Plugins

Google Antigravity (agy CLI) models for DSH — streaming chat with Gemini/Claude/GPT-OSS subscriptions, native tool cards, thinking turns, and in-GUI Google OAuth login.

Configure reasoning-effort levels and sub-agent defaults for custom DSH models.

Customize the "deep diving" thinking status label to anything you like.

A Live2D whale-girl companion for the DeepSeek Harness Web UI: the model stays on screen and reacts to what the agent is actually doing (thinking, tool calls, streaming text, errors, turn completion); click her to send the agent a message and watch the reply stream into a speech bubble; right-click for a menu of expressions, dress-up items, desk scenes and one-shot animations, every action mapped from the original model author hotkey sheet so nothing overlaps and everything expires on its own. Non-commercial model assets (CC BY-NC-SA 4.0), MIT code, by Andersen216 (https://github.com/Andersen216).

Display-layer translation for the DSH Web UI — thinking chains, task cards and answers in 8 target languages via local Ollama or Google/Bing, originals preserved.

Let Your Ideas Flow — Tydora is a modern desktop Markdown editor combining WYSIWYG editing, bidirectional links, mind maps, and an infinite canvas — empowering deep thinking and effortless expression.

UI enhancement suite for the DSH web client: Chinese locale completion, one-row stats, auto-expanded thinking, chat width, session archiving and delete, plus an optional prompt-injection switch (off by default).

Live2D desk pet overlay for the DSH web GUI: mirrors agent state (thinking, idle, error, done, awaiting approval) with motions and speech bubbles, per-part touch reactions, drag-to-dock, switchable personas, and custom models via URL or local path.

Visual branch brainstorming that creates an isolated Session for each direction, automates parent, sibling, checkpoint, and return Handoffs, and provides a full tree tab with an optional Better Sidebar view.

Streaming-transcript fold for the DSH web UI: thinking and tool rows fold away while the newest thinking window opens itself; a finished turn scrolls back to your question, which also stays pinned at the top while you read; blue sparks fly from the thinking window edge and the answer writing head.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Per-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3.8 line (llama.cpp or NInfer).

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.

Installs Herta as a DeepSeek Harness agent: a preset carrying her persona and memory prompt sections, six memory and voice tools, a narrative layer that separates her thinking from what she says, 80 bundled voice clips, offline and MiniMax speech synthesis, and two conversation views that render the session with her own components.

Task reliability: auto-retry on model timeouts/failures, auto-continue unfinished tasks, completion verification, thinking-repeat interruption, resume after sleep or restart, autopilot mode and a remote trigger endpoint (npm: `dsh-task-reliability`).

Thinking in Chinese: injects a system prompt so thoughts and replies stay in Chinese, expands the reasoning block by default with interactive collapse, and localizes UI labels (npm: `dsh-think-zh-expand`).

Liang Saint Slider as the DeepSeek Harness model + thinking-effort selector.

Thinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects two per-call shapes (reasoning-only calls, restated-material calls) and re-fires instead of latching; plus two mid-stream breakers that en

Installs Herta as a DeepSeek Harness agent: a preset carrying her persona and memory prompt sections, six memory and voice tools, a narrative layer that separates her thinking from what she says, 80 bundled voice clips, offline and MiniMax speech synthesis, and two conversation views that render the session with her own components.

Injects one system-prompt section so the agent's chain-of-thought, planning and tool-invocation reasoning stay in Simplified Chinese. Zero external dependencies - clone and link-install from any local directory, no npm build or publish required.

Visual round-table meetings for DeepSeek Harness — expert nodes on a ring with directed edges, an aggregation gateway, proxy thinking for black-box worker models, and adversarial review (red-team) of settled plans with per-viewpoint endorse/reject.

A whip for DeepSeek V4 Pro: it watches the reasoning fingerprint of every thinking block and pulls the model back when it slips from focused "We will / I will" mode into scattered "let me" mode.

Desktop pet drawn from the official whale outline, for both the desktop app and the web UI: SVG animations and facial expressions follow agent state (thinking, working, done, error, waiting for confirmation), and it can follow other running sessions with a count badge; poke it, drag it, shake it dizzy, squash it against a screen edge, or rub the cursor over its head for a headpat; 7 palettes, 4 sizes, synthesized sounds, light/dark theme sync, and a playable web preview.

Injects one fixed system-prompt section so the agent thinks and replies in Chinese, regardless of the user's language.