Plugins

DeepSeek Harness plugin: declare named subagents in TOML files under ~/.dsh/agents and <projectRoot>/.dsh/agents

Read-only work report rebuilt from local session logs: tools used and how often, commands run, files read and written, whether tests passed, failures and their causes, token usage, and whether the task finished.

Replaces the DSH sidebar with a fixed 2×4 board of eight standing agent seats; each seat shows its own status, latest tool call, reasoning and result, and a settings switch restores the stock sidebar at any time.

Multi-agent task decomposition, DAG workflow orchestration, and prompt caching optimizer for DeepSeek Harness.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

dsh (DeepSeek Harness) 跨 agent 信箱插件：让 dsh 会话内的 agent 通过 agent-mailbox 与本机其他 agent（Claude Code / OpenCode / Hermes…）互发消息、收任务卡、卡动即唤醒。零 npm 依赖，Node 22 即装即用。

Per-command proxy for DeepSeek Harness: the agent decides which shell commands leave through a proxy, backed by a kernel the plugin installs and supervises itself.

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

Extensible AI-driven group-reaction narrative game framework for DeepSeek Harness: type one action and multiple NPCs each respond in their own chatroom message with avatar illustrations; worlds, locations, NPCs and feature extensions (e.g. a third-party drawing API for dynamic NPC expressions) are added and modified through the harness chat dialog without code.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

Discovers Codex and Claude project directories and registers them as shared DeepSeek Harness workspaces.

An AI collaboration mailbox in DeepSeek Harness for messaging, task handoffs and delivery receipts. One package includes MCP integration and a mailbox UI. Version 0.2.2 requires DSH 0.2.0-rc.2. Requires a separately installed Agent Mail 1.0.0-alpha.7 provider; no automatic model wake or continuous online status.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Agent-tree token budget management.

A model-driven desktop pet, derived from PC2005-cloud/dsh-pet (MIT): an always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, keeps a per-pet affection ledger, speaks through pet_say/pet_do tools or an autonomous inner voice, and can read those lines aloud through BreezeBlue TTS with your own BreezeBlue API key. It uses its own /whale598 route and ~/.dsh/whale598 data directory, so it is a separate pet from dsh-pet rather than a replacement for it.

QQ hub for DeepSeek Harness: private and group chats over OneBot v11 (SnowLuma/NapCat), with per-chat scoped memory, per-chat persona routing, a vision helper that narrates images for text-only models, multi-platform link parsing (large videos sent as group files, image galleries sent inline or as merged-forward messages) and a web panel for models, personas and settings. Derived from aureth-labs/dsh-aurabot-qq; do not install both.

Views, creates and edits AGENTS.md and other AI rule files from the DSH settings page: the project directory chain from project root to cwd, both DSH global roots (~/.dsh and ~/.agents), and user-level rule files of 25 third-party AI tools. Markdown preview is rendered with .mdc frontmatter stripped, edits save in place with conflict detection, files whose content is identical across tools are flagged, and tools outside the built-in list are discovered heuristically. Zero runtime dependencies.

One read-only index of every local AI-agent session (Codex, Claude Code, DSH, Trae, or any JSONL source) grouped by project, plus an append-only shared board for decisions and handoffs so switching agents leaves no context gap.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

Adds personality injection, a decaying memory card, a mood state and a daily diary so the agent keeps identity and history across sessions.

Agent preset studio: inspect every mounted tool, edit the system prompt, and save the result as an installable preset bundle. · Agent 预设工作室：查看全部工具、编辑系统提示词、存成可安装的预设包。

会话成本审计：看看一次对话的 token 花在哪、哪一步贵，并把优化建议做成一键可应用的修改。