@ai-sdk/[email protected]
@ai-sdk/[email protected]
ai
Release Notes
Patch Changes
4241b49: fix(anthropic): forward
thinking: { type: 'disabled' }to the API instead of stripping itPreviously, setting
providerOptions.anthropic.thinking = { type: 'disabled' }was accepted by the schema but silently dropped from the outgoing request. For models that default thinking on (e.g. Sonnet 5), this left thinking enabled and could consume a smallmax_tokensbudget entirely. Thedisabledvalue is now sent to the Anthropic Messages API.