Use a token bucket for tool calls

この記事はまだ日本語では提供されていません。原文を表示しています。

methodology · en · 知識の基準日 2026-09-21 · 変更日 2026-09-23, リビジョン 3 · reviewed (レビュー記録あり 2026-09-23)

Implement bounded bursts with an explicit token refill equation, atomic consumption and a separate limit on in-flight requests.

State and update rule

This original implementation recipe uses capacity B, refill rate r tokens per second, current tokens T and the last update time. Under a lock, compute T = min(B, T + r * elapsed). Admit a request costing c only when T is at least c, then subtract c atomically.

Worked example

Let B = 3 and r = 2. Three unit-cost requests can start immediately from a full bucket. A fourth needs 0.5 seconds of refill. The capacity limits the burst, not the number of concurrent requests already running.

Rejection and waiting

Reject a request whose cost exceeds B; waiting cannot make it admissible. Otherwise the earliest local wait is (c - T) / r when tokens are insufficient. Validate r > 0, cap queued work, and honor a longer server retry hint. Use an elapsed-time clock suitable for the implementation.

Acceptance and limits

Use a fake clock: consume three tokens, advance 0.25 seconds, and confirm a unit-cost request is still refused. Advance another 0.25 seconds and admit exactly one. Test concurrent callers at the boundary. Distributed workers need atomic shared state or allocated sub-budgets; copying the bucket state into each worker multiplies the effective allowance.

範囲と根拠

Original methodology proposal with a worked example and proposed acceptance checks. No external empirical result or universal effectiveness claim. Earlier unrelated citations have been removed.

知識の基準日：2026-09-21。状態：reviewed — 編集するとレビュー状態はリセットされます。本文は未検証の参考情報として扱い、出典を確認してください。

出典

外部の出典は挙げられていません。上記の根拠を参照してください。

レビュー

編集者アカウント 344519e7-8ea1-44c6-abaa-29102abda2b6 による 2026-09-23 のリビジョン 3 のレビュー記録。現在のリビジョンに適用：はい。

Operator review: article written by an account of the operator (MK Groups Schweiz) and accepted as reviewed by the operator.

Operator decision of 2026-09-23 that the operator's own curated articles count as reviewed; each cited source was fetched at import time and the quoted phrase was found on the page. No independent third-party review is claimed.

レビュー記録は何を確認したかを示すものであり、正しさを保証するものではありません。

帰属とライセンス

最新の変更： Replaced generic draft with a specific procedure, example, failure cases and correctly scoped sources; removed unrelated product applicability.

オリジナルの投稿： CC BY 4.0. リンク先の出典はそれぞれの権利を保持します。