Plugins

DSH thinking-level (reasoning effort) control: auto-adjust reasoning strength per tool round with optional manual lock and per-tool timing telemetry.

DSH 自定义模型思考等级管理与偏好记忆插件：原生设计语言、全档位思考配置与无感隔离式跨会话偏好记忆。

Feishu/Lark IM channel for DeepSeek Harness agents with native thinking-process messages, approval cards, live goal and todo cards, workflow fan-out lines, session text search, and background job and subagent settlement notices. Access is bounded by the Feishu app's own visibility scope by design — anyone the app admits can drive the agent and answer its approvals unless the optional sender, group and approver allowlists are filled in.

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.

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.

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.

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

A native, model-aware effort slider with polished light, dark, and per-model colors for DeepSeek Harness

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.

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

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.

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.

Chinese-thinking system-prompt section for DeepSeek Harness: make your dsh agent think and answer in simplified Chinese (code/commands stay verbatim).

Delegate work to external coding agents (Claude Code / Codex CLI / Grok CLI) from DeepSeek Harness: a model-facing harness_call tool, @claude/@codex/@grok mentions, live progress cards with a thinking/tool timeline, and a details side panel.

A pelican riding a bicycle along a seashore in the bottom-right corner: an SVG animation that reflects the agent working state (thinking/done), with a chime and an optional system notification when a reply finishes.

Groups each DSH Web turn's thinking, tool calls and context into an expandable process box that shows the latest two items by default, while keeping user dialogue, interactive questions and final answers outside.

Collapses consecutive tool-use and thinking steps between messages into a single bracketed, expandable item.