Releases: langchain-ai/langchain
langchain-anthropic==0.3.19
Changes since langchain-anthropic==0.3.18
release(anthropic): 0.3.19 (#32595)
chore: update references to use the latest version of Claude-3.5 Sonnet (#32594)
fix(anthropic): correct input_token count for streaming (#32591)
fix(anthropic): clean up null file_id fields in citations during message formatting (#32592)
revert(anthropic): streaming token counting to defer input tokens until completion (#32587)
fix(anthropic): sanitize tool use block when taking directly from content (#32574)
fix(anthropic): streaming token counting to defer input tokens until completion (#32518)
fix(anthropic): Add proxy (#32409)
feat(anthropic): support cache_control as a kwarg (#31523)
fix(anthropic): update test model names and adjust token count assertions in integration tests (#32422)
docs(anthropic): add documentation for extended context windows in Claude Sonnet 4 (#32517)
feat: port various nit changes from wip-v0.4 (#32506)
langchain-openai==0.3.30
langchain-openai==0.3.29
Changes since langchain-openai==0.3.28
release(openai): release 0.3.29 (#32463)
chore: formatting across codebase (#32466)
fix(openai): revert some changes (#32462)
feat(openai): minimal and verbosity (#32455)
fix(openai): don't crash get_num_tokens_from_messages on gpt-5 (#32451)
feat(openai): custom tools (#32449)
test(openai): add tests for prompt_cache_key parameter and update docs (#32363)
fix(openai): add in output_text (#32450)
chore(openai): bump openai sdk (#32322)
fix(openai): add max_retries parameter to ChatOpenAI for handling 503 capacity errors (#32286)
fix: formatting issues in docstrings (#32265)
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)
langchain-core==0.3.74
langchain-core==0.3.73
Changes since langchain-core==0.3.72
release(core): 0.3.73 (#32446)
feat(core): zero-out token costs for cache hits (#32437)
fix(core): fix index checking when merging lists (#32431)
fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
fix: lint
fix: tool call streaming bug with inconsistent indices from Qwen3 (#32160)
fix(core): resolve cache validation error by safely converting Generation to ChatGeneration objects (#32156)
chore(core): add test for nested pydantic fields in schemas (#32285)
refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
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)
langchain==0.4.0.dev0
Changes since langchain==0.3.27
chore: increment versions for 0.4 branch (#32419)
feat: standard outputs (#32287)
fix: use new Google model names in examples (#32288)
fix: update bar_model to use the correct model version claude-3-7-sonnet-20250219 (#32284)
refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
fix: devcontainer (#32260)
chore(langchain): add ruff rules ARG (#32110)
chore(langchain): add ruff rules TC (#31921)
feat(docs): improve devx, fix Makefile targets (#32237)
chore(langchain): add ruff rules D1 (except D100 and D104) (#32123)
chore(langchain): add ruff rules SLF (#32112)
chore(langchain): strip_ansi fucntion to remove ANSI escape sequences (#32200)
fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235)
refactor(langchain): refactor unit test stub classes (#32209)
langchain-openai==0.4.0.dev0
Changes since langchain-openai==0.3.28
chore: increment versions for 0.4 branch (#32419)
feat: standard outputs (#32287)
chore(openai): bump openai sdk (#32322)
fix(openai): add max_retries parameter to ChatOpenAI for handling 503 capacity errors (#32286)
fix: formatting issues in docstrings (#32265)
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)
langchain-groq==0.3.7
Changes since langchain-groq==0.3.6
release(groq): 0.3.7 (#32417)
feat(groq): losen restrictions on reasoning_effort, inject effort in meta, update tests (#32415)
feat(groq): openai-oss (#32411)
fix: formatting issues in docstrings (#32265)
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)
docs(groq): cleanup (#32043)
langchain-core==0.4.0.dev0
Changes since langchain-core==0.3.72
chore: increment versions for 0.4 branch (#32419)
feat: standard outputs (#32287)
fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
fix: lint
fix: tool call streaming bug with inconsistent indices from Qwen3 (#32160)
fix(core): resolve cache validation error by safely converting Generation to ChatGeneration objects (#32156)
chore(core): add test for nested pydantic fields in schemas (#32285)
refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
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)
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)