> ## 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.

# InputBuffer

> One inbound track's frames, read in process_input().

One inbound track's frames. Reached as `self.media.<track>`, and read in `process_input()`. Each
buffer holds the last 128 frames and drops the oldest when full, so a model that falls behind does
not grow memory without bound.

<ResponseField name="try_read(n=1, mode=ReadMode.LATEST)" type="list[InputFrame] | None">
  Return `n` frames, or `None` when fewer than `n` have arrived. Never waits, and consumes nothing
  when it returns `None`. This is the one to use inside `process_input()`: too few frames is a
  reason to skip the step.
</ResponseField>

<ResponseField name="await read(n=1, timeout=None, mode=ReadMode.LATEST)" type="list[InputFrame]">
  Wait until `n` frames are available, then return them. Raises `TimeoutError` if `timeout`
  elapses first. A wait inside `process_input()` holds the step, so keep this for a hand-written
  `run()`.
</ResponseField>

<ResponseField name="available" type="int">
  How many frames are buffered right now.
</ResponseField>

<ResponseField name="total_received" type="int">
  How many frames have arrived on this track since the session started.
</ResponseField>

<ResponseField name="closed" type="bool">
  Whether the track has closed.
</ResponseField>

<ResponseField name="clear()" type="None">
  Drop the buffered frames and leave the track open. The runtime does this for you when the last
  client leaves or the session ends.
</ResponseField>