Plugins

Reorder the messages queued while a DSH agent is busy, from inside the official queue dock: a drag handle and per-row ↑ / ↓ buttons on the dock's own rows, applied on the host as one concurrency-checked inbox splice. The dock is decorated rather than replaced, so previews, inline editing, steering, removal and attachments stay as shipped. A move is refused when the queue has changed since the caller last saw it, when the row is not a user prompt (a goal round prompt, for example), or when the queue belongs to a subagent session.

Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.

Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.

Intelligent sub-agent orchestration for DeepSeek Harness, with model discovery, routing, planning, and parallel delegation.

AI 主持人驱动的多角色群聊插件（DSH Host）：自动生成主持人 + 3~6 专家团队、动态调度讨论、成员 subagent 深度推理、总结结论并导出 md 到工作区

Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.

Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversat

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.

WhaleHarbor desktop pet for DeepSeek Harness: an always-on-top transparent float window hosts a chibi whale-maid built from 13 AI-generated parts and animated as a CSS paper-doll (breathing, blinking, ahoge sway, sweat, hops, tremors), mirroring work state in eight moods — idle, busy, approval, question, error, celebration, nap, and subagent clones — with poke, drag, three sizes, tray toggle, and live stats in the speech bubble. Requires the WhaleHarbor desktop shell (Windows build).

Whole-book translation production line for DeepSeek Harness: deterministic chapter detection and segmentation, per-chapter subagent translation, glossary control, full-book review, targeted revision, and auditable meta.json evidence.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

ServerChan3 (Server酱) push notifications when a turn finishes — title, model, project directory, git branch, status and a reply excerpt, with subagent filtering and fire-and-forget delivery.

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Registers Kimi, Grok, Codex, and MiniMax as DeepSeek Harness model routes, vendor subagent recipes, and kernel_status / kernel_run / kernel_switch tools.

Session change-review for DeepSeek Harness: tracks write/edit tool calls and renders VS Code-style side-by-side diffs via diff2html, auto-following the theme, with subagent aggregation and one-click revert.

One-shot Grok CLI subagent provider for DeepSeek Harness

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

Per-conversation subagent model selection for DeepSeek Harness Desktop.

Holds the OS wake lock while any agent, subagent, or background job runs, releases it after a configurable grace period, and provides a bilingual web settings page with live status, manual hold, and display-on options.