Skip to main content

​
Description

Deploy (or roll back to) an already-published release. The release must already exist - run reactor model publish first to register the release tag and push the image (and optionally the weights). Use this command to:
  • Activate a freshly published release when it is ready for traffic.
  • Roll back to an older release if the current one has issues.
Weights: If the release has no weights of its own, the deploy reuses the most recently deployed release’s weights (server-side, no upload). When neither the release nor any previously deployed release has weights, the deploy still succeeds and prints a warning to upload them with reactor weights upload. Workspace-aware: When run from a workspace (any directory under one containing a reactor.yaml, stopping at the enclosing repository root) with no positional argument, the model name and release tag are taken from the file’s model.name and model.version fields. An explicit <model>:<release> on the command line can override the workspace release tag - use it for rollbacks to an earlier release - but its <model> part must match the workspace model.name or the command is rejected. Strategy: By default a deploy replaces instances one at a time, so the model keeps serving throughout. --strategy replace-all signals the whole old generation at once: an idle fleet turns over in seconds, and a busy one runs at reduced capacity until the fresh instances finish loading. Under both, an instance still serving a session keeps serving it until the session ends or the instance’s grace period runs out, which is up to five minutes in production. Immediate (emergency cutover): --immediate cuts that tail. After signalling the rollout, the platform disconnects the model’s live sessions so the new release takes over in seconds instead of minutes. Reach for it when the running release must stop serving now (a bad version, a safety problem), not for routine deploys. It implies --strategy replace-all (spelling the strategy out is fine; any other strategy is an error). It terminates whatever sessions are live when the sweep runs, including ones that started during the deploy. Two overlapping deploys, or a retry, each disconnect the then-live set. Clients are told the model was redeployed where their session’s release supports it; on older releases they see a plain disconnect. Their sessions end either way. --yes skips the confirmation prompt for scripts and CI. Examples:

​
Options

​
Global options

​
See also