Can cost_drift catch a cost that creeps up slowly, not just a sudden spike?

Yes. cost_drift compares each call site against two references at once: a rolling recent normal, which catches a jump, and one pinned at a known-good point that only a person moves, which catches the creep the rolling one absorbs.

The cost-specific case is a prompt that grows a little each release. No single deploy looks expensive, and the pinned reference is what notices the sum.

The mechanism is the same one duration_drift uses for a gradual slowdown.

keep reading

More on this.

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y