Plugins

Long-term memory kept as blocks: one event per block, written to a local append-only event log with a block view and derived indexes, so a full history stays recoverable while only the matching blocks reach the context. The model saves entries with memory_remember and pulls the relevant few with memory_recall, plus one automatic recall pass before each step. Data stays in ~/.beme; no external service and no API key.

Local long-term memory for DeepSeek Harness with SQLite storage, automatic extraction, semantic recall, corrections, reliable forgetting, and an in-app summary dialog.

Context rollover: auto-saves a handoff before the context window fills and re-injects it once in the next session segment. Two tools and a settings panel.

Adjusts the context-window percentage at which DSH triggers its native automatic compaction: a slider on the plugin page in the plugins manager sets it from 1% to 100% (default 80%, arrow keys adjust by 1%), and the retained-history budget shrinks with lower thresholds so early compaction is not defeated; the compaction run itself stays with the native engine.

Automatic session titles for DSH: names a session from its first prompt plus the first assistant reply ("project｜task") instead of truncating the prompt. Replaces the built-in session-title provider through a bundle patch, adds an "AI rename" entry to the session row menu with a preview dialog, and a settings page for the provider/model, the naming rules and a diagnostic event log. 49 unit tests.

Adds delete and multi-select batch delete to the sidebar session menu, removing session chat logs with an automatic backup and one-click undo while leaving workspace files untouched.

Adds an Auto-rename row to each Session sidebar menu: the model reads the Session log, weights recent user messages higher (exponential decay, 3-day time constant), and writes a title of at most 10 CJK characters into the Session title. Also opens that Session menu on right-click, and exposes the same operation as the session_auto_rename agent tool. Requires DSH 0.2.1-rc.5 or newer.

Adds per-model hide/show switches for custom (llm-pi-ai) providers to the DSH settings page. Hidden models disappear from the conversation model picker and are archived verbatim, so they can be restored at any time; disabling or uninstalling the plugin restores everything automatically. Built-in DeepSeek providers are not managed.

Retry failed model requests automatically: intercepts every request error and replays the same step after a 2s / 5s / 10s / 20s backoff ladder, so gateway blips and rate limits no longer end the turn.

Bing daily wallpaper as the app background: auto-refresh every day, pin any of the last 30 days.

GLM Coding Plan usage quota ring in the composer dock - 5-hour and weekly credit windows with level, auto-refresh and one-click retry. Requires a GLM Coding Plan subscription and key, plus your BigModel organization and project IDs (the team quota API returns empty without them).

Zero-friction quick ask for DSH: select text in chat, Markdown/code, rendered HTML reports, or the better-sidebar editor. The default answer starts automatically (English prose is translated, a term is explained, a question is answered); typing cancels it. Answers stream from a one-shot completion on the main window's model, inherit a read-only conversation snapshot, read the selected file as context (up to 20,000 characters by default), and never write to the main session. One-line install; host routes, client slots, document renderers and the iframe selection bridge are separable extension points.

Claude-styled terminal panel for the DSH web GUI: agent shell commands run in a persistent real PTY with a genuine prompt, echo and exit codes, auto-open in the right sidebar and are scoped per conversation; optional live_terminal_* tools for reading, searching and screenshotting. Fork of Lancang-hzau/dsh-live-terminal (MIT); it shares its live_terminal_* tools and right-sidebar panel, so do not install it together with the upstream plugin in the same profile.

One-click polish, expand and autopilot for the DeepSeek Harness composer: rewrite the draft with the model the session is switched to, expand a one-line wish into a task brief, or let an AI drive a goal round after round.

深鲸工序 · 设计插件线：PS / AutoCAD / 3ds Max / Blender 四条完整工序流水线（意图→工序→落盘审阅→执行→校验→回执），也是框架 —— 写一个适配器就能接入新软件

Deterministic auto-dispatch for native DeepSeek Harness Agent Teams: wakes idle members when a task becomes ready, and turns advisory write scopes into an effective soft lock.

A per-command sandbox allow-list for the bash tool: a rule names a CLI and the writable roots it gets, so allow-listed programs such as lark-cli and gh run inside the kernel sandbox with the workspace plus those roots appended. Unlike plugins that answer the approval for you or that widen the writable set for every command, the grant here is scoped to the matched command, the workspace stays writable, and other commands keep their exact behaviour. Matching is by write footprint rather than by command string, so write-neutral pipes like `2>&1 | tail -N` still match; rules are edited from a Settings page or the Plugins row. Overlays cover Seatbelt, bubblewrap and Landlock; on Windows the writable root is swapped for $HOME instead.

One-click WorkBuddy daily check-in button pinned to the composer tool row. Clicking it calls the check-in route provided by dsh-connect-workbuddy for the currently selected account, and shows the result next to the button: already checked in, credits claimed, or streak days. The done state persists across sessions via a local date stamp and reconciles with the upstream status on load, flipping back automatically after midnight.

Agent tools that download a Bilibili video, transcribe it with a local whisper.cpp build, then write a structured Markdown note with DSH's own LLM (optionally printing it to PDF). Windows only: missing dependencies are auto-downloaded into the data directory — yt-dlp.exe and the ffmpeg.exe build from GitHub and gyan.dev, the whisper.cpp x64 binary from GitHub, and a ~547 MB model from the hf-mirror mirror; PDF export shells out to a locally installed Edge/Chrome. Two tools: video_to_notes and note_to_pdf. Pure JS, no extra API key.

Long-term memory backed by a local SQLite store: project-scoped memory auto-injection with junk filtering, rule-based or model-assisted memory extraction from recent turns, write-side dedup and feedback-weighted ranking. The Python bridge runs on $NEXUS_PYTHON or the DSH-bundled interpreter at <DSH home>/dsh-runtimes/dsh-primary-runtime/dependencies/python/ (Python 3.8+).

Moves DSH sessions between workspaces with validation of live/subagent/offline states and automatic backups of every move under ~/.dsh/session-move-backups/.

Connects OpenCode Go subscriptions to DSH Desktop, with API-key management, usage snapshots, automatic model synchronization, and model selection.

Connects a local Codex ChatGPT login to DSH Desktop, with account controls, quota snapshots, automatic model synchronization, and model selection.

Shows per-answer and conversation cost estimates from recorded token usage, with automatic model pricing updates and detailed price-source breakdowns.