Plugins

Grouped skill picker for the composer. A button beside the input box opens a panel that browses every installed skill by scene (research, office, data, writing, media, dev), with auto-classification for new skills, Chinese annotations, search and drill-down; picking one inserts the /skill-name gesture.

Adds a My Groups tab to the DSH Installed plugins page: custom groups with drag reordering, colored text tags, Chinese notes, group locking, real enable switches, and two preset snapshot slots.

macOS arm64 only; requires dsh-pet installed (the bundled binary is a closed prebuilt). Desktop switch for the dsh-pet pet: one click to show or hide it, and it can start DeepSeek Harness when that is closed.

Windows only; needs PowerShell and the bundled install.ps1. Adds an interface menu to the left of the model selector with three actions that run immediately: reload the interface, restart DSH, and close DSH. The Windows build ships no built-in reload or restart entry, so this adds one.

Adds a Restart button beside the permission control in the composer toolbar that relaunches DSH in one click, so freshly installed plugins apply without closing and reopening the app.

Adds a Windows Explorer folder context-menu entry that registers the folder as a DSH project, with a switch for the menu entry in Settings → General. Windows only, and nothing extra has to be installed.

Adds a Restart row to the desktop app's sidebar foot beside Settings that restarts the app and reloads the page onto the newly installed plugin bundle.

Renders installed DSH plugin titles and descriptions in Simplified Chinese: at startup it translates the plugins the local JSON cache lacks through the harness LLM service, then projects { en, zh } metadata for resolveText() to render — no DOM changes, no third-party API.

Adds a low-key companion panel with a pomodoro timer, a todo list, drink-water and stand-up reminders, plus lesson explanations and homework tutoring through the installed desktop pet.

Composer enhancements: caches unsent drafts per workspace for new sessions and per Session id for existing ones, restoring them after switching away and dropping them once sent or cleared; adds an @plugin completion group that mentions an installed plugin so the agent receives that plugin's metadata as runtime context for the turn.

See what you actually installed: a chip shows how many plugins your profile really loads, and a searchable panel lists every one with its version, its author-written one-liner, and whether it is built-in or third-party. Read-only, zero config.

Give DeepSeek Harness its own persistent computer: a bundled microVM with shell, browser, live view and approval gates

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

Adds a checkbox-style switch at the right end of the Installed group header on the DSH Plugins page: it opens a checklist of the unofficial plugins, all checked by default, and toggles only the ones you keep checked. Once everything is off the button flips to enabling them again. Disable/enable only — it never uninstalls a plugin or deletes plugin files and configuration, and its UI copy follows the app language.

System-prompt surface drift gate: every section any plugin or preset contributes to the assembled system prompt is hashed and baselined; a silent rewrite of what the model is told fails loud.

Deterministic write gate: scope policy denies out-of-scope write/edit calls before they touch the disk, residue rules scan the written text, and every decision lands in a content-hashed JSONL ledger; can reuse the repo's agent-pr-gate.yaml so CI and session enforce one policy.

GitHub issue service for DSH: turns a telemetry failure analysis into a uniform issue report, builds a pre-filled new-issue URL that is shortened when it would exceed a configured length budget, and rewrites a plain description into a structured issue with the deployment's model.

Prints every plugin in the DeepSeek Harness loader tree at boot, with the exception text for anything that failed, and checks dependency version drift, profile config validity, web port reachability and registered tools.

Staleness keeper for the Codebase Memory knowledge graph: it compares the graph Branch node head_sha with git rev-parse HEAD and reports an exact behindBy, rebuilds only the stale projects through the codebase-memory-mcp CLI so the MCP tool 60-second cap does not apply, watches each project for edits, and mirrors the same state into a settings card and a REST control surface.

Routes eligible bash commands through rtk (Rust Token Killer) so tool output is compressed before it reaches the model, by asking the installed rtk to rewrite each command and adopting what it prints; when rtk is absent the executor behaves exactly like the stock one.

Jenkins CI integration with a live build-progress panel in the right sidebar, a multi-instance settings page, five model-facing tools (list jobs, build status, console log, workspace, trigger build), and a failure wake that hands a failed followed build to the conversation that followed it.

Send local files to WeChat from any DSH session by reusing an installed IM plugin, plus cron-scheduled tasks that run in fresh sessions, a workspace activity glow, a header activity indicator, a completion chime, a macOS sidebar vibrancy toggle and a one-click host restart.

Host-side long-task detection for small-context local models: long outputs are scaffolded into a parts skeleton (one part per reply, then assemble), and multi-step work into a PLAN.md ledger with notes/ (plan first, one step per reply). Detection is heuristic and host-side, so it does not depend on the model judging its own limits.

Verified-progress ledger: three tools record a claimed step as progress only after an independent subagent with a fresh context confirms it against the workspace. The declared scope is fingerprinted before and after each verification, so a verifier that changed anything has its verdict voided and the round cannot become progress.