Serving Gate a Rollout on Version Readiness

Serving Gate a Rollout on Version Readiness

Wait for a model version to load, confirm its signature, and smoke test it.

1. Poll the version's status until the ModelServer reports AVAILABLE. The newly exported version is commonly in the LOADING state for the first few seconds after export, so the check is retried rather than failed on the first look.
2. Read the loaded version's metadata to confirm the training pipeline exported the signature the serving clients expect, catching an export that loaded cleanly but has the wrong shape.
3. Send the smoke test input to the pinned version. A successful prediction is the signal that the rollout may proceed; anything else should hold it.

What you'll need to have ready

• modelName: The name the model was registered under in the ModelServer.
• version: The version number of the freshly exported model to gate on.
• signatureName: Optional signature the smoke test should target.
• smokeInstances: A small, known input whose prediction is cheap to sanity check. This is a liveness check on the exported version, not an accuracy evaluation.

For your developer

Arazzo workflow tensorflow:rollout-readiness, 3 operations: getModelVersionStatus → getModelVersionMetadata → predictModelVersion. Specs on APIs.io.