プラグイン

セッション管理用DSH Webプラグイン：アーカイブ／アーカイブ解除、確実な物理削除（transcriptファイルと~/storages/*.jsonの一括処理）、ドラッグ＆ドロップによるworkspaceの再割り当て、ブランチベースのメッセージ編集（edit/retry/rerollと元に戻せるバージョン履歴）。

DSH 向けの経験検証レイヤー：ツール失敗／リトライ／検索のシグナルをゼロトークンで収集し、AI が検証済みスキルブック（三層検証）へと洗練、タスク開始時に参照します。10 個の体験版スキルとベンチマークデータ（複雑タスク成功率 100% 対 素の 60%）を同梱。

テキスト専用モデル向けの透過的なマルチモーダルルーティング：すべてのモデル呼び出しにおけるすべての画像が、自身のマルチモーダル理解器によって完全に文字起こしされます（逐語 OCR、データ、不確実領域、インジェクション対策済み）。vision_relook による集中的な再確認と、画像関連の失敗時の自動リトライを備えます。バンドルされたエンドポイントなし、借用ログインなし。

失敗した API リクエストを自動再試行し、DSH の会話を継続させます。ステータスコードとエラーコードをカスタマイズ可能です。 失敗した API リクエストを自動再試行し、DSH の会話を中断させません。カスタムのステータスコードとエラーコードをサポートします。

DSH 用文字化けガードバンドル：書き込み前の特徴ベースの文字化け検出と審査後リリース（同一内容の再試行は通過）、実行前の pwsh エンコーディング監査（ANSI/GBK/UTF-16/Default）。Windows と中国語を優先。

Keeps a turn from closing on an unfinished reply: a stream guard turns silent truncation into an in-step retry, and a completion protocol asks the model to declare how each turn ended.

Read-only /btw side questions for DeepSeek Harness: forks the current session, injects the running turn's task, recent tool calls and partial answer so a mid-turn question has context, denies every tool call at execution time, and keeps a per-session topic history with follow-up, stop, retry and delete.

Sends desktop notifications when a DSH turn finishes or fails, and sends 继续 automatically after the model-retry budget is exhausted.

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.

read、read_image、visionツールが開く前にファイルを整えます。2048 px超または8 MB超の画像を縮小し（同じターン内に1280 pxで1回再試行）、BMP/TIFFをPNGに変換し、バイト列から誤った拡張子のアップロードを判定して修正します。docx/xlsx/pptx、テキスト層付きPDF、csv/tsv、htmlを外部プログラムなしでMarkdownに変換します。

context上限に達してbuilt-in compactionが放棄された後、自動でもう一度圧縮してから再試行します。それでも失敗した場合は元sessionをhandoff packageにまとめ、新sessionで続行。engine変更なし、UI追加なし。session revivalは既定で明示的な操作が必要で、元sessionはread-only。

プロセス内クラッシュガード。DSHを終了させる致命的error handlerを引き継ぎ、stackから原因pluginを特定し、home patch layer内の該当行だけを無効化します。profileや、その内側のprovider設定は変更しません。crash画面からretry／keep-disabled／uninstallを選択でき、原因を特定できない場合は一時的なsafe-mode sessionを開きます（CLIとWeb起動のみ）。

DSHエージェントのフォアグラウンド待機を拒否します。sleep、wait、tail -f、watch、-cなしのping、無限ループなどの待機コマンド、wait_agentやwait: trueのjob_outputなどのブロッキング待機ツール、同じ確認コマンドの短時間内の反復、sudo -nなし、BatchModeなしのssh、ログイン処理、対話型エディター、docker -itなど人の入力・確認を要するコマンドを拒否し、バックグラウンド実行またはターン終了を案内します。予算とポーリング時間枠を設定でき、メッセージ言語はsystem（zh/en）に従います。実行時依存ゼロ。

失敗したモデル要求を自動再試行。すべての要求エラーを捕捉し、2秒/5秒/10秒/20秒のバックオフ後に同じステップを再送して、ゲートウェイの瞬断やレート制限でターンが終了するのを防ぎます。

composerドックにGLM Coding Planの利用枠リングを表示。5時間/週のクレジット枠、レベル、自動更新、ワンクリック再試行に対応。GLM Coding Planの契約とキー、BigModel組織ID/プロジェクトIDが必要（チーム利用枠APIはIDなしだと空）。

Windows版DSHデスクトップアプリのシステムトレイメニューとアカウントメニューに、ネイティブの「Restart DeepSeek Harness」を追加します。起動時にプラグインがパッチ済みのresources/app.asarを準備し、分離ヘルパーが正常終了後に元ファイルをバックアップして差し替えます。デスクトップ更新後はパッチを再適用します。どちらのメニュー項目も次回起動時にアプリを正常に再起動します。Windowsデスクトップ専用で、他のホストは409 not_desktopを返します。

composer横のボタンで現在の下書きを実行しやすいpromptへその場で書換え。軽い整文から大幅展開まで4つのpresetと独自presetに対応。composerを離れずボタンからpreset、prompt model、推論強度を切替。下書きに内容がある時だけ表示し、強化中はtimer、失敗時はretryを表示。

DSH内で実際のChatGPT/Codex契約枠を確認。`/wham/usage`から5時間/週次枠、リセットまでの時間、追加利用残高、追加制限グループ、コードレビュー枠を取得。サーバー発行リセットクレジットを安定した再試行安全なidempotency keyで一覧/利用し、複数アカウントを切替。`/codex/models`から実カタログを取得し、利用不可なら組み込み一覧で補わず空表示。Settingsからブラウザー認証またはdevice codeでワンクリックサインイン（callback貼付も可）；認証情報はDSH credential service内に保持。DSH内蔵の`llm-pi-ai` Codex routeを再利用してmodelを呼び出し、provider routeは登録も占有もしません。他プラグインが所有する場合はquota consoleのみになります。残枠チップをcomposer横に表示。

DeepSeek Harness向けWindowsサンドボックスACL修復プラグイン。SetNamedSecurityInfoW Win32 5のgrantWrite失敗を修正し、コマンドを見せずに再試行します。

WeChatのチャット記録をDSHセッションへ転送。Windows共有先が結合転送ZIPを受け取り、GUIオーバーレイでワークスペースとセッションを選択。ZIPはファイル添付のユーザーメッセージとして届き、エージェントが展開・読取します。WeChatのPNG/HEIC実データなのに.jpgのような拡張子はマジックバイトで正規化。失敗時は再試行用にバッチを保持。Windows 10/11、Developer Mode有効、共有先登録用repo installerが必要。

DSH用union IM bridge、15 channel adapter/12 platform。version 0.1.2-rc.1〜0.2.1-rc.2のhost設定を能力probeで適応（12 tag enum、version分岐なし）。Feishu voice tierだけsystem ffmpeg必要。25 command panel。tool approval/questionは元chatで応答、deny-by-default・initiator-only・5分期限。image/file inputはhost model metadataでgate。file返却、bounded retry（送信不確実なら再送しない）。自前Tasks/Channels tabは他pluginがslot所有時に停止。im-concise presetとtext-only時のGenUI fence/raw HTML除去、svg→PNG。model allowlist。/relayで最終回答をnotify channelへaccount ID/alias指定で転送し、曖昧なら推測しない。secretは一方向でvaultへ、応答に出し直さない。 npm: dsh-im-union.

ompと同じ規約でDeepSeek HarnessをHindsightメモリサービスへ接続。共有バンク、プロジェクトタグの自動付与、プロジェクト＋全体想起、メンタルモデル、重複検出、失敗したバックグラウンド処理の再試行ツールを備える。Hindsightサーバーの起動が必要（既定http://127.0.0.1:8888）。

連続して発生する同一内容のツール失敗を監視し、任意で次のモデルステップ前に一時停止します。元の結果と成功した繰り返し呼び出しは保持し、DSH Webのチャット内にレポートを表示します。

壊れたDSHターンを復旧します。製品の再試行回数を増やし、待機を同じステップ内のライブカウントダウンとして表示。途中で切れた出力も同一ターン内に保持し、ターン終了後は任意で継続ラウンドを開始できます。コンポーザーが空なら送信ボタンをその継続に割り当てます。