Plugins

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Reasoning-wait thinking indicator for the DeepSeek Harness web composer

Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.

Results-only conversation toggle for the Web GUI: hides thinking and tool-call process rows, keeps one live status line while the agent works, restores working animations under prefers-reduced-motion, zh-CN/en localized. Works in the stock composer and inside dsh-split-screen panes; verified on DSH 0.1.1 and 0.1.5.

Customize the visible DSH Web thinking status with lifecycle-safe CSS.

Content-degradation detection (thinking loops, output repetition) for DeepSeek Harness, with a continue-vs-handoff cost verdict and zero-model handoff documents.

Writes the harness agent live state (thinking, working, waiting, done, error) to a state file that a bundled Electron Live2D desktop pet polls, so the pet bubble and face follow what the agent is doing.

Shows a Chinese translation under each English thinking block in the DSH web chat, without modifying the session transcript; per-chunk caching, a configurable translation model, and a settings panel.

Auto-expands streaming thinking: always keeps the latest thinking block expanded, manual actions take priority, only the last block expands when opening a session, and nothing remains after uninstall.

Personalises the DSH running-turn status line: rotating bilingual quips, a configurable animated loading icon (5 styles x 3 sizes) and one-click matching to the active theme colour, all in a General-settings panel, plus a # Chinese / # English sectioned quips editor. Ships with no dependencies, no build step and no config file.

A desktop pet in the DSH web GUI: floating, draggable sprite pet that animates with agent activity (thinking, idle, error, done, awaiting approval), with a settings page for size, switching, gallery search and one-click pet install. Ships 4 bundled Hunter x Hunter starter pets.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

A Taffy mood mascot for the DeepSeek Harness Web UI: the corner GIF reacts live to agent state — approval pending / approved / rejected / begging, thinking, tool runs, interrupts, ask_user_question waiting, compaction, long-task fatigue, idle-ignored approval, idle / sleeping — with SSE-pushed state, drag positioning, middle-click console, tool-card mirror console, per-mood locking, persisted appearance settings and per-day bucket statistics.

Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.

Matrix-style CLI chat page for the DSH web UI: the agent's thinking streams down the screen as green code rain while replies print normally in the terminal.

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.

One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.

Conversation node appearance for the DeepSeek Harness web GUI: configurable per-category and per-tool colors (left accent bar + tinted background), plus a show-thinking toggle; pure frontend rendering, takes effect instantly and persists to the DSH user settings file.

Read another session's content (messages, tool calls/results, thinking) from within a DSH session

DeepSeek Harness plugin: import models with capabilities from an OpenAI-compatible /v1/models listing (gateway capability extensions) and edit per-model capabilities (thinking, vision) on its settings page

A full-screen terminal workbench for DeepSeek Harness with a durable assistant, workspace-grouped project sessions, transcript-only scrolling, and structured thinking, tool, diff, plan, and subagent views.