Rooms and Dialogue

Configure the room before running dialogue

The current web interface is centered on the default room. The backend also exposes room APIs, but creating a separate room through the API does not mean this page provides a room switcher. The template walkthrough uses those APIs explicitly.

The sidebar has three setup panels:

• 添加角色 — Create a character. Each character describes an AI role.
• 人设管理 — Define the user's persona: who you are playing.
• 世界观管理 — Supply world information, setting, and context.

None of these guarantees that a model will follow every instruction.

Variables and conditions

VARIABLES supports Room and Global scope, along with set, add, inc, and dec operations. Use numeric values when a condition expects numbers.

A variable like danger = 0 is stored state. It only affects the narrative when a world-information entry, behavior rule, or tool actually references it.

Conditions support these operators: exists, eq, ne, gt, gte, lt, lte, includes, and truthy. You can combine them with AND/OR grouping in configuration.

The visible room status and Active Branches panels help you inspect changes. An updated variable is not proof of a particular model response.

Enable model dialogue deliberately

The current source resolves provider credentials in this order:

1. Stored application settings
2. Environment variables
3. An existing Pi login file

Do not assume that omitting .env disables all provider access. Keep credentials out of scene templates and shared archives.

After selecting a supported provider/model and checking the context you intend to send:

• Use Speak for a single role turn.
• Use Commence Auto-Dialogue for automatic scheduling.

A new model message is the real success signal. An active button or connected socket alone is not. Use the stop control to end automatic scheduling before changing the setup or leaving the app.

When the Agent uses Ask, the ASK panel presents the pending question. Choose or enter an answer there to resume the interaction. A room waiting for an answer is not necessarily stalled. The exact question and continuation are model-dependent and were not live-provider tested for this guide.

Archive versus Compact

Archive captures a local snapshot that you can inspect and export.

Compact belongs to the conversation summarization workflow. Do not use it as a synonym for backup.

An archive can contain messages, persona, world information, and variables—review it before sharing. See Templates for a reusable setup with history omitted.