What's Changed since v0.3.3

• Add OpenAI and Claude thinking support - v0.4.0-rc.0 by @brainlid in https://github.com/brainlid/langchain/pull/297
• vertex ai file url support by @ahsandar in https://github.com/brainlid/langchain/pull/296
• Update docs for Vertex AI by @ahsandar in https://github.com/brainlid/langchain/pull/304
• Fix ContentPart migration by @mathieuripert in https://github.com/brainlid/langchain/pull/309
• Fix tests for content_part_for_api/2 of ChatOpenAI in v0.4.0-rc0 by @nallwhy in https://github.com/brainlid/langchain/pull/300
• Fix tool_calls nil messages by @udoschneider in https://github.com/brainlid/langchain/pull/314
• feat: Add structured output support to ChatMistralAI by @mathieuripert in https://github.com/brainlid/langchain/pull/312
• feat: add configurable tokenizer to text splitters by @mathieuripert in https://github.com/brainlid/langchain/pull/310
• simple formatting issue by @Bodhert in https://github.com/brainlid/langchain/pull/307
• Update Message.new_system spec to accurately accept [ContentPart.t()]… by @rtorresware in https://github.com/brainlid/langchain/pull/315
• Fix: Add token usage to ChatGoogleAI message metadata by @mathieuripert in https://github.com/brainlid/langchain/pull/316
• feat: include raw API responses in LLM error objects for better debug… by @TwistingTwists in https://github.com/brainlid/langchain/pull/317
• expanded docs and test coverage for prompt caching by @brainlid in https://github.com/brainlid/langchain/pull/325
• Fix AWS Bedrock stream decoder ordering issue by @stevehodgkiss in https://github.com/brainlid/langchain/pull/327
• significant updates for v0.4.0-rc.1 by @brainlid in https://github.com/brainlid/langchain/pull/328
• filter out empty lists in message responses by @brainlid in https://github.com/brainlid/langchain/pull/333
• fix: Require gettext ~> 0.26 by @mweidner037 in https://github.com/brainlid/langchain/pull/332
• Add retry: transient to Req for Anthropic models in stream mode by @jonator in https://github.com/brainlid/langchain/pull/329
• fixed issue with poorly matching list in case by @brainlid in https://github.com/brainlid/langchain/pull/334
• feat: Add organization ID as a parameter by @hjemmel in https://github.com/brainlid/langchain/pull/337
• Add missing verbose_api field to ChatOllamaAI for streaming compatibility by @gur-xyz in https://github.com/brainlid/langchain/pull/341
• Added usage data to the VertexAI Message response. by @raulchedrese in https://github.com/brainlid/langchain/pull/335
• feat: add run mode: step by @CaiqueMitsuoka in https://github.com/brainlid/langchain/pull/343
• feat: add support for multiple tools in run_until_tool_used by @fortmarek in https://github.com/brainlid/langchain/pull/345
• Fix ChatOllamaAI stop sequences: change from string to array type by @gur-xyz in https://github.com/brainlid/langchain/pull/342
• expanded logging for ChatAnthropic API errors by @brainlid in https://github.com/brainlid/langchain/pull/349
• Prevent crash when ToolResult with string in ChatGoogleAI.for_api/1 by @nallwhy in https://github.com/brainlid/langchain/pull/352
• Bedrock OpenAI-compatible API compatibility fix by @stevehodgkiss in https://github.com/brainlid/langchain/pull/356
• added xAI Grok chat model support by @alexfilatov in https://github.com/brainlid/langchain/pull/338
• Support thinking to ChatGoogleAI by @nallwhy in https://github.com/brainlid/langchain/pull/354
• Add req_config to ChatMode.ChatGoogleAI by @nallwhy in https://github.com/brainlid/langchain/pull/357
• Clean up treating MessageDelta in ChatModels.ChatGoogleAI by @nallwhy in https://github.com/brainlid/langchain/pull/353
• Expose full response headers through a new on_llm_response_headers callback by @brainlid in https://github.com/brainlid/langchain/pull/358
• only include "user" with OpenAI request when a value is provided by @brainlid in https://github.com/brainlid/langchain/pull/364
• Handle no content parts responses in ChatGoogleAI by @nallwhy in https://github.com/brainlid/langchain/pull/365
• Adds support for gpt-image-1 in LangChain.Images.OpenAIImage by @Ven109 in https://github.com/brainlid/langchain/pull/360
• Pref for release v0.4.0-rc.2 by @brainlid in https://github.com/brainlid/langchain/pull/366
• fix: handle missing finish_reason in streaming responses for LiteLLM compatibility by @fbettag in https://github.com/brainlid/langchain/pull/367
• Add support for native tool calls to ChatVertexAI by @raulchedrese in https://github.com/brainlid/langchain/pull/359
• Adds should_continue? optional function to mode step by @CaiqueMitsuoka in https://github.com/brainlid/langchain/pull/361
• Add OpenAI Deep Research integration by @fbettag in https://github.com/brainlid/langchain/pull/336
• Add parallel_tool_calls option to ChatOpenAI model by @martosaur in https://github.com/brainlid/langchain/pull/371
• Add optional AWS session token handling in BedrockHelpers by @quangngd in https://github.com/brainlid/langchain/pull/372
• fix: handle LiteLLM responses with null b64_json in OpenAIImage by @fbettag in https://github.com/brainlid/langchain/pull/368
• Add Orq AI chat by @arjan in https://github.com/brainlid/langchain/pull/377
• Add req_config to ChatModels.ChatOpenAI by @koszta in https://github.com/brainlid/langchain/pull/376
• fix(ChatGoogleAI): Handle cumulative token usage by @mweidner037 in https://github.com/brainlid/langchain/pull/373
• fix(ChatGoogleAI): Prevent error from thinking content parts by @mweidner037 in https://github.com/brainlid/langchain/pull/374
• feat(ChatGoogleAI): Full thinking config by @mweidner037 in https://github.com/brainlid/langchain/pull/375
• Support verbosity parameter for ChatOpenAI by @rohan-b99 in https://github.com/brainlid/langchain/pull/379
• add retry_on_fallback? to chat model definition and all models by @brainlid in https://github.com/brainlid/langchain/pull/350
• Prep for v0.4.o-rc.3 by @brainlid in https://github.com/brainlid/langchain/pull/380
• Use moduledoc instead of doc for LLMChain documentation by @xxdavid in https://github.com/brainlid/langchain/pull/384
• Support OTP 28 in CI by @kianmeng in https://github.com/brainlid/langchain/pull/382
• OpenAI responses by @vasspilka in https://github.com/brainlid/langchain/pull/381
• Add AGENTS.md and CLAUDE.md file support by @brainlid in https://github.com/brainlid/langchain/pull/385
• Suppress the compiler warning messages for ChatBumblebee by @brainlid in https://github.com/brainlid/langchain/pull/386
• fix: Support for json-schema in OpenAI responses API by @vasspilka in https://github.com/brainlid/langchain/pull/387
• Prepare for v0.4.0 release by @brainlid in https://github.com/brainlid/langchain/pull/388

New Contributors

• @ahsandar made their first contribution in https://github.com/brainlid/langchain/pull/296
• @mathieuripert made their first contribution in https://github.com/brainlid/langchain/pull/309
• @udoschneider made their first contribution in https://github.com/brainlid/langchain/pull/314
• @Bodhert made their first contribution in https://github.com/brainlid/langchain/pull/307
• @rtorresware made their first contribution in https://github.com/brainlid/langchain/pull/315
• @TwistingTwists made their first contribution in https://github.com/brainlid/langchain/pull/317
• @mweidner037 made their first contribution in https://github.com/brainlid/langchain/pull/332
• @jonator made their first contribution in https://github.com/brainlid/langchain/pull/329
• @hjemmel made their first contribution in https://github.com/brainlid/langchain/pull/337
• @gur-xyz made their first contribution in https://github.com/brainlid/langchain/pull/341
• @CaiqueMitsuoka made their first contribution in https://github.com/brainlid/langchain/pull/343
• @fortmarek made their first contribution in https://github.com/brainlid/langchain/pull/345
• @alexfilatov made their first contribution in https://github.com/brainlid/langchain/pull/338
• @Ven109 made their first contribution in https://github.com/brainlid/langchain/pull/360
• @martosaur made their first contribution in https://github.com/brainlid/langchain/pull/371
• @quangngd made their first contribution in https://github.com/brainlid/langchain/pull/372
• @arjan made their first contribution in https://github.com/brainlid/langchain/pull/377
• @koszta made their first contribution in https://github.com/brainlid/langchain/pull/376
• @rohan-b99 made their first contribution in https://github.com/brainlid/langchain/pull/379
• @xxdavid made their first contribution in https://github.com/brainlid/langchain/pull/384

Full Changelog: https://github.com/brainlid/langchain/compare/v0.3.3...v0.4.0