Change8

langchain==1.2.0

📦 langchainView on GitHub →
2 features🐛 4 fixes🔧 4 symbols

Summary

This release introduces a strict mode for structured outputs in ProviderStrategy and adds an extras field to BaseTool, alongside fixes for multithreading race conditions and HuggingFace model initialization.

✨ New Features

  • Added 'strict' flag to ProviderStrategy structured output for OpenAI and LangChain.
  • Added 'extras' field to BaseTool for Core and Anthropic integrations.

🐛 Bug Fixes

  • Fixed multithreading race condition in shell output.
  • Fixed helper logic for init_chat_model when using the HuggingFace backend.
  • Added sentinel value to ProviderStrategy/strict to improve reliability.
  • Resolved minor linting issues.

🔧 Affected Symbols

ProviderStrategyinit_chat_modelBaseToolShellTool