Changes since langchain-text-splitters==1.0.0
release(text-splitters): 1.1.0 (#34346)
feat(text-splitters): add R programming language support (#34241)
feat: Use uuid7 for run ids (#34172)
chore(cli,standard-tests,text-splitters): fix some ruff TC rules (#33934)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
style: more refs fixes (#33730)
chore(text-splitters): API reference link in README (#33713)
style: more refs work (#33707)
feat(infra): langchain docs MCP (#33636)
style: more refs work (#33616)
chore: update pyproject.toml url entries (#33587)
fix: support python 3.14 in various projects (#33575)
Changes since langchain-openai==1.1.2
test(openai): switch model from nano to mini when using flex (#34336) revert: make integration tests output verbose (#34329) chore(infra,openai): make integration tests output verbose (#34327) release(openai): 1.1.3 (#34325) fix(openai): correct image resize aspect ratio caps (#34192) refactor(standard-tests): improve VCR config (#33968) feat(openai): Use responses API if model is gpt-5.2-pro (#34306) fix(openai): handle missing 'text' key in responses API content blocks (#34198)
Changes since langchain-huggingface==1.1.0
release(huggingface): 1.2.0 (#34335)
fix(langchain-classic): fix init_chat_model for HuggingFace models (#33943)
fix(huggingface): Helper logic for init_chat_model with HuggingFace backend (#34259)
docs(fireworks,groq,huggingface,mistralai,ollama,openai): x-ref convert_to_openai_tool (#34276)
chore: update core dep in lockfiles (#34216)
Changes since langchain-mistralai==1.1.0
release(mistralai): 1.1.1 (#34334)
fix(mistralai): handle null content in tool call responses (#34268)
docs(fireworks,groq,huggingface,mistralai,ollama,openai): x-ref convert_to_openai_tool (#34276)
chore: update core dep in lockfiles (#34216)
Changes since langchain-groq==1.1.0
release(groq): 1.1.1 (#34332)
feat(groq): Allow kwargs in with_structured_output to override tool_choice (#34053)
refactor(standard-tests): improve VCR config (#33968)
chore(ollama,groq): Filtering Parameters in bind_tools for Ollama and Groq (#34167)
docs(fireworks,groq,huggingface,mistralai,ollama,openai): x-ref convert_to_openai_tool (#34276)
docs(core,groq,openai): nits for ref docs (#34243)
chore: update core dep in lockfiles (#34216)
Changes since langchain-tests==1.0.2
release(standard-tests): 1.1.0 (#34331)
chore(standard-tests): enable mypy disallow_any_generics rule (#34222)
refactor(standard-tests): improve VCR config (#33968)
feat(standard-tests): invocation model override (#34170)
feat(standard-tests): ensure only one chunk sets model_name in usage_metadata (#34224)
fix(standard-tests)!: remove deprecated has_tool_choice property (#34174)
docs(standard-tests): ensure first admonition is expanded (#34194)
docs(standard-tests): fix supports_json_mode docstring (#34181)
docs(standard-tests): fix formatting bug, rearrange admonition (#34180)
docs(standard-tests): enrich doc to indicate missing default values (#34179)
docs(standard-tests): improve doc for structured_output_kwargs and supports_json_mode (#34178)
fix(standard-tests): fix broken links (#34175)
fix(standard-tests): remove broken code block docstring title (#34173)
style(standard-tests): some fencing (#34171)
Changes since langchain-ollama==1.0.0
release(ollama): 1.0.1 (#34330)
test(ollama): Add unit test for ChatOllama reasoning parameter (#34095)
fix(ollama): pop unsupported 'strict' argument in ChatOllama (#34114)
docs(fireworks,groq,huggingface,mistralai,ollama,openai): x-ref convert_to_openai_tool (#34276)
chore: update core dep in lockfiles (#34216)
chore(docs): fix a few refs syntax errors (#34044)
chore: update README.md files (#33919)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
style: misc refs work (#33771)
chore: update pyproject.toml url entries (#33587)
Changes since langchain-anthropic==1.2.0
chore(anthropic): bump min core version (#34326)
release(anthropic): 1.3.0 (#34324)
chore(anthropic): make test agnostic of python version (#34320)
docs(anthropic): clean up docstrings (#34317)
docs(anthropic): nit comments (#34314)
feat(anthropic): accept TypedDict for built-in tool types (#34279)
refactor(standard-tests): improve VCR config (#33968)
refactor(anthropic): comments and _BUILTIN_TOOL_PREFIXES (#34305)
docs(anthropic): fix line number highlighting (#34303)
feat(anthropic): auto-apply mcp beta header (#34301)
docs(anthropic): use named betas param in docstring example (#34300)
docs(anthropic): cleanup nits (#34299)
chore(anthropic): update test_tool_search cassette (#34297)
fix(anthropic): ignore null values of caller on tool_use blocks (#34286)
feat(anthropic): support mcp_toolset in bind_tools (#34284)
feat(core,anthropic): extras on BaseTool (#34120)
feat(anthropic): document and test fine grained tool streaming (#34118)
feat(anthropic): use model profile for max output tokens (#34163)
feat(anthropic): auto append relevant beta headers for computer use (#34117)
feat(anthropic): tool search support (#34119)
feat(anthropic): add effort support (#34116)
chore: update core dep in lockfiles (#34216)
feat(anthropic): auto append relevant beta headers (#34113)
chore(anthropic): vcr integration test (#34160)
docs(anthropic,core,langchain): updates (#34106)
feat(langchain): support SystemMessage in create_agent's system_prompt (#34055)
Changes since langchain-core==1.1.3
release(core): 1.2 (#34319)
style(core): docs nit (#34312)
fix(core): widen openai tool/function conversion input type to Mapping (#34304)
chore(core): add admonitions around use of load (#34285)
feat(core,anthropic): extras on BaseTool (#34120)
Changes since langchain-chroma==1.0.0
release(chroma): 1.1 (#34316)
feat(chroma): Add Search API (#34273)
chore: update core dep in lockfiles (#34216)
fix(chroma): resolve OpenCLIP + Chroma image embedding test regression (#33899)
fix(chroma): pydantic validation error when using retriever.invoke() (#31377)
style: refs pass (#33813)
chore: update pyproject.toml url entries (#33587)
Changes since langchain-openai==1.1.1
release(openai): 1.1.2 (#34302)
fix(openai): Allow temperature when reasoning is set to the string 'none' (#34298)
feat(langchain,openai): add strict flag to ProviderStrategy structured output (#34149)
docs(fireworks,groq,huggingface,mistralai,ollama,openai): x-ref convert_to_openai_tool (#34276)
fix(openai): add missing tools param to ChatOpenAI with_structured_output (#34075)
Changes since langchain-core==1.1.2
release: langchain-core 1.1.3 (#34266) fix(core): undo jinja2 restrictions (#34072) fix: remove partial usage for retriever func + afunc (#34265)
Changes since langchain==1.1.2
release(langchain): 1.1.3 (#34255)
feat: add agent name to AIMessage (#34254)
chore(core): improve typing of messages utils functions (#34225)
feat(anthropic): add effort support (#34116)
feat(langchain): add support for Upstage (Solar) in init_chat_model (#34220)
Changes since langchain-openai==1.1.0
release(openai): 1.1.1 (#34252)
fix(openai): Fixing error that comes up using the Responses API with built-in tools and custom tools (#34136)
docs(core,groq,openai): nits for ref docs (#34243)
test(openai): mark test_structured_output_and_tools flaky (#34223)
chore: update core dep in lockfiles (#34216)
Changes since langchain-core==1.1.1
release(core): 1.1.2 (#34253)
fix(core): pass tool_call_id to on_tool_start callback (#34235)
chore(core): improve typing of messages utils functions (#34225)
fix(core): prevent async task garbage collection (RUF006) (#34238)
chore(core): use anext and deprecate py_anext (#34211)
feat(core): support google maps grounding in genai block translator (#34244)
docs(core,groq,openai): nits for ref docs (#34243)
docs(core): improve style for refs (#34227)
docs(core): update StrOutputParser docstring (#34213)
Changes since langchain==1.1.1
release: langchain 1.1.2 (#34210) fix: simplify summarization cutoff logic (#34195)
Changes since langchain==1.1.0
release: langchain 1.1.1 (#34206) feat: Use uuid7 for run ids (#34172) fix(langchain): (SummarizationMiddleware) adjust token counts based on model (#34161) docs(langchain): docstrings for summariziation middleware types (#34158) fix(langchain): add types to human_in_the_loop middleware (#34137) docs(anthropic,core,langchain): updates (#34106)