: Goal 라운드 프롬프트), subagent 세션의 큐라면 이동을 거부합니다.

DeepSeek Harness용 격리된 멀티 에이전트 토론입니다. 성향이 다른 토론자들이 서로 영향을 받지 않고 조사한 뒤 반대 심문하고 심사자가 결론을 모읍니다. 백그라운드 작업으로 실행되며 에이전트별 진행률·토큰 집계, 웨이브 병렬 실행, 세션 참조 재개를 지원합니다.

composer 버튼으로 현재 세션에서 사용할 수 있는 모든 스킬의 중국어 제목, 용도, 사용 예시를 보여주는 패널을 엽니다. 새로 설치한 스킬도 한 번에 목록에 추가하고 로컬에 저장합니다.