Plugins

Session-header task capsule with color-coded run states, click-to-jump and a multi-task dropdown, plus task notification cards (done / error / waiting-for-confirmation) with synthesized sound and optional system notifications.

Dynamically trusts every Host header that actually arrives and flips the default web binding to 0.0.0.0: wildcard or unenumerable entry domains work without editing the start command, the authentication layer is untouched, and hosts are evicted by LRU beyond a capacity cap.

Turn event notifications: six event classes (completed, error, interrupted, approval requested, AI question, limit reached) delivered via sound, system notification, in-page banner, webhook, IM and host desktop-notification channels; when several browser windows are open, only one rings.

Runs a thesis-antithesis-seal debate whose verdict is computed from real command exit codes and case counts, never from agent prose.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Turns a plain-browser DSH session into the WhaleHarbor lite client: a standalone browser --app window with a client-style top bar and task notifications, while the full desktop installer downloads in the background (multi-source, SHA-256 verified) and an install prompt appears when ready.

Proxies the loopback-only dsh web onto a LAN port so phones and other machines can reach it, with an optional access password that browsers type in and the bundled Android client unlocks with biometrics. Adds a LAN-access settings page with QR codes, inlines dsh-web-mobile (MIT, attribution kept) for the mobile layout, and the Android client in the same repository adds finish/approval notifications, voice input and a home-screen widget.

Adds a restart row to Settings → General that relaunches dsh web with the same invocation through a detached helper, refuses under a detected systemd supervisor unless allowRestart is true, and tests whether the listening port is free by connecting to it rather than binding it.

在 DSH 需要人工回答或一轮对话跑完时弹出系统通知。标准可安装的 dsh 客户端插件。

In-process cross-session communication, peer session creation, and shared blackboard for DeepSeek Harness.

Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.

Windows-native tools for DSH agents: clipboard read and write, system notifications, hosts file inspection and network diagnostics, each returning structured data with UI cards from injection-safe PowerShell.

TRAE-style conversation rollback — per-turn checkpoints (10-turn sliding window) roll back touched files and truncate model context in place, keeping the same session id. Human-initiated only: a /rollback command or a per-turn Web button (works on interrupted turns too), with a preview listing each affected file and its action — restore, recover, delete, or skip.

Team cost captain: meters every model call (subagents included), attributes each call to a member by workspace rules, prices it with the built-in DeepSeek 2026-09 catalog (peak/off-peak, CNY/USD) or user overrides, and appends it to a local JSONL ledger. Adds hot-reloadable member budgets, 80%/100% webhook alerts, optional over-budget enforcement, a team_cost_report tool with CSV export, and a settings-page team dashboard served over a Typert RPC service.

Model pricing for the DSH settings page: ~7,250 models / 213 providers with the harness catalog overlaid, honest lowest-listed comparison, session costs priced by the actual route, cache-leak attribution, and a verified promotion feed.

DSH web plugin: a sidebar footer QR-code button that lets a phone scan and re-issue the current browser's authenticated launch URL, reusing the same ?token exchange the desktop just completed.

Tri-channel task notifications: in-page toasts with chimes, browser OS banners, and host-direct OS toasts that keep working with the browser closed, plus a bell panel with persistent history.

Adobe Lightroom Classic as native dsh tools through the lightroom-py MCP server: read the catalog, apply develop settings and presets, export JPEG/TIFF/PSD/DNG, and write ratings, labels, keywords and IPTC — 15 tools driving the Lightroom Classic installed on the local machine, no cloud round-trip; the Python package is on PyPI and the Lightroom plugin installs with one command.

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.

Irreversible secret-scrubbing guard: rewrites access keys, bearer tokens, and private key blocks into `[REDACTED:<category>]` placeholders before they reach the session log and the model.

Multi-channel notifications for DeepSeek Harness: registers a send_notification tool and a settings page fanning out to NotifyX, WeCom app webhook, WeCom group robot, email (Resend), SMTP, DingTalk, Feishu robot; plus browser notifications and automatic notification on task completion and blocking events.

Whole-report verification for scientific reports: per-claim checks against Crossref, PubMed (retraction scan), ClinicalTrials.gov, UniProtKB, GEO/SRA and PatentsView, URL accessibility and title agreement, claim-vs-source meaning at temperature 0, and a durable restartable audit ledger with an annotated report.

Self-evolving project-level Agent for DeepSeek Harness: 16 SDD workflow skills (clarification, PRD, issue, coding, locating, acceptance, review) plus project memory and knowledge that compound over time.