Skip to main content
Capture is what makes everything downstream possible. Without recorded traffic there is no evidence for a route change and no corpus to train from. It is decided per workload, with a sample rate, and it is on by default for a new workload.

​
What is recorded

Two layers. Metadata is recorded for every request, whether or not the workload is capturing: The full request and response bodies are stored only when the workload is capturing and the request falls inside the sample rate.
Metadata is what powers per-workload cost and latency reporting, so those keep working with capture off. What you lose is the ability to replay a candidate model against real traffic, which is the evidence a route change needs.

​
Sampling

The sample rate is a fraction from 0 to 1, applied deterministically per request ID. The same request is either always captured or never captured; it does not flip between retries of the same call. A high-volume workload rarely needs everything. What matters is coverage of the input shapes you actually see, and a 10% sample of a million calls has that.

​
Turning it off

Set capture off for the workload. Metadata continues; bodies stop.
The setting is cached on the request path, so a toggle can take up to 60 seconds to take effect. It is a recording switch, not a kill switch. If you need a hard guarantee for a specific call, do not send it through a capturing workload in the first place.
If the settings store is unreachable the gateway fails capture-on. Losing traces silently is the worse outcome, because you cannot tell afterwards that they were lost.

​
What it is used for

Cost per workload

Which call sites actually spend the money, which is rarely the one people guess.

Routing evidence

Candidate models are replayed against captures, not against your live traffic.

Failures

The calls that went wrong, which is what a training run needs.

Training corpus

A workload that cannot route down becomes a candidate for its own model.