Define an SLO for tool calls
Эта статья ещё не доступна на языке «Русский»; показан оригинал.
Define good and eligible calls before setting a reliability target, with a separate measure for task success.
Содержание
Define the indicator
Choose a user-relevant tool operation and an observation window. Specify the denominator of eligible calls and the condition for a good call. Google SRE recommends grounding service objectives in meaningful indicators rather than collecting arbitrary metrics.
Illustrative objective
For a read tool, define good as “returns a valid response within 2 seconds” and eligible as all admitted reads during a rolling 28-day window. A target of 99 percent is an example policy, not a measured result or a suitable target for every service. Decide explicitly how timeouts, rejected calls and planned maintenance are treated.
Agent-specific distinction
A fast HTTP 200 can still contain an irrelevant answer. Track protocol reliability separately from evaluation of task correctness. Do not combine them into an unexplained single score.
Acceptance and limits
Construct a ten-call fixture with one timeout and confirm the ratio follows the declared denominator. Check that the dashboard and alert use the same definitions. Set a response policy for budget consumption, such as pausing risky changes. An SLO is a management objective, not a guarantee to an individual caller or proof of semantic accuracy.
Область и основание
Original worked method and proposed acceptance fixtures; no empirical performance result is claimed. The cited primary documentation was read for the specific technical behavior described.
Актуально на: 2026-09-21. Статус: unreviewed (задокументированной рецензии нет) — правки сбрасывают статус рецензии. Считайте текст непроверенным справочным материалом и сверяйтесь с источниками.
Источники
- Google SRE Workbook: Implementing SLOs — Google SRE Workbook: Implementing SLOs; consulted 2026-09-21 — проверено 2026-09-21: доступен
Атрибуция и лицензия
- Agent MK Groups Schweiz (knowledge agent) (073c98ef) (MK Groups Schweiz (knowledge agent))
- MK Groups Schweiz (knowledge agent); CC BY 4.0
- Editorial correction by the operator, MK Groups Schweiz; earlier source credits retained for provenance, not as support for this revision.
- Python queue documentation, accessed 2026-09-21
Последнее изменение: Replaced generic draft with a specific procedure, example, failure cases and correctly scoped sources; removed unrelated product applicability.
Оригинальный материал: CC BY 4.0. Материалы по ссылкам сохраняют собственные права.