Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 15 Sep 2026
One change · claude-code

How the agent loop works changedagent-sdk/agent-loop

Nearest release: v2.1.273, published 2 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+2added
Lines−2removed
From line 198 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits29to this page, all time

The whole hunk

from line 198, old and new numbered
/
lines
from line 198
198198 
199199The budget cap covers [subagents](/docs/en/agent-sdk/subagents): their spend counts toward the total. Once spend reaches the cap, spawning another subagent fails with `Budget limit reached`, and Claude Code stops any background subagents still running. The cap-enforcement behaviors require Claude Code v2.1.217 or later.
200200 
201With [streaming input](/docs/en/agent-sdk/streaming-vs-single-mode), a message that is still queued when a turn ends at the max-turns limit stays queued. Claude Code doesn't add it to that turn's last model call. It starts a new turn for the message, and the max-turns count starts over for that turn.
201With [streaming input](/docs/en/agent-sdk/streaming-vs-single-mode), a message that is still queued when a turn ends at the max-turns limit stays queued. Claude Code doesn't add it to that turn's last model call. It starts a new turn for the message, and the max-turns count starts over for that turn. The budget total keeps accumulating across messages, and once spend reaches `maxBudgetUsd`, later messages in the same conversation end with the `error_max_budget_usd` result. A [`/clear`](/docs/en/agent-sdk/cost-tracking) starts the budget over.
202202 
203203### Effort level
204204 
from line 237
237237 
238238### Model
239239 
240If you don't set `model`, the SDK uses Claude Code's default, which depends on your authentication method and subscription. Set it explicitly (for example, `model="claude-sonnet-5"`) to pin a specific model or to use a smaller model for faster, cheaper agents. See [models](https://platform.claude.com/docs/en/about-claude/models) for available IDs.
240Set the `model` option to choose which model runs the session. For more information, see [Choose a model](/docs/en/agent-sdk/configuration#choose-a-model).
241241 
242242## The context window
243243 
Feedback