Plugins

Dynamic Schulte grid waiting-time mini-game: click 1..N in order on a static grid or a spinning roulette wheel while the model thinks.

Pi TUI (differential-rendering terminal framework) front end: streaming markdown, thinking collapse, tool cards, slash commands, approval/question overlays, shared dsh session store.

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

SAP AI Core provider with shared OAuth, five Qwen model choices, thinking budgets, streaming, and tool calls; validated on cn40.

[LLM] 使 DSH 能从 magpie 上游同步输入模态及 thinking level

DeepSeek Harness plugin: tell every agent to write its private reasoning in Simplified Chinese.

A Claude Desktop-inspired composer slider for adjusting model reasoning effort with click, drag, or keyboard controls.

Windows x64 bundle with the official Antigravity CLI, using agy acp and cached CLI login. Delegates one-shot text tasks with selectable authentication, model and thinking level; uses host peers for Harness 0.2.1 from rc.3 and 0.2.2 from rc.1, including subsequent RCs and stable releases within both series.

Composer history that restores the whole input state: composer contents, image and file attachments, @ references and slash commands, plus the model, thinking effort, permission and agent preset used.

A session-header 3-dots menu: download the session log, switch each chat's transcript between Normal and Verbose, and define what Verbose expands (thinking blocks, tool calls, terminal output).

DSH model provider for Cohere — OpenAI-compatible wire by default, Cohere's native v2 lane for citations/RAG/thinking-budget. Direct wire adapter, no proxy.

Calm monochrome UI with lavender accents, startup and switching motion, a thinking workspace, scoped skills, and optional local voice and pet connections.