Plugins

Context-window attribution for DSH Web: a Mini Utility Dock panel that ranks the user messages, assistant turns, reasoning blocks and tool results of a session by the tokens each one occupies, so it is clear which entries hold the window. It also shows the share by entry type, the heaviest entries across the live sessions of the host, and, where the host provides them, provider usage and the estimated system/tools/messages composition. The panel is read-only: it does not estimate cost, modify a session, or trigger compaction.

DeepSeek Harness Web GUI

Persistent tmux control-mode cockpit for DSH Web that mirrors native panes in a dock.

Windows process-tree reconciler for the DSH host: samples the host process tree and the job ledger, attributes each process to the job that created it, flags unattributed and orphaned processes with a confidence level, and offers guarded termination of a whole tree. Termination is refused unless the target belongs to the DSH host tree, is re-sampled and re-checked immediately before the kill (creation time included), and contains no protected descendant, so an allowlisted PID cannot widen the kill scope.

Nous Portal free-tier provider for dsh: Portal OAuth (device-code) agent-key lifecycle behind an OpenAI-compatible harness route

Native SVW waveform rendering plugin for DeepSeek Harness

Design mode for DeepSeek Harness: the design-loop agent preset plus design-principles and design-qa skill packs

Runtime governor for DeepSeek Harness: zero-progress steering, generation-bound verification evidence, evidence-aware completion guarding, and task-profile tool restriction.

DSH plugin guard: checks profile bundle lists for duplicate loader entries on every plugin load, preventing the 'duplicate loader entry id' boot crash caused by listing an aggregate bundle and its sub-plugins together — and the `dsh plugin` reconcile recu

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.