Plugins

Search and manage archived and unarchived chats with read-only previews, tags and notes, workspace archiving, ZIP backups, origins and branches, manual residual-chat checks and automatic update checks. Retains legacy Recycle Bin recovery without automatic cleanup.

Live subagent run monitor for the Web UI: a sidebar footer trigger plus a fixed top-right card panel showing each subagent of the current session in real time (running/elapsed, terminal outcomes, tree indent), with one-click jump into the child conversation and a return button, refresh-surviving and mobile-hidden by default.

Reference logged-in Chrome/Edge tabs and authorized local HTML with @ for reading, batched actions, screenshots and WebMCP; collect annotations in chat drafts with a draggable toolbar. Select running Windows apps with icons, prefer a matching installed MCP or approve installation, then fall back to Cua Driver. Supports text and key chords, paged control handles, minimized-window checks and optional action readback. Includes guided browser pairing and refreshed annotation controls; background input depends on the app.

Twelve official Remotion skills synced from the official upstream (programmatic video with React: animation, audio, captions, 3D, maps, charts, render, Studio), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Automatic conversation distillation: background subagent reflection + skill create/update.

DeepSeek Harness Default System Prompt Management Plugin: Browse, search, and override the final system prompt assembled into each session round within the Web GUI "Settings".

Host-side DSH evaluation control plugin: injects one evaluation trial's variables, budget limits, session root and fork lineage into the agent process, routes its model calls through a host broker under a gateway lease, and writes a schema-versioned bundle descriptor for evidence attribution.

Native-style notification sounds for DeepSeek Harness: a chime when the agent needs your decision or finishes a task, clickable system notifications that jump back to the window, repeat reminders, quiet hours, and goal-mode alerts that wait for the final round.

IDE-style Git panel in the DSH Web GUI: a resident tab with a three-column overview (branch/tag list, searchable commit-history graph, commit detail with changed-file tree and message) and a changes page (stats bar, uncommitted list with per-file stage/unstage/discard, commit box with amend); side-by-side diffs carry lazy highlight.js syntax highlighting, on-demand between-hunk context expansion and word-level intra-line emphasis, with image files shown as before/after panes; plus a zsh-style branch marker in the input bar. Every git command runs as an argv array through the host subprocess service, cwd locked to the repo root.

omdsh: a keyboard-first DeepSeek TUI coding agent on the DeepSeek Harness runtime

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

DeepSeek Harness plugin for dsh-baton: adding it is the whole install. Switched on, it registers the dsh-baton MCP server for Claude Code and Codex, then takes the baton over a local, owner-only control socket, runs it in a specific session through the ho

Connects Qoder (Lingma CN / international) models to DSH through their PATs, with a per-region multi-account pool, daily check-in, automatic failover, and read-only credit visibility.

Native interactive answers, editable cards and on-demand UI skills for DSH.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Pauses the agent right before it sends the next model request of a tool round while keeping the composer usable: a bare Enter or the resume button lets it continue, and text typed meanwhile is sent along as a steering message; the pause never interrupts an in-flight API call and the model does not notice it.

In-app plugin marketplace for DSH: plugin discovery, install, upgrade, toggle and uninstall in one panel for Web and Desktop host profiles, pairing a community catalog of 4,000+ entries with customizable curated lists, plus eight agent tools and a standalone dshm CLI, without a marketplace server or account.

While vibe coding, save an answer you may need later, use Side Chat for a question that suddenly comes up, or open a related conversation for deeper work without losing focus on the current task.

Edit a sent message to rewind and branch the conversation from that turn, switch versions with a counter under the bubble, and browse every branch in a turn-level version tree.

Two-phase agent preset for DeepSeek V4 Pro: the first request sees only bash+read (Minimal-aligned bootstrap), then the full Standard tool catalog after the first tool call or reply; ships as an installer bundle plus a manual preset directory.

One-click optimization of a raw instruction into a professional prompt: three output styles, situation-aware role/task/goal profiling, multi-sample selection scored by a model judge, self-iterating learning (session memory + smart defaults + user overrides), /template for 22 sub-scenes with zero model calls, input-box ✨ one-click optimize/undo, prompt_optimize tool, auto-optimize hook, a runtime status page, a settings panel (dsh 0.2.0) and auto-detected zh/en documents.

Appearance customization for the DeepSeek Harness WebUI: theme palette, wallpaper and video backgrounds, translucency and glassmorphism.

Windows tray desktop shell: auto-installs and auto-updates the exe from GitHub Releases, creates desktop shortcuts for both the app and the web UI, and exposes a desktop_launch tool to start it from the conversation.

Brings WorkBuddy desktop-app models into DeepSeek Harness: the China and international builds each appear as their own group in the model picker, with the reasoning tiers the upstream declares, per-reply credit cost and remaining balance, per-account model visibility, and image input where supported.