Plugins

Application de chat interactive en terminal pour dsh : conversation en streaming, cartes d'outils, panneau de tâches, recherche plein texte, relecture de trajectoire, onglets multi-sessions et répartition A2A (basée sur Ink).

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

让你更清楚地了解究竟是什么占据了你的等待耗时 ⏱️ DSH 实时时序轨迹与执行过程追踪插件

A [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) plugin that adds a **Files** tab to the Conversation View strip — the same level as **Chat** and **Trajectory** — showing the session workspace as a tree with a basic text preview beside it.

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and

View tab manager for the DeepSeek Harness Web GUI session header: enable, hide, reorder and rename the conversation view tabs (Chat / Trajectory), with locale-aware zh/en copy and npm update reminders.

Always-on-top capybara task reporter for DSH Web — a transparent floating pet that narrates each trajectory step in a speech bubble, names the project it reports for, and alerts you when a task completes while you work elsewhere.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.