플러그인

공식 `web_fetch`가 WSL에서 DNS에 고정된 공인 IP로 직접 연결하는 대신 `HTTP(S)_PROXY`를 통해 undici `ProxyAgent`를 사용하도록 `wsl-proxy ctx.web` fetch provider를 등록합니다(Windows 프록시 뒤에서 공식 경로가 `TypeError: fetch failed`를 일으키는 문제).

세션용 무한 캔버스입니다. 영역을 workspace와 agent 프리셋에 연결하고 고정된 세션 카드, 스티키 노트, 정렬 가이드를 배치합니다.

DeepSeek Harness에서 GPT 모델용 Codex 스타일 코딩 도구와 agent 프리셋을 제공합니다: exec_command, write_stdin, apply_patch, view_image. OpenAI Chat Completions 및 Responses API 경로를 추가하고 DSH 네이티브 plan, ask, approval, compaction에 연결합니다. 장시간 명령은 DSH 백그라운드 job이 되며 제한된 head/tail 출력을 job_output으로 읽습니다. 하위 에이전트 유형마다 preset, provider, model, reasoning effort를 고정할 수 있습니다.

DeepSeek Harness 컨텍스트 정리: 내용 인식 도구 출력 축약, 오래된 로그 정리, 사용자 요구사항과 진행 중 작업 고정, 감사 기록을 남기는 “아카이브 후 압축”.

DSH Web 사이드바 상단에 전용 고정 패널과 보관 섹션을 추가하고 세션을 pin/unpin합니다. 기본 제공 점 3개 메뉴와 통합됩니다.

사이드바 목록 위에 Workspaces/Recent-sessions 전환기를 추가합니다. 고정 세션 그룹, 행별 메뉴(pin/unpin, session id 복사), 제목 필터, 브라우저 로컬 핀 저장을 지원합니다. dsh-plugin-pin-session에서 한 번 마이그레이션합니다.

DSH용 Clean Architecture 참고 라이브러리입니다. Go, Java, C#, Python의 고정 참고 저장소 8개를 로컬 FTS5 데이터베이스에 색인합니다. assertion 규칙, 검토 원장, 읽기 전용 관찰 패널을 제공합니다.

DeepSeek Harness Web GUI용 다중 세션 분할 보기입니다. 상단 window에서 root slot을 크기 조절 가능한 분할 컨테이너로 바꾸고 각 pane은 전용 session에 고정된 전체 DSH client를 iframe으로 실행합니다. pane별 제목 표시줄과 LRU 절전 기능이 있습니다.

DSH Web UI용 서드파티 메뉴 관리자입니다. 다른 플러그인이 추가한 메뉴 항목을 한곳에 모아 접기와 고정을 지원합니다.

DeepSeek Harness 사이드바를 독립적으로 스크롤되는 고정됨과 최근 패널로 나누고, 고정된 세션을 최근에서 숨깁니다.

작업 인식 DSH 플러그인 내비게이터: GitHub 토픽과 커뮤니티 목록에서 로컬 색인을 구축하고, 28개 이중 언어 기능 클래스를 검색하며, 커밋 수준의 정적 위험 감사, 동의 게이트 고정 설치, 구성 검사 및 복구를 제공합니다.

DSH 플러그인: 원격(비루프백) /api 접근을 위한 비밀번호 게이트(기본적으로 비밀번호 없음), 루프백에 고정된 특권 엔드포인트의 차단 해제, 제거 시 모든 항목 복원, 로컬 127.0.0.1 사용자에게 워크스페이스 선택을 위한 네이티브 OS 폴더 선택기 제공. selec

Adds a cross-workspace activity sidebar for running, waiting and unread sessions, with search, optional pinned and scheduled-delivery groups, local read tracking and confirmed archiving.

A sticky-notes wall pinned to the sidebar: one click opens a full-page wall, notes save as you type, and writing #tags in the text turns them into one-click filter chips. Six paper colors, pinning, search, JSON export and import.

Domain-routed proxy for DSH fetch traffic: hosts on a force-proxy list always go through the proxy, every other host tries direct first and fails over to the proxy within a second, the first channel to answer is pinned for the session, connections are reused for 120 seconds, and each attempt is logged. Can also route pnpm/git subprocesses used by plugin installs.

Archives sessions that have gone unused for longer than a set number of days (5 by default), skipping archived, pinned, and protected ones — a session context-menu item marks a single session as protected, a small shield shows it on the row, and a General settings field changes the threshold.

A right-sidebar tab listing the files DSH Sessions produced, newest first, with the Session in view expanded on top: a click copies a row's full path, a double click previews it in the sidebar, and a file can be pinned in one Session or in all of them.

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.

Adds a Speed setting (Standard, Fast, Ultrafast) for OpenAI and Codex models on a patched dsh build: the pinned dsh 0.2.1-alpha.2 web client needs the Model / Effort child-slot patch, the host pi-ai must be 0.87.1 or 1.1.0 (other versions refuse to load), and the terminal controls need a patched dsh-TUI. Then it appears in the Model / Effort menu; in dst /speed opens a picker or sets the speed directly, and the current speed shows in the bottom bar. The choice is kept per session, provider and model and is sent as the request service tier.

Replaces the DSH sidebar list with a workspace rail: pinned chats and folders, projects that are folders with their own AGENTS.md and files, a virtualized Recents list ordered by the last finished turn, a project_search tool, unread markers, a collapsed icon column with an unread count and a live browser tab title.

팀 공유 지식 베이스입니다. 한 구성원이 종속성 없는 Hub를 실행하고 나머지는 플러그인을 설치해 초대 코드로 참여합니다. 업로드 자료는 요약, 신뢰도, 포인트와 함께 10개 범주로 분류되며, 에이전트 도구 15개로 업로드·검색·회상·댓글·읽기를 할 수 있습니다. 중요한 항목은 직접 작성한 추천과 함께 고정되어 구성원이 읽을 때까지 유지됩니다. 계정마다 비공개 로컬 라이브러리, 컬렉션, 주간 요약, 버전 차이도 제공됩니다.

망각 곡선을 사용하는 에이전트 메모리입니다. 언급되면 가중치가 올라가고 잊히면 낮아집니다. 고정한 항목은 감쇠하지 않습니다. 도구 6개와 설정 패널을 제공합니다.

DeepSeek Harness의 세션 간 장기 메모리입니다. 고정 규칙은 매 턴 주입하고 나머지는 IDF 가중 keyword 근거로 회상합니다. fact-key 중복 제거, 일반 JSON 저장, 설정 페이지 편집/삭제를 지원합니다.

DSH Workspace 브라우저에 Claude Code 및 Codex 세션을 표시하고 열기/계속하기/고정/이름 변경/보관을 지원합니다. terminal, file, git 탭도 제공합니다.