> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reactor.inc/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> To build and serve your own model, start at /deploy/development/quickstart and /deploy/development/overview. Deploying is the default path: reactor init scaffolds a workspace, reactor auth login authenticates, and reactor model deploy registers the model, publishes the release with the weights/ folder, and activates it on Reactor's GPUs, in one command from that workspace. Docker must be running, because the publish step builds the image locally. Bump model.version in reactor.yaml before redeploying a change, because a release that already has an image is reactivated as it is. Deployment access is granted per account, so contact team@reactor.inc if a deploy is refused. Every key in reactor.yaml is documented at /deploy/platform/reactor-yaml. Model code imports reactor_runtime; Python client code imports reactor_sdk. The runtime overview explains the model interface. Running the model on your own machine with reactor run is optional and needs a GPU you attach with --gpus; /deploy/development/local-testing covers that loop and pairs a complete brightness model with a Python client test in a separate brightness-test workspace.
> Reactor hosts multiple models, each with its own connect slug (modelName) and command/event schema. The catalog of every model — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. Some models expose one slug per experience (e.g. HappyOyster); always take the slug from the model's own pages, never guess it.
> Fastest path to a working app: `npx create-reactor-app my-app --model=<slug>` scaffolds a complete app with secure auth wired up. Typed TypeScript SDKs are published as @reactor-models/<model>; Python uses the base reactor-sdk package.
> Auth: exchange an API key (rk_...) for a JWT via POST https://api.reactor.inc/tokens from your server. Never put the API key in client-side code.
> Append .md to any docs URL for clean Markdown. Search these docs via the MCP server at https://docs.reactor.inc/mcp.

# ModelMessage

> Base for a typed message from the model to its clients.

Base for a typed message from the model to its clients. Subclass it and declare fields like a
dataclass:

```python theme={"theme":{"light":"github-light","dark":"github-dark-high-contrast"}}
class Progress(ModelMessage):
    """Sent every 20 chunks while a rollout runs."""

    chunk: int
    total: int = MessageField(default=100, description="Chunks in the full run.")
```

The client receives `{"type": "progress", "data": {"chunk": 3, "total": 100}}`. The wire type is
the snake\_case form of the class name. The class docstring documents the message in the published
schema. A message with no fields is valid and is
the right shape for a pure signal.

Send one to every connected client with `await self.send(message)`, or to a single client with
`await client.send(message)`. Returning one from an `@event` handler makes it that command's
correlated reply. See [Events & Messages](/deploy/development/reactor-app/events-and-messages).