#10776 20a9abe Thanks @hntrl! - fix(deps): remediate uuid vulnerability by removing direct uuid usage
Updated dependencies [dc20c0e, 20a9abe]:
71e53f1 Thanks @Josh-Engle! - Prevent local file corruption when using LocalFileStore2301260]:
6b8ef6c]:
#10591 d7a98cd Thanks @christian-bromann! - feat: add @langchain/perplexity standalone provider package
#10594 884c2d3 Thanks @christian-bromann! - feat(fireworks): extract standalone provider package
#10593 0fb6fa4 Thanks @christian-bromann! - feat(together-ai): migrate Together AI into provider package
Updated dependencies [d6bf4fc]:
9270c48]:
5552999]:
#10475 3d35eb1 Thanks @hntrl! - fix(langchain): add "aws" alias to MODEL_PROVIDER_CONFIG so hub/node auto-detects ChatBedrockConverse from Python-serialized prompts
Updated dependencies [478652c, 52e501b]:
af9bbd3]:
aacbe87]:
3682a8d]:
62ba83e]:
b583729]:
#9786 8ee833c Thanks @SkrOYC! - fix: resolve flaky tests and configuration issues
Updated dependencies [16d691c, 1058574]:
#9763 8f0757f Thanks @AdamParker19! - fix(langchain): resolve className collision in MODEL_PROVIDER_CONFIG
Refactored getChatModelByClassName to accept an optional modelProvider parameter for direct lookup, avoiding the className collision issue where multiple providers share the same className (e.g., google-vertexai and google-vertexai-web both use "ChatVertexAI"). When modelProvider is provided, the function uses direct config lookup instead of searching by className. Backward compatibility is maintained for existing callers that only pass className. This eliminates the duplicated import logic that was previously in _initChatModelHelper.
Updated dependencies [0870ca0, cf46089]:
#9905 41bfea5 Thanks @christian-bromann! - fix(classic/community/core): avoid long lived abort signals
Updated dependencies []:
1fa865b, 28efb57, 4e42452, a9b5059, a9b5059]:
1d58bf2 Thanks @jacoblee93! - fix(classic): Fix typo in package.jsona7c6ec5, 04923f9, e16c218]:
3efe79c]:
cc502e1 Thanks @jacoblee93! - fix(langchain): Add secretsFromEnv and secrets for prompt pulling
fix(@langchain/classic): Add secretsFromEnv and secrets for prompt pulling13c9d5b, 75b3b90]:
#9675 af664be Thanks @jacoblee93! - Bump LangSmith dep to 0.4.0
Updated dependencies []:
#9596 316392e Thanks @christian-bromann! - fix(@langchain/classic): add langsmith as external dependency
#9606 41b26a4 Thanks @patrykkopycinski! - bin p-retry
Updated dependencies [5a01b5b, eab88a5, 5f79bc5, 7b301c0, bb2f422, 2a5ba50, 47edf3f, 2e563e3, 72795fe, f97b488, 29a8480, 3ecc1e7, 6baa851, a552cad, 69a1045]:
#9416 0fe9beb Thanks @hntrl! - fix 'moduleResultion: "node"' compatibility
#9463 10fa2af Thanks @christian-bromann! - fix(core): update p-retry to fix memory leak
Updated dependencies [0fe9beb]:
#9379 34c472d Thanks @kenowessels! - OpenAPIToJSONSchema required from nested schema
Updated dependencies [415cb0b, a2ad61e]:
04bd55c, ac0d4fe, 39dbe63, dfbe45f]:
OpenAIModerationChain
This release updates the package for compatibility with LangChain v1.0. See the v1.0 release notes for details on what's new.