Plugins

Keep branching from any completed answer at any depth while the main session stays untouched.

Quote selected conversation text into the Web composer as native reference chips for focused follow-up turns.

Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory).

Every conversation gets an ending: mark dev-done, release channel and version in the conversation header, see how many items still need attention in the sidebar, and read all unfinished conversations, tasks and schedules in the right-panel ledger.

Adds a lightweight follow-up row under each DSH answer: one anchor question plus 1-3 user-voice quick replies, so the next turn is one click away; supports always / balanced / conservative strategies and optional refusal or emotional-context skips.

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.

Watches the turn endings of the models you select and asks a second model whether the turn was actually finished: if the assistant stopped after text with no tool call, a three-way verdict of continue, finished or uncertain is recorded and shown in a sidebar panel. In suggest mode it only reports; in auto-continue mode it calls agent.followup() once the turn is idle to send a continuation message, up to a per-turn limit. Single-step turns are always rechecked, watched models can be picked exactly or matched by case-insensitive regex, and the resume text is configurable.

Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.

DeepSeek Harness plugin that predicts your next message after each reply. Press Tab to accept it as an editable draft; it never sends by itself.

Continue an existing PC DSH session from WeChat: polls WeChat iLink messages, injects into a running session via followup or resumes a closed one, and sends the reply back. Supports /会话 to list/bind sessions and /新会话 to unbind. Requires the wechat-acp daemon; only allowlisted WeChat senders are handled (empty allowlist denies everyone).

Select any text in a DSH chat reply to get a floating Follow-up/Copy pill: one click quotes the selection into the composer so you can type your own follow-up question, or copies it.