> ## 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 video model catalog — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. Robotics policy documentation starts at /robotics/overview; X-WAM observations, actions, and client integration are under /robotics/xwam/; Cosmos3 Nano Policy DROID is under /robotics/cosmos/nano-policy-droid/. 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.

# Troubleshooting

> Diagnose missing predictions, checkpoint selection, and controller mismatches.

| Symptom | Check |
| - | - |
| HTTP 429 with `no available capacity` | No worker is available. Retry later; this is separate from request validation. |
| No prediction | Confirm a nonempty instruction, eight finite state values, and a newly delivered frame on every track after the request. |
| Resending produces no reply | Byte-identical `state_json` is deduplicated. A changed retry field requests fresh inference. |
| Checkpoint selection rejected | Inspect `command_error` and `get_checkpoint`. Choose from `available` before the first prediction; a different pinned choice requires a new session. |
| No new reply after reset | Reset retains the existing input value without answering it again. Send new state JSON and keep publishing frames. |
| Wrong reply reaches the controller | Match `step` to the outstanding request and consume each logical request once. |
| Robot motion looks incorrect | Confirm absolute joint targets in radians, correct joint order, and gripper `0` open / `1` closed. |
| Timing is worse than `inference_seconds` | That field excludes transport and execution queues. Measure capture-to-execution latency separately. |

For support, provide the model slug, session ID, selected checkpoint, command/error names, state
shape, and timestamps. Do not include API keys. Contact [Reactor](mailto:team@reactor.inc).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.