Plugins

Registers system-prompt sections that make the model reason in Simplified or Traditional Chinese, with strict/prefer modes and an optional reply-language policy. Adds a /thinking-zh command for per-session switching. Zero runtime dependencies.

WeChat Mini Program engineering tools: scan a project for pages missing from app.json, scaffold pages with automatic registration, fix orphan pages, manage subpackages, tabBar and components, and drive the WeChat DevTools CLI for preview QR codes and uploads.

Checks installed DSH plugins for version-declaration and API risks against the current host, with source locations when available, certainty, impact basis and coverage limits. Adds a compatibility settings panel, plugin-detail findings/badges, a compat_check agent tool and a skill provider.

Adds a restart_self tool and /restart command that replace the DSH host process with the same command line and port, then deliver a message into the calling session so the agent picks the work back up by itself.

Plugin development toolset: mark files read by shell commands, sync code into a profile, mock a plugin backend, preview a plugin frontend, verify plugin loading, spin up an isolated test instance, run named shell shortcuts, and list the plugin's tools.

A small dock in the DSH Web UI: restart the host or reload the page in one click. Restart asks first (now / 30s / 60s / 2min / cancel); the dock drags to any edge only after a 320ms hold, and stays anchored when the window resizes. Refresh refuses to run unless the plugin bundle is verifiably loadable (timestamp baseline + real bundle fetch + syntax compile), so a reload can never brick the app. Restart is Windows-only (PowerShell 5.1); the UI and page refresh work on all platforms.

Command resolution forensics: which file a command actually runs, which PATH entry won, what it shadows, how many entries are duplicates or dead, and whether the copies behind one name report the same version.

Task-priority session notifications for DSH: main-line sessions alert immediately on completion or failure, side-line completions can be batched into one alert, and questions or permission requests alert as they arrive; supports multiple main-line markers and a balanced mode that treats every session as main-line while nothing is marked.

Speaks a cue for DeepSeek Harness on Windows: a configurable phrase when an agent turn completes normally, a second phrase when the agent needs you to choose — a question, a plan approval, or a permission request — and a time-of-day greeting when a new conversation starts. A small bubble in the lower-left corner mutes and unmutes every cue with one click, with its own toggle chime. Phrases are synthesized with a Microsoft Edge neural voice (skipping aborted and errored turns, subagent turns, and rounds that a goal is still driving), cached under the DSH home directory and replayed locally, with the desktop SAPI voice as the offline fallback.

Quiet break, water, long-session and late-night reminders delivered by three bundled chibi companions, with cloud bubbles and a light bounce. Works in-page without extra downloads; the optional macOS desktop window uses a separately downloaded Electron helper.

Plays a sound when a DSH task completes, fails, or waits for approval, with per-category switches.

Shows the repository, branch, working-tree change count and short commit SHA on the composer row, with a searchable branch switcher and a per-file diff pane in the right sidebar.

Turns real git history into two Chinese changelog drafts (short for users, long for developers); every entry carries its commit SHA and an evidence-backed verified/unverified mark, and commit subjects are never translated.

Branch panel for the composer: creates rule-checked branches from production6, validates commit messages against a type(scope) convention, and commits, pushes, or merges into stage in one click.

Fork and delete buttons on each workspace row of the Harness sidebar, plus a /fork-worktree command: fork creates a git worktree and registers it as a new workspace, delete removes the workspace folder through git worktree remove (asking again before discarding uncommitted work) and drops the registration.

By default, blocks marking a team task complete without a passed independent verification record whose commit matches the worktree HEAD, and adds a dependency DAG board and a settings page.

Extends the composer model selector menu with a third Context window row, preset capacities (64K–2M), custom input, provider-wide sync, and adaptive compaction guard.

Bidirectional dispatch for DSH: opens visible desktop sessions for tasks dispatched in by Grok Bot / Yobiru, adds /dispatch-grok and /dispatch-zcode slash commands to send tasks out, and reports the session result back to the dispatching peer on completion (peers are user-configured; nothing is sent until configured).

A machine-checked reasoning ledger: every fact must resolve to a real file:line and be quoted verbatim from it, every assumption must state what would falsify it, and a conclusion may not rest on an assumption that never comes back for review. The ledger can carry a review date, a confidence and a kill condition. Ships the checker tool, an /fp command family, an optional gate that asks before irreversible shell commands, and a web panel listing the error codes each round fixed.

Coordinates PUA and Completion Guard tasks from /task-run or a CLI, requiring frozen acceptance and a current candidate/Goal certificate before completion, with an 8-round and 90-minute ceiling. Verified on macOS Desktop 0.2.0-rc.2. Since 0.3.7, PUA 0.3.27, Completion Guard 0.9.0 and SpecWorkflow 0.1.1 are bundled, so only Task Runner itself needs installing.

Keeps an unattended DeepSeek Harness session moving when nobody answers ask_user_question: it fronts the question waterfall, leaves a human answer untouched, and after a configurable window (120 s by default) submits the option marked (Recommended)/（推荐）, or the configured first/last fallback; plan reviews stay with the human unless explicitly enabled.

Windows-only: adds a switch to Settings → General that powers the computer off when the finished conversation ends (default delay 60 s, configurable 5–86400 s), behind a native countdown dialog that cancels the pending shutdown in one click (shutdown /a).

Shows what each installed skill costs in the model context and hides a skill from the catalog without deleting it. Lists every skill found on disk with the exact catalog line the model receives (description normalized and truncated at the catalog cap), its body size and token estimate; previews the catalog message byte-for-byte as the agent will receive it, compares that with the copy already published in the current session, and reports skills on disk that never reach the catalog (invalid frontmatter, or shadowed by a higher-priority root). Hiding writes disable-model-invocation into frontmatter and keeps the file, so the skill still works via /name. Also imports skills from ClawHub, Skills.sh and GitHub URLs and uninstalls user-owned ones.