langchain-core==0.3.81

Changes since langchain-core==0.3.80

release(core): 0.3.81 (#34459)
fix(core): serialization patch (#34458)

langchain-classic==1.0.1

Changes since langchain-classic==1.0.0

release(langchain-classic): 1.0.1 (#34467)
fix(core): serialization patch (#34455)
feat(langchain): enhance init_chat_model with improved validation (#34226)
feat(langchain): Add support to google_genai provider in init_embeddings (#34388)
docs: Fix typo in Zapier NLA API description (#34424)
release(core): 1.2.3 (#34421)
release(openai): 1.1.6: update max input tokens for gpt-5 series (#34419)
release(openai): 1.1.5 (#34409)
feat(infra): add CI check for out of date lockfiles (#34397)
fix(huggingface): Helper logic for init_chat_model with HuggingFace backend (#34259)
feat(core,anthropic): extras on BaseTool (#34120)
feat(anthropic): add effort support (#34116)
feat: Use uuid7 for run ids (#34172)
chore: disable blockbuster for langchain-classic (#34186)
style(core,langchain,qdrant): fix some docstrings for refs (#34105)
fix(core): Decouple provider prefix from model name in init_chat_mode… (#34046)
style(core,langchain-classic,openai): fix griffe warnings (#34074)
chore(docs): fix a few refs syntax errors (#34044)
chore: update README.md files (#33919)
chore(langchain): pass on reference docstrings (middleware) (#33904)
docs(langchain): correct IBM provider link in chat_models docstring (#33897)
refactor(langchain): use create_importer for HypotheticalDocumentEmbedder (#32078)
docs: fix typos in libs/langchain/langchain_classic/chains/summarize/chain.py (#33877)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
fix(langchain): remove Tigris (#33829)
chore: correct langchain-community references (#33827)
style: refs pass (#33813)
style: misc refs work (#33771)
chore: use model IDs, latest anthropic models (#33747)
chore(langchain): fix lint_imports paths (#33749)
style: more refs fixes (#33730)
style(core): more cleanup all around (#33711)
style: more refs work (#33707)
fix: links (#33691)
docs(langchain): clarify create_tool_calling_agent system_prompt formatting and add troubleshooting (#33679)
fix: update some links (#33686)
fix(langchain): correctly initialize huggingface models in init_chat_model (#33167)
style: even more refs work (#33619)
style: more refs polishing (#33601)

langchain-core==1.2.5

Changes since langchain-core==1.2.4

release(core): 1.2.5 (#34456)
fix(core): serialization patch (#34455)
fix(core): RunnablePick method return types (#34208)
fix(core): preserve Field(description=...) in @tool decorator (#34354)
fix(core): populate default args from tool's args_schema (#34399)
fix(core): use tool_calls instead of deprecated function_call in get_buffer_string (#34355)
feat(core): add PEP 702 __deprecated__ attribute support to @deprecated (#34257)
fix(core): ensure tool_call_count is never null (#34431)
feat(core): automatically count and store meta for tool call count (#33756)
feat(core): add 'approximate' alias in place of count_tokens_approximately (#33045)
chore(core): fix some ruff preview rules (#34425)

langchain-core==1.2.4

Changes since langchain-core==1.2.3

release(core): 1.2.4 (#34429)
feat(core): add usage_metadata to metadata in LangChainTracer (#34414)
fix(core): defer persisting traces for iterator inputs (#34416)
chore(core): fix some docstrings (#34426)

langchain-openai==1.1.6

Changes since langchain-openai==1.1.5

release(openai): 1.1.6: update max input tokens for gpt-5 series (#34419)

langchain-core==1.2.3

Changes since langchain-core==1.2.2

release(core): 1.2.3 (#34421)
fix(core): allow unknown blocks in convert_to_openai_messages (#34420)
feat(infra): add CI check for out of date lockfiles (#34397)

langchain-openai==1.1.5

Changes since langchain-openai==1.1.4

release(openai): 1.1.5 (#34409)
fix(openai): rely on langchain-core for setting chunk_position (#34404)

langchain-tests==1.1.1

Changes since langchain-tests==1.1.0

release(standard-tests): 1.1.1 (#34393)
docs(standard-tests): throw more descriptive errors for some streaming cases (#34389)

langchain-openai==1.1.4

Changes since langchain-openai==1.1.3

release(openai): 1.1.4 (#34395)
revert(openai): switch model from nano to mini when using flex (#34394)
fix(openai): Correct hyperlinks in documentation of function with_structured_output (#34385)

langchain-core==1.2.2

Changes since langchain-core==1.2.1

chore(core): bump lockfile (#34392)
release(core): 1.2.2 (#34391)
fix(core): use get_type_hints for Python 3.14 TypedDict compatibility (#34390)