Plugins

Adds a Managed Agents settings tab and MCP tools to dispatch long-running agent tasks to Ark cloud Managed Agents.

A persistent agent team for long-running collaboration in DeepSeek Harness: durable agent identities, per-project Workspaces, responsibility-bearing Channels, and Task Threads chaining session agents.

Domain-identity layer for long-running agent sessions — declaration-first domain addressing, a session factory, four-level pause, and model dispatch for coordinating multiple top-level sessions.

Counts agent steps and, every N of them, adds a progress-report instruction to the batch that is about to be sent, so the agent states what it is doing, what it finished and what comes next, then carries on without stopping for you. Interval, prompt text and a main-agent-only default are editable in its settings page.

Runtime requirement drift guard that keeps long-running DSH agents aligned with the user's approved goal, constraints, and decisions.

DeepSeek Harness rate-limiting plugin that prevents API 429 errors during long-running tasks, with task retrospectives.

WSL console for the harness — manage distributions, edit .wslconfig and wsl.conf in a typed form, and run commands, file edits and long-running processes inside any distribution with its own wslx-* tools.

Bounded-context memory for long-running dsh conversations and large group chats, with a focus-limited person pipeline, a fixed injection budget, and append-only event archives.

Wakes a session when a long background task finishes after the turn has ended, and lets the model schedule its own wake-ups (once, interval, or cron with jitter) under quiet hours and a daily budget.

Nudges the main agent of a long-running DSH session to report progress at a configurable interval, with exponential back-off, stuck detection, a per-session Progress tab, and a manual "nudge now" action.

Progress tab for the DSH right sidebar: the turn status of the session and the progress long-running tasks reported, in one tab beside the conversation.

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.

Detached-broker supervision of long-running services (dev servers, watchers, mock APIs) that survive turns, sessions and DSH restarts, with a Service sidebar tab (registered via better-sidebar's extension API) and service_start/stop/restart/list/logs model tools.

Externalizes oversized assistant and tool messages in long sessions into project files while keeping a recent window, and archives reasoning from empty turns as a visible message so long tasks do not stall on context size.

Quest tree for DeepSeek Harness: track a long-running task as a main quest plus a branch tree, with a sidebar panel showing status, progress, markdown notes and a 'you are here' marker to prevent drift.

Host-side progress checkpoints for long DSH tasks. After N minutes or M tool calls the model is nudged to post a one-line progress note and keep working, so you can correct it before it runs far off course.

Experiment-orchestration SOP skill for long-running experiments. A top-level model drafts a decomposition plan — subtasks, the model for each, an acceptance figure with tolerance, and dependency order — and dispatches only after the user confirms that plan; each subtask then goes to a lightweight executor subagent as a self-contained prompt, and its report is confined to measured facts and the delta from the agreed figure, with judgement and decisions staying at the top level. Ships one plan template and five task templates (gather, execute, consistency check, read-only review, mechanical transform), acceptance gates split into a task layer and an experiment layer, and three rules that stop internal-consistency evidence from being presented as independent or external validation.

A right-side panel that tells you in plain words what a long-running task has finished, what it is doing right now, and what it will most likely do next — read-only, never touches your session, and you can ask it a question or just chat with it while the task keeps running. Requires the dsh-better-sidebar plugin, whose right sidebar hosts the panel.

General-purpose chat agent on a parent agent + worker sub-agent split, for DSH Desktop only: a sidebar row opens each assistant's long-running conversation, where the parent chats, records schedule, lists, memos, logs, profile, persona and projects as plain files in that assistant's workspace folder, and hands other work to background workers through the bundled complete-subagent, picking each worker's model from the ones you enable and approving their write access. A heartbeat wakes it for reminders, a daily brief and wake-ups it sets itself, and holds back during quiet hours. Through the bundled im-robot it chats over WeChat: the model decides per reply with im_route whether the reply also goes to WeChat, and images and files sent from WeChat appear in the conversation and stay in the workspace's IM/WeChat folder for a set number of days. Its tools never appear in normal sessions.

Purpose-aware monitoring for DeepSeek Harness long-running commands

Live progress for long-running DSH tasks: a script appends JSON lines to a per-session progress file, the Web UI draws them in a floating overlay and a right-sidebar tab that also lists background jobs which reported nothing, and `dsh-progress run -- <cmd>` wraps a command that cannot report for itself.

Live progress for long-running background jobs in the DSH web GUI: a draggable floating ball in the session that owns the job, expanding into a panel with done/total, speed and ETA.

Automatically resumes active goal sessions after DSH restart; long-running tasks continue without a manual nudge.

Service farm for DSH: register, start, stop and restart long-running project services, with agent tools (farm_status/start/stop/restart/logs/register), farm.yaml declarations and an overview drawer UI with live log follow, search and export.