Plugins

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Adds a permanent Delete session action to the sidebar session menu, behind a confirmation dialog that reports the log size, running turns, subagents, background jobs and reminders bound to the session; the id is then released from the live, archive and workspace registries, so the row stays gone on refresh instead of folding back in.

Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.

Transparent acrylic window material and layered frosted panels for the DeepSeek Harness desktop app: the window reveals the desktop wallpaper (Windows Acrylic supplies the blur), the composer is a pane of frosted glass, and chat text is hard-clipped at the composer's top edge. Note: the page styling installs with the plugin, but making the window itself transparent needs a one-time app.asar patch (the patch bundle in this repo's Releases; double-click enable-transparency.cmd). The patch takes effect after a restart and must be re-applied after every DSH update. The plugin works without it — the window simply stays opaque.

Full-page NetEase Cloud Music player for DSH: daily recommendations, playlist browsing by category, charts, new releases, search, playlist/album/artist pages, QR-code login, synced lyrics, queue and downloads, plus four agent tools for search, song URLs, lyrics and playlist tracks.

Generates release material from what a local repository can actually support: a hero image, a feature grid and bilingual copy rendered as SVG and HTML from `README.md`, `package.json` and optional screenshots. Facts are quoted from those files — name, version, license, summary, features, install snippet — and a field that is missing is left unrendered rather than filled with placeholder text. Every feature carries a source citation such as `README.md#L42`, and a claim the repository cannot substantiate is linted out before anything is written, with the reasoning left in `lint-report.json`. `manifest.json` records a sha256 for each input and output, and `--now` or `SOURCE_DATE_EPOCH` makes a run byte-identical. Also ships a GUI panel that regenerates from inside a session.

Keeps the DSH host awake during active tasks using native power assertions and releases them when tasks finish.

Plugin updater for DeepSeek Harness that delegates every version decision to the dsh CLI, so the pnpm release-age policy still decides what is eligible; it snapshots before applying, can roll back, keeps a lock list, and can check or auto-apply on a schedule the user turns on.

macOS only: holds a PreventUserIdleSystemSleep assertion (caffeinate -i -w <host pid>) while any DSH session runs, and releases it when the last one stops, so a long turn is not cut off by idle sleep. The display may still turn off. It keeps holding through the maintenance phase, where Agent.status reports idle and a long manual /compact runs, via the compaction/start and compaction/end events. It reconciles against ctx.agents.list() every 60s, so a session already running when the plugin is hot-reloaded is picked up at once instead of at the next turn boundary. A failed hold retries with exponential backoff capped at 60s and never gives up; release escalates from SIGTERM to SIGKILL after 2s, and -w lets caffeinate exit by itself if the host dies. No browser half — configured through the profile patch. 51 tests, including two that read pmset -g assertions on real hardware.

Bring a DSH plugin repository's build and release pipeline into the app: a sidebar panel listing each repository's latest workflow run, its releases, and how far the local checkout has drifted from the last release, with buttons to trigger a build, cut a release, publish a draft, re-run, cancel, or read the failed-step log. Drives the workflows through the machine's authenticated gh CLI, so the plugin stores no credential of its own, and which repositories are tracked lives in a config file rather than the package.

Folds each 4-50 KB paste in the DSH composer into its own chip (expand or delete it individually), and turns a paste of 50 KB or more into a real file attachment. Declares DSH >=0.1.7-rc.2 <0.3.0-0, so it stays visible on the 0.2 release line.

Adds a draggable power pill to the DeepSeek Harness Web GUI: a live status dot plus restart and stop actions, where restart is handed to a detached helper that resumes the same boot invocation once the port is released.

OpenRouter provider that reads the live /models list, so new models appear without a harness release: models sorted by name with input/output prices, per-model reasoning levels, image input, reasoning_details replay, Anthropic prompt caching, and actual spend per session including subagents from OpenRouter usage.cost, shown under the Web UI composer and by /cost.

Adds a Check for Updates row in Settings and a right-sidebar card that update the DSH CLI and every profile plugin, with npm channel selection (auto/stable/next/alpha), minimum release age, backups, one-click rollback and a test reminder for the badge and browser notification.

GitHub operations for DeepSeek Harness: releases, tags, a guarded generic API pass-through, workflow runs, secrets and sanitized mirror publication.

DSH core version monitor & upgrade helper: sidebar status badge, npm release checker, and one-click update command

A DSH plugin that automates shipping a local project: create a GitHub repository and publish it (git init/commit/push + topics + tag + release), sync requirements/progress to Linear, publish to npm, and announce in the community Discussions — to join the

Track DeepSeek Harness's own releases and update in one click: reads the npm dist-tags and the GitHub changelog, shows every change between the running build and the target, grades the risk, then hands the install to a detached helper that backs the current install up with an atomic rename, runs npm, verifies what landed, relaunches, and rolls back when the new build does not come up.

Adds a Check for Updates row in Settings and a right-sidebar card that update the DSH CLI and every profile plugin, with npm channel selection (auto/stable/next/alpha), minimum release age, backups, one-click rollback and a test reminder for the badge and browser notification.

LiveBench leaderboard for DSH — discovers the release the official site currently publishes, then reads its CSV and category JSON, and renders model rankings in an isolated same-origin iframe opened from a button beside the composer. Search, organization / open-weight / reasoning filters, per-category sorting, task-level detail, up to four models side by side, CSV export; refreshes every 60 s by default (configurable 30–3600) and caches only to the plugin's own .cache/rankings.json.

Pre-boot health checks and repair for dsh plugin trees — ten static scan rules that follow the launcher runtime resolution, fault attribution after a failed boot, whitelisted reversible fixes verified in an isolated instance first, an upgrade preview naming the plugins a target release would skip, and a panel with plugin-row management plus a RAG knowledge base of past failures.

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and

Evidence-first frontend release checks: real-browser content, accessibility, runtime, network, and baseline regression reports with screenshots.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.