[Release] langchain-ai/langchain langchain-anthropic==1.5.0: langchain-anthropic==1.5.0

langchain-anthropic version 1.5.0 introduces support for `reasoning_effort` as a standard chat model parameter, enabling more granular control over Claude's reasoning capabilities. The release includes fixes for tool recognition with the `advisor_` prefix, improved documentation following Sonnet 5 release, and various dependency updates. Key improvements focus on enhancing the Anthropic integration's compatibility with extended thinking features and maintaining consistency across the LangChain ecosystem.

Key Points

• •Added `reasoning_effort` as a standard chat model parameter for fine-grained control over Claude's reasoning behavior
• •Fixed tool recognition by adding `advisor_` prefix handling to builtin tool detection
• •Updated docstrings and documentation to reflect Sonnet 5 model release
• •Refreshed model profile data to ensure accurate model capability information
• •Updated dependencies across multiple directories with 11 minor and patch version bumps
• •Fixed VCR cassette handling to properly ignore LangSmith requests during testing
• •Improved test reliability and consistency in the Anthropic integration layer

Workflow Diagram

Concepts