@ai-sdk/anthropic
4.0.106 · 17 Nov 2026Apache-2.024.5M / weekRepositoryHomepagenpmAtom feed
Upgrading @ai-sdk/anthropic From 3.0.90 to 3.0.143
51 releases in betweenevery note read
Reading releases, release notes and advisories…
Security
- 3.0.94
Prevent prototype pollution when synchronously parsing provider JSON inputs and expose
secureJsonParsefrom provider-utils.
Release by release
3.0.142 – 3.0.1432 releases, nothing new or fixed in the notes
- Fixed
Disable MCP connector tools when structured output falls back to the JSON response tool and the caller selects no tools or a named application tool, and when a named application tool choice falls back to automatic tool selection.
- Fixed
- New
anthropic: Support adding tools by value in mid-conversation
toolChanges(inline-tools-2026-09-15) - Fixed
Reject conflicting inline tool additions when a named tool choice falls back to auto or the internal JSON response tool limits available application tools, including definitions replayed from conversation history. Only validate definitions emitted in the request, preserving warning-only handling of ignored additions on the initial system message.
- New
- New
Enable native structured output and strict tools for supported Claude 5 models on Bedrock. In automatic mode, Bedrock and Anthropic now fall back for schemas that native structured output cannot represent: recursive references, open objects, or more than ten optional properties. Anthropic uses the JSON response tool; Bedrock Converse uses the JSON tool or JSON instructions for models that reject forced tool use. The JSON-tool fallback excludes disabled and unselected application tools. Explicit
outputFormatselection remains unchanged. - Fixed
anthropic: Parse valid JSON string tool input and safely serialize BigInt and cycles in tool results
- New
- Fixed
anthropic: Use native structured outputs for Claude models that reject forced tool use (Sonnet 5.5, Opus 5.5, Fable 5.1) even when the provider disables them by default, as Amazon Bedrock and Google Vertex do. Self-referencing schemas keep the JSON response tool. Also keep
definitionsand$defsnext to a top-level$refwhen sanitizing structured output schemas, so the reference still resolves. - Fixed
anthropic: When the JSON response tool is in use but the model answers in text without calling it (for example with manual thinking, where the forced tool choice is downgraded to
auto), return the final answer text instead of dropping it. Text before a tool call, result, or message continuation is still dropped. - Fixed
anthropic: Keep the JSON response tool for schemas that native structured outputs cannot represent when upgrading models that reject forced tool use. Schemas with open objects (maps, free-form objects) would otherwise come back as
{}, and schemas with more than 10 optional properties can be rejected as too complex.
- Fixed
3.0.136nothing new or fixed in the note
- Fixed
Defer validation schema construction until first use to reduce provider import time.
- Fixed
Defer construction of Anthropic provider option schemas until they are first used to reduce package import time.
- Fixed
- New
Add MiniMax M3.1 Flash support with reasoning effort, image detail, video input and frame sampling, prompt cache control, and sampling controls.
- New
35 internal lines (docs, tests, tooling) left out.
A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.