What's Changed

• Add req_config to ChatOpenAIResponses by @xxdavid in https://github.com/brainlid/langchain/pull/415
• Add thinking config to vertex ai by @mattmatters in https://github.com/brainlid/langchain/pull/423
• Add support for OpenAI Response API Stateful context by @cjimison in https://github.com/brainlid/langchain/pull/425
• Fixes image file_id content type for ChatOpenAIResponses by @sezaru in https://github.com/brainlid/langchain/pull/438
• fix(ChatMistralAI): missing error handling and fallback mechanism on server outages (#434) by @xu-chris in https://github.com/brainlid/langchain/pull/435
• feat(ChatMistralAI): add support for parallel tool calls by @xu-chris in https://github.com/brainlid/langchain/pull/433
• use elixir 1.17 by @nbw in https://github.com/brainlid/langchain/pull/427
• feat(GoogleChatAI): add thought_signature support for Gemini 3 function calls by @abh1shek-sh in https://github.com/brainlid/langchain/pull/431
• Don't include top_p for gpt-5.2+ in ChatOpenAIResponses by @montebrown in https://github.com/brainlid/langchain/pull/428
• Fix Mistral 'thinking' content parts by @arjan in https://github.com/brainlid/langchain/pull/418
• Add verbose_api field to ChatPerplexity and ChatMistralAI by @arjan in https://github.com/brainlid/langchain/pull/416
• Add support for OpenAI reasoning/thinking events in ChatOpenAIResponses by @arjan in https://github.com/brainlid/langchain/pull/421
• Add new reasoning effort values to ChatOpenAIResponses by @xxdavid in https://github.com/brainlid/langchain/pull/419
• fix "Support reasoning_content of deepseek model" introducing UI bug … by @kayuapi in https://github.com/brainlid/langchain/pull/429
• Support json schema in vertex ai by @mattmatters in https://github.com/brainlid/langchain/pull/424
• Base work for new agent library by @brainlid in https://github.com/brainlid/langchain/pull/442
• fix ChatGrok tool call arguments and message flattening by @KristerV in https://github.com/brainlid/langchain/pull/420
• Revert "fix ChatGrok tool call arguments and message flattening" by @brainlid in https://github.com/brainlid/langchain/pull/445
• prep for v0.5.0 release by @brainlid in https://github.com/brainlid/langchain/pull/451

New Contributors

• @cjimison made their first contribution in https://github.com/brainlid/langchain/pull/425
• @sezaru made their first contribution in https://github.com/brainlid/langchain/pull/438
• @xu-chris made their first contribution in https://github.com/brainlid/langchain/pull/435
• @nbw made their first contribution in https://github.com/brainlid/langchain/pull/427
• @abh1shek-sh made their first contribution in https://github.com/brainlid/langchain/pull/431
• @kayuapi made their first contribution in https://github.com/brainlid/langchain/pull/429
• @KristerV made their first contribution in https://github.com/brainlid/langchain/pull/420

Full Changelog: https://github.com/brainlid/langchain/compare/v0.4.1...v0.5.0