Tessary
Tessary cost drift
cost_drift is one of Tessary's built-in classifiers: a tripwire that watches each call site's spend against its own past. It tracks dollars per turn, with token counts attached as evidence.
It catches the quiet ways an agent gets more expensive: a prompt that grew, retries that multiplied, caching that stopped working. Comparisons run against the call site's own history, both its recent normal and a reference pinned at the last deploy, so sudden jumps and slow creep both register. A drop in cost shows up as clearly as a rise. Findings go to triage, where the ones ruled real issues open cases.
6 questions
Answered, plainly.
Can cost_drift catch a cost that creeps up slowly, not just a sudden spike?Yes. It checks a rolling recent baseline that catches sudden jumps and one pinned at the last deploy that catches the creep the rolling one absorbs.answer →Does cost_drift work for a scheduled agent that has no user sessions?Yes. cost_drift tracks dollars per turn at the call site, not per user session, so a scheduled job's runs build a baseline the same way.answer →Is cost_drift turned on by default?Yes. cost_drift is one of three classifiers Tessary calls deterministic and turns on by default, alongside duration_drift and tool_error.answer →How do I tell traffic growth apart from a broken agent in my LLM bill?Look at dollars per turn, not total spend: growth adds turns at the same per-turn price and leaves the ratio flat, while a defect moves the ratio.answer →What is Tessary's cost_drift classifier?cost_drift is a built-in classifier that watches a call site's dollars per turn against its own history to catch quiet cost increases.answer →Why does each turn get pricier as an agent's run goes on?Each step's tool output and reasoning gets carried into the next call's prompt, so input tokens climb turn over turn even if the task stays the same.answer →