Plugins

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Attach tags to sessions and search sessions by tag in the Web settings panel.

Persistent wallpaper skin for the dsh web profile: static image or muted looping video as the app background, with translucent panels and a floating picker panel.

Token usage statistics for DeepSeek Harness. Per-channel usage with balances and plan quotas for mainstream providers, CNY cost estimates, and daily charts — a settings-sidebar section.

Bottom-right 余额 badge for the DSH Web UI: on expand it fetches the currently-selected provider's OpenCode Go plan limits or DeepSeek prepaid balance, plus local token usage and pricing-based spend estimates.

DeepSeek API quota panel collapsed into a left-edge handle for the Web UI: click to expand balance, official today's consumption (with platform token) and live conversation cost; fork of dsh-deepseek-quota.

Floating community panel for the Web UI: 24h hot topics and hot plugins TOP10 with a draggable, always-on-top button.

Interactive terminal chat app for dsh: streaming conversation, tool cards, jobs panel, full-text search, trajectory replay, multi-session tabs, and A2A dispatch (Ink-based).

Real PTY terminal panel for the DSH Web UI: host half spawns shells with node-pty (cmd.exe default on Windows), rendered in the browser with xterm.js; multi-tab sessions, dock/floating window, clipboard support.

Incremental diff reviewer for DSH: after approving a batch, only new changes since the checkpoint are shown, with a Web review panel and `/review` command that inject feedback back to the agent.

Installed-plugin catalog for DSH: group plugins by origin (official vs self-installed) in a searchable panel with enable/disable, uninstall, and one-click update.

Runtime log panel for DeepSeek Harness: live SSE log view in Settings plus bounded date/size rotating JSONL files.

The missing companion CLI for DeepSeek Harness (dsh): manage MCP servers with one command — add/list/remove/test with dry-run connection checks, plus one-shot import from Claude Code / Codex. Also mounts as a dsh plugin so the agent can manage MCP itself.

Turn navigator panel (current turn / total turns with up/down jump) for the DeepSeek Harness web GUI

A desktop-native BigFish companion driven by DeepSeek Harness session events.

A dsh status plugin with host-plane and browser halves: harness runtime health (process, listener, API-key presence, memory, uptime, plugin inventory) as JSON plus server-pushed SSE alerts, surfaced as a header badge with an expanded panel in the Web UI

Cited memory over DSH's lossless session log: distilled facts carry `(sessionId, eventRange)` citations that expand back to the exact original log excerpt.

System panel for DeepSeek Harness: machine, runtime, working repositories and Kubernetes cluster health

Typing companion with five characters and composer following. This entry installs the universal page package (page mode only); the optional Rust desktop mode for macOS and Windows ships in the platform-specific release packages (darwin-arm64, darwin-x64, win32-x64).

Feishu/Lark integration for DeepSeek Harness through the official lark-cli: a sidebar panel for app setup and QR sign-in, a command console, and agent tools that run any lark-cli command across 18 business domains, 200+ high-level commands and the full OpenAPI; the official CLI is downloaded on first use on Windows, macOS or Linux.

Right-sidebar Git review panel for DSH: staged and unstaged change tree, inline and side-by-side diffs, stage/unstage/discard, commit and push, AI-generated commit messages, and line blame. A fork of sadgsk/dsh-review-panel 0.3.1; install either this or the upstream panel, not both.

Collects the open questions of each AI turn into a right-side panel; you answer them, add notes, and send the decisions back to the conversation in one message.

Adds contextual guidance for explaining technical misconceptions in conversations.