> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features.md).

# 功能

功能是该 SDK 的 AI 驱动能力模块。每个功能都连接到 Convai，用于特定目的——执行场景内行为、表达情绪、跨会话记住用户、遵循叙事图，或通过摄像头看见世界。每个功能都有专用的模块系统、ScriptableObject 配置文件，以及其自己的 Convai 集成。

选择一个功能开始：

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>动作</strong><br>让角色执行场景内行为——移动、拾取、播放动画、触发事件——以响应自然语言指令。</td><td><a href="/pages/48542e3f43c9fa4320574cae5c541c172f781a1d">/pages/48542e3f43c9fa4320574cae5c541c172f781a1d</a></td></tr><tr><td><strong>动态上下文</strong><br>将实时运行时状态——环境条件、玩家状态、模拟事件——在对话中直接输入角色的感知。</td><td><a href="/pages/eb13f9c057b5d7a65a7d8338048c0f7def05d5cf">/pages/eb13f9c057b5d7a65a7d8338048c0f7def05d5cf</a></td></tr><tr><td><strong>场景元数据</strong><br>自动将场景对象注册到 Convai，让角色无需手动注入上下文就能理解周围的物理世界。</td><td><a href="/pages/3e23af730226f449644f6a9c60f206a69124eb0e">/pages/3e23af730226f449644f6a9c60f206a69124eb0e</a></td></tr><tr><td><strong>长期记忆</strong><br>让角色具备跨会话记忆——他们会随着时间记住单个用户、事实和过往互动。</td><td><a href="/pages/619185ebc41c18d7fc15c71b6aaa2a22367ff0a6">/pages/619185ebc41c18d7fc15c71b6aaa2a22367ff0a6</a></td></tr><tr><td><strong>多角色会话</strong><br>在一个共享房间中运行多个角色，并控制玩家在任意时刻正在与哪个角色交谈。</td><td><a href="/pages/f76eaea2a343c7d72b93487d582ec00dd7ba1c58">/pages/f76eaea2a343c7d72b93487d582ec00dd7ba1c58</a></td></tr><tr><td><strong>叙事设计</strong><br>围绕作者创建的故事图构建对话，并通过基于章节的行为变化和触发器驱动的进程推进剧情。</td><td><a href="/pages/892f091d719fc0313f9c15cd06a5133939efee0e">/pages/892f091d719fc0313f9c15cd06a5133939efee0e</a></td></tr><tr><td><strong>视觉</strong><br>将场景摄像头或网络摄像头的实时视频流传输到 Convai，使角色能够看见并响应实时视觉输入。</td><td><a href="/pages/b40605131fc22d0b4a7a0e62e0e97c744ec19d0e">/pages/b40605131fc22d0b4a7a0e62e0e97c744ec19d0e</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.