Plugins

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

Replaces the composer model selector with a "model · reasoning level" trigger that opens a card holding the model-switch entry and a gradient particle slider for changing reasoning effort, and shows the model name alone when a model reports no reasoning levels.

Allows deepseek harness to think dynamically like human,automatically judge the difficulty of tasks with suitable thinking chain.

Pixel-font "deep seeking" thinking status with an animated DeepSeek blue whale (20 spout frames and 32 tail-wag frames).

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

A lightweight plugin that adds model thinking token statistics to the bottom Dock.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.

Interactive Side-Assistant Dock to ask quick side questions via /btw with real-time thinking status and history pagination without interrupting the active agent loop.

Raises Node's HTTP headers/body timeouts for the whole DSH process (default 30 min, proxy-aware) so Ollama and LM Studio models that stay silent while thinking or generating a large tool call are not cut off at 5 minutes; replaces the node_modules undici patch.

Ask a sidebar assistant about selected assistant text: an ephemeral right-side panel answers from a snapshot of the main conversation's LLM history with streaming Markdown, collapsible thinking and multi-turn follow-ups, without touching the main conversation.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Registers /wrapped, which reads the session's own stats and renders a shareable dark SVG summary card — tool vs. thinking time, decode speed, and a tool/thinking-ratio verdict.

During long agent thinking, posts a hot-news or reminder message directly into the conversation stream.

Rotates the model status line through a 53-phrase English/Chinese deep-theme pool: a random pick at turn start, event-driven switching on new thinking segments or tool calls (3s throttle), and a click on the status line toggles the language.

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

Animated DeepSeek blue-whale desktop pet floating on the DSH Web page: draggable with speech bubbles and mood poses, a pet_say tool for the model to make it talk, and turn-start/end thinking and celebrating states.

Folds each DSH Web turn's thinking, tool calls and context into bordered process boxes cut at every piece of model text; a collapsed box shows its latest two items, the stacked lines above its border open that one box, the border itself folds it back, and user dialogue, interactive questions and model text stay outside.

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

Adds AMD Radeon Cloud as a model provider in DeepSeek Harness, with reasoning-effort levels declared per model. The provider definition ships in the plugin's own patch layer rather than in your profile.

Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.