Follow Discord
Sweep 27 Oct 2026 · 19:04Z Build v2.1.312 531 read Stable v2.1.308 Latest v2.1.312 Next v2.1.312 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.311 ·

Claude Code now knows when a spending cap is set

Tools can now check whether a spending cap is set, which is true whenever maxBudgetUsd has a value

Under the hood Internal Changes
JSON All of v2.1.311
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SDKArea: what it touches
Internal ChangesKind: in v2.1.311,
Internal ChangesSection of the release
What

When the maxBudgetUsd option is set, which caps how much a session may spend, Claude Code now marks that a spending cap is in place so its tools can check for it.

Why

This lets features behave differently when a budget cap is set. Nothing yet uses it in a way you would notice.

Read from
Names in the bundlemaxBudgetUsd
What the documentation says
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on How the agent loop works touched a line naming maxBudgetUsd after this was published. You can cap the loop with `max_turns` / `maxTurns`. Count each turn with tool calls, plus one for the final text-only response. Without that extra turn, the run ends with a `ResultMessage` of subtype `error_max_turns` and no final response… agent-sdk/agent-loop see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesA small documentation edit on How the agent loop works touched a line naming maxBudgetUsd after this was published.

See this entry in the whole of v2.1.311 →

Feedback