Checked fact 124012 Oct 2026Agents and apps

The documentation says the loop can be capped with a maximum number of tool-use turns or with an estimated spend in US dollars, and that spend can pass the budget cap by up to the cost of the response that reaches it.

Toned down to what the source says

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

You can cap the loop with max_turns / maxTurns, which counts tool-use turns only. ... You can also use max_budget_usd / maxBudgetUsd to cap turns based on a spend threshold. ... Max budget (max_budget_usd / maxBudgetUsd) | Estimated spend at which the loop stops ... Spend can therefore pass the cap by up to the cost of that one response

What the source said when we opened it, on 12 Oct 2026.

The source

How the agent loop works
Claude Code documentation

Open the source archived copy

Checked

Checked by the notis newsroom on 12 Oct 2026, against the source above.

In the story

How an agent harness runs a model and enforces limits 12 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The documentation says the loop can be capped with a maximum number of tool-use turns or with an estimated spend in US dollars, and that spend can pass the budget cap by up to the cost of the response that reaches it.” ai notis, checked 12 Oct 2026. Source: How the agent loop works (Claude Code documentation). https://ainotis.com/c/1240

As a reference (APA style)

ai notis. (2026, October 12). The documentation says the loop can be capped with a maximum number of tool-use turns or with an estimated spend in US dollars, and that spend can pass the budget cap by up to the cost of the response that reaches it [Checked claim 1240]. ai notis. https://ainotis.com/c/1240

Anyone may quote this address. It does not change; if we correct the story, this page says so.