Merged
Conversation
ca9d207 to
2e41c6b
Compare
2e41c6b to
c3930e0
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.
Releases
@langchain/openai@1.3.0
Minor Changes
af9bbd3Thanks @hntrl! - feat(openai): support tool search and defer_loadingtools.toolSearch()factory for the OpenAI Responses APItool_searchbuilt-in tool, supporting both server-executed and client-executed modes.defer_loadingfrom LangChain toolextrasthroughbindTools()and into the Responses API payload, enabling on-demand tool discovery.tool_search_callandtool_search_outputresponse items in both streaming and non-streaming converters.tool_search_call→server_tool_callandtool_search_output→server_tool_call_result.Patch Changes
6db417b,d69dfcc]:@langchain/community@1.1.24
Patch Changes
#10425
792d573Thanks @pawel-twardziak! - fix(community): auto-detect VL model endpoint and add apiUrl override for ChatAlibabaTongyi#10004
a40ddc7Thanks @aditya-gg04! - fix/community-better-sqlite3-node24-support#10298
aad77abThanks @pawel-twardziak! - fix(community): Add multimodal content support to Bedrock Anthropic formatter#10399
1edc658Thanks @pawel-twardziak! - add missing AWS inference profile region prefixes (au, jp, global)#10413
7a3774aThanks @shivamtiwari3! - fix(community): update PPTXLoader to use officeparser v6 API (fixes #10168)Updated dependencies [
6db417b,af9bbd3,d69dfcc]:langchain@1.2.33
Patch Changes
#9862
5b250b1Thanks @stellarrover! - fix(langchain/agents): Fix ReactAgent routing with returnDirect + beforeModel middlewareThis fixes a routing error when an agent has both tools with returnDirect: true and middleware with beforeModel hooks (e.g., summarizationMiddleware). Before this fix, non-returnDirect tools would fail with "Branch condition returned unknown or null destination".
Updated dependencies [
6db417b,d69dfcc]:@langchain/classic@1.0.24
Patch Changes
af9bbd3]:@langchain/core@1.1.33
Patch Changes
#10412
6db417bThanks @pawel-twardziak! - fix(core): respect timeout option in streamEvents v2#10424
d69dfccThanks @pawel-twardziak! - fix(core): preserve multimodal content in getBufferString as placeholders@langchain/anthropic@1.3.24
Patch Changes
08657f2Thanks @pawel-twardziak! - Fix temperature/topK/topP handling: guard all three so undefined values are notset on the request object, and fix broken topK/topP validation when thinking is
enabled.
6db417b,d69dfcc]:@langchain/aws@1.3.3
Patch Changes
e3fb76bThanks @pawel-twardziak! - feat(aws): add defaultHeaders to ChatBedrockConverse@langchain/deepseek@1.0.18
Patch Changes
af9bbd3]:@langchain/google@0.1.7
Patch Changes
#10343
a1062b7Thanks @pawel-twardziak! - fix: merge consecutive same-role Gemini content blocks#10313
bc4cd65Thanks @pawel-twardziak! - fix(langchain-google): parse JSON error bodies from non-JSON content types#10397
955ef6bThanks @pawel-twardziak! - fix(google): fix v1 converter dropping tool_calls, text-plain and file blocks#10402
9099f53Thanks @pawel-twardziak! - fix(google): use dynamic ls_provider based on platform instead of hardcoded "google"#10415
d7d0bc7Thanks @pawel-twardziak! - fix(genai): round-trip thinking content blocks in multi-turn convos#10407
c2960feThanks @fahe1em1! - lazy-load jose in CJS auth helpers#10292
e4193f8Thanks @afirstenberg! - fixes for Vertex function calls#10400
a870750Thanks @afirstenberg! - support role name for function response in Vertex@langchain/google-common@2.1.26
Patch Changes
#9987
561224bThanks @mbarinov! - fix(google-common): prevent 400 error when AIMessage has empty text content#9979
6a2da5bThanks @christian-bromann! - fix(google): add support for ContentBlock.Multimodal types in Google providersUpdated dependencies [
6db417b,d69dfcc]:@langchain/google-gauth@2.1.26
Patch Changes
561224b,6a2da5b]:@langchain/google-genai@2.1.26
Patch Changes
#10415
d7d0bc7Thanks @pawel-twardziak! - fix(genai): round-trip thinking content blocks in multi-turn convos#9979
6a2da5bThanks @christian-bromann! - fix(google): add support for ContentBlock.Multimodal types in Google providersUpdated dependencies [
6db417b,d69dfcc]:@langchain/google-vertexai@2.1.26
Patch Changes
@langchain/google-vertexai-web@2.1.26
Patch Changes
@langchain/google-webauth@2.1.26
Patch Changes
6db417b,561224b,6a2da5b,d69dfcc]:@langchain/openrouter@0.1.7
Patch Changes
af9bbd3]:@langchain/xai@1.3.10
Patch Changes
af9bbd3]: