langchain-anthropic==0.3.18

Changes since langchain-anthropic==0.3.17

release(anthropic): 0.3.18 (#32292)
refactor(anthropic): AnthropicLLM to use Messages API (#32290)
refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281)
feat(docs): improve devx, fix Makefile targets (#32237)
fix: LLM mimicking Unicode responses due to forced Unicode conversion of non-ASCII characters. (#32222)
fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235)
docs(openai): add comprehensive documentation and examples for extra_body + others (#32149)
fix(anthropic): update integration test models (#32189)
fix(anthropic): fix test (#32145)
ruff: restore stacklevels, disable autofixing (#31919)
ruff: add bugbear across packages (#31917)
huggingface[patch]: ruff fixes and rules (#31912)
anthropic[patch]: ruff fixes and rules (#31899)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
anthropic[patch]: pass back in citations in multi-turn conversations (#31882)
Revert "infra: temporarily skip tests" (#31854)

langchain==0.3.27

Changes since langchain==0.3.26

fix(langchain): update deps
release(langchain): 0.3.27 (#32227)
feat(langchain): add ruff rules PL (#32079)
docs: formatting cleanup (#32188)
fix: replace deprecated Pydantic .schema() calls with v1/v2 compatible pattern (#32162)
feat(langchain): add ruff rules TRY (#32047)
feat(langchain): add ruff rules PT (#32010)
fix(ollama): robustly parse single-quoted JSON in tool calls (#32109)
fix(core): JSON Schema reference resolution for list indices (#32088)
refactor(langchain): remove model_rebuild (#32080)
feat(langchain): add ruff rules G (#32029)
feat(langchain): add ruff rules DTZ (#32021)
feat(langchain): add ruff rules PTH (#32008)
chore: update error message formatting (#31980)
docs: add Google-style docstrings to tools and llms modules (zapier, … (#31957)
chore[langchain]: fix broad base except in crawler.py (#31941)
ruff: restore stacklevels, disable autofixing (#31919)
ruff: add bugbear across packages (#31917)
exception: update Exception to ValueError for clearer error handling (#31915)
langchain[patch]: harden xml parser for xmloutput agent (#31859)
langchain: Add ruff rules B (#31908)
langchain: Fix Evaluator's _check_evaluation_args (#31910)
langchain: Use pytest.raises and pytest.fail to handle exceptions in tests (#31911)
huggingface[patch]: ruff fixes and rules (#31912)
anthropic[patch]: ruff fixes and rules (#31899)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
fix: complete exception handling for UpstashRedisEntityStore (#31893)
fix: lint/format (#31894)
langchain: Add ruff rule RUF (#31874)
langchain: Add ruff rules FBT (#31885)
langchain: Add ruff rule RET (#31875)
langchain: Add ruff rules C4 (#31879)
langchain: Add ruff rules SIM (#31881)
langchain: Add ruff rules A (#31888)
langchain: Add ruff rules EM (#31873)
langchain: Add ruff rules PIE (#31880)
langchain: Add ruff rule W (#31876)
langchain: Bump ruff version to 0.12 (#31867)
langchain[patch]: fix a bug where now.replace(day=now.day - 1) would raise a ValueError when now.day is equal to 1 (#31878)
langchain[patch]: Add bandit rules (#31818)
core[path]: Use context manager for FileCallbackHandler (#31813)
openai[patch]: allow specification of output format for Responses API (#31686)
openai[patch]: add attribute to always use previous_response_id (#31734)
docs: fix typo in globals.py (#31728)
core[patch]: Add additional hashing options to indexing API, warn on SHA-1 (#31649)
langchain[patch]: smith.evaluation.progress.ProgressBarCallback: Make output after progress bar ends configurable (#31583)

langchain-text-splitters==0.3.9

Changes since langchain-text-splitters==0.3.8

fix(text-splitters): update langchain-core version to 0.3.72
fix(text-splitters): update lock for release
fix(langchain): class HTMLSemanticPreservingSplitter ignores the text inside the div tag (#32213)
feat(text-splitters): add Visual Basic 6 support (#31173)
text-splitters: Add ruff rules FBT (#31935)
text splitters: add chunk_size and chunk_overlap validations (#31916)
fix: automatically fix issues with ruff (#31897)
text-splitters: Ruff autofixes (#31858)
text-splitters: Bump ruff version to 0.12 (#31866)
text-splitters: bump spacy version to 3.8.7 (#31834)
text-splitters: Add ruff rule UP (pyupgrade) (#31841)
text-splitters: 0.3.9 (#31844)
security: Remove xslt_path and harden XML parsers in HTMLSectionSplitter: package: langchain-text-splitters (#31819)
text-splitters: fix stale header metadata in ExperimentalMarkdownSyntaxTextSplitter (#31622)
chore: Bump langsmith in splitter uv (#31626)
text-splitters: Add keep_separator arg to HTMLSemanticPreservingSplitter (#31588)
text-splitters[patch]: fix some import-untyped errors (#31030)
text-splitters: Fix regex separator merge bug in CharacterTextSplitter (#31137)
packaging: remove Python upper bound for langchain and co libs (#31025)
text-splitters: Set strict mypy rules (#30900)

langchain-core==0.3.72

Changes since langchain-core==0.3.71

release(core): 0.3.72 (#32214)
fix(core): Dereference Refs for pydantic schema fails in tool schema generation (#32203)
docs: formatting cleanup (#32188)

langchain-xai==0.2.5

Changes since langchain-xai==0.2.4

fix: bump deps for release (#32179)
release(xai): 0.2.5 (#32174)
docs(xai): update for Grok 4 (#31953)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-xai[patch]: Add ruff bandit rules to linter (#31816)
openai[patch]: allow specification of output format for Responses API (#31686)
standard-tests: add benchmarks (#31302)
docs: update xai docs (#31382)
xai: document live search feature (#31381)

langchain-perplexity==0.1.2

Changes since langchain-perplexity==0.1.1

.
fix(perplexity): temp xfail int tests (#32191)
fix: bump deps for release (#32179)
release(perplexity): 0.1.2 (#32176)
feat(perplexity): expose search_results in chat model (#31468)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-perplexity[patch]: Add ruff bandit rules to linter (#31812)
[Doc] Improve api doc for perplexity (#31636)
packaging: remove Python upper bound for langchain and co libs (#31025)

langchain-ollama==0.3.6

Changes since langchain-ollama==0.3.5

release(ollama): 0.3.6 (#32180)
feat(ollama): warn on empty load responses (#32161)
docs(ollama): add validate_model_on_init note, bump lock (#32172)
fix(ollama): robustly parse single-quoted JSON in tool calls (#32109)

langchain-huggingface==0.3.1

Changes since langchain-huggingface==0.3.0

fix: bump deps for release (#32179)
release(huggingface): 0.3.1 (#32177)
fix(huggingface): update model used in standard tests (#32116)
fix: bump lockfiles (#31923)
ruff: restore stacklevels, disable autofixing (#31919)
ruff: add bugbear across packages (#31917)
huggingface[patch]: ruff fixes and rules (#31912)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
huggingface: fix HuggingFaceEndpoint._astream() got multiple values for argument 'stop' (#31385)
langchain-huggingface[patch]: Add ruff bandit rules to linter (#31798)
huggingface: handle image-text-to-text pipeline task (#31611)

langchain-deepseek==0.1.4

Changes since langchain-deepseek==0.1.3

fix(deepseek): release openai version (#32181)
fix: bump deps for release (#32179)
release(deepseek): 0.1.4 (#32178)
fix(deepseek): convert tool output arrays to strings (#31913)
fix: bump lockfiles (#31923)
ruff: restore stacklevels, disable autofixing (#31919)
deepseek[patch]: ruff fixes and rules (#31901)
ruff: more rules across the board & fixes (#31898)
fix: automatically fix issues with ruff (#31897)
langchain-deepseek[patch]: add ruff bandit rules (#31792)
[Doc] Improve api doc for DeepSeek (#31655)
standard-tests: add benchmarks (#31302)
partners: (langchain-deepseek) fix deepseek-r1 always returns an empty reasoning_content when reasoning (#31065)
packaging: remove Python upper bound for langchain and co libs (#31025)
partners[lint]: run pyupgrade to get code in line with 3.9 standards (#30781)
Fix deepseek release tag, as it is update name. (#30717)
Revert "deepseek: temporarily bypass tests" (#30424)

langchain-core==0.3.71

Changes since langchain-core==0.3.70

release(core): 0.3.71 (#32186)
fix(core): exclude api_key from tracing metadata (#32184)
fix(core): add type key when tracing in some cases (#31825)
feat(core): add sanitize_for_postgres utility to fix PostgreSQL NUL byte DataError (#32157)