Releases: langchain-ai/langchain
langchain-tests==1.0.1
Changes since langchain-tests==1.0.0
release(standard-tests): 1.0.1 (#33792)
fix(standard-tests): update multimodal tests (#33781)
style: more refs fixes (#33730)
chore(standard-tests): Update API reference link in README (#33714)
style: more refs work (#33707)
fix: links (#33691)
fix(standard-tests): fix tool description in agent loop test (#33690)
style: more refs work (#33616)
chore: update pyproject.toml url entries (#33587)
fix: support python 3.14 in various projects (#33575)
langchain-model-profiles==0.0.3
langchain-huggingface==1.0.1
langchain-core==1.0.3
langchain-openai==1.0.2
Changes since langchain-openai==1.0.1
fix(standard-tests): update multimodal tests (#33781)
release(openai): 1.0.2 (#33769)
test(openai): mark tests flaky (#33750)
fix(openai): replace pytest.warns(None) with warnings.catch_warnings in ChatOpenAI test to resolve TypeError . Resolves issue #33705 (#33741)
fix(openai): update model used in test (#33733)
style: more refs fixes (#33730)
style(core): more cleanup all around (#33711)
fix: links (#33691)
fix(openai): update test (#33659)
feat(openai): add unit test for streaming error in _generate (#33134)
langchain-model-profiles==0.0.2
langchain-model-profiles==0.0.1
langchain-anthropic==1.0.1
- Add default max token count for Sonnet 4.5.
Changes since langchain-anthropic==1.0.0
release(anthropic): 1.0.1 (#33752)
fix(anthropic): clean up tests, update default model to use ID (#33751)
chore: remove mentions of sonnet 3.5 (#33737)
style: more refs fixes (#33730)
chore: move ToolNode improvements back to langgraph (#33634)
fix: links (#33691)
refactor(anthropic): remove unnecessary url check (#33671)
chore(anthropic): update integration test cassette (#33685)
style(anthropic): use aliases for model names (#33590)
chore: update pyproject.toml url entries (#33587)
docs: fix Anthropic, OpenAI docstrings (#33566)
langchain==1.0.3
Changes since langchain==1.0.2
chore: remove mentions of sonnet 3.5 (#33737)
fix(langchain_v1): remove thread_model_call_count and run_model_call_count from tool node test (#33725)
release: core 1.0.2 and langchain 1.0.3 (#33736)
fix(langchain_v1): removed unsed functions in tool_call_limit middleware (#33735)
style: more refs fixes (#33730)
chore: move ToolNode improvements back to langgraph (#33634)
feat: support structured output retry middleware (#33663)
fix(langchain_v1): correct ref url (#33715)
style: more refs work (#33707)
feat(langchain): export UsageMetadata (#33692)
release(core): 1.0.1 (#33639)
langchain-core==1.0.2
Changes since langchain-core==1.0.1
release: core 1.0.2 and langchain 1.0.3 (#33736)
fix: filter out injected args from tracing (#33729)
style: more refs fixes (#33730)
fix(core): improve JSON get_format_instructions using Opik Agent Optimizer (#33718)
style(core): more cleanup all around (#33711)
style: more refs work (#33707)
fix(core): translate Google GenAI text blocks to v1 (#33699)
feat(langchain): export UsageMetadata (#33692)
fix: links (#33691)
fix(core): fix PydanticOutputParser's get_format_instructions for v1 models (#32479)
refactor(core): Minor refactor for code readability (#33674)
fix(infra): add emacs backup files to gitignore (#33675)
fix: update some links (#33686)
style(core): more refs work (#33664)