Core LangChain.js abstractions and schemas
Last release 8 days ago
20 Aug 2026
Ships on a steady schedule
a new release about every 2 weeks
Nearly every release is documented
notes for 59 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
350 releases · first in 2023
Release timeline
350 releases since 2023Releases
- 1.1.2618 Feb 2026
Release notes
Open source →Patch Changes
- Updated dependencies [
6933769,50d5f32,5552999,8331833]:- @langchain/[email protected]
- @langchain/[email protected]
- @langchain/[email protected]
- Updated dependencies [
- 1.1.2517 Feb 2026
Release notes
Open source →Patch Changes
- Updated dependencies [
478652c,3d35eb1,bbbfea1,52e501b]:- @langchain/[email protected]
- @langchain/[email protected]
- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#10002
27186c5Thanks @aditya-gg04! - fix(core): support reasoning/thinking blocks in StringOutputParser -
#10077
05396f7Thanks @christian-bromann! - feat(core): add ContextOverflowError, raise in anthropic and openai -
#10081
5a6f26bThanks @hntrl! - feat(core): add namespace-based symbol branding for error class hierarchiesIntroduces
createNamespaceutility for hierarchical symbol-based branding of class hierarchies. All LangChain error classes now use this pattern, replacing hand-rolled duck-typeisInstancechecks with reliable cross-realmSymbol.for-based identity.- New
LangChainErrorbase class that all LangChain errors extend - New
createNamespace/NamespaceAPI in@langchain/core/utils/namespace - Refactored
ModelAbortError,ContextOverflowErrorto use namespace branding - Added
ContextOverflowError.fromError()static factory method - Deprecated
addLangChainErrorFieldsin favor ofLangChainErrorsubclasses - Migrated Google provider errors (
GoogleError,ConfigurationError, etc.) to namespace branding - Updated Anthropic and OpenAI providers to use
ContextOverflowError.fromError()
- New
- Updated dependencies [
- 1.1.25-dev-177136549329817 Feb 2026pre-release
Nothing published for this version
- 1.1.2412 Feb 2026
Release notes
Open source →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/[email protected]
- @langchain/[email protected]
- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
- #9978
70a4400Thanks @christian-bromann! - fix(core): fix web_search_call and file_search_call contentBlocks for OpenAI Responses API
-
- 1.1.2312 Feb 2026
Release notes
Open source →Patch Changes
-
#10304
7560180Thanks @MunemHashmi! - fix(community): use generous default max_length for Milvus metadata VarChar fields -
#10253
07b8619Thanks @pawel-twardziak! - fix(community): switch JiraProjectLoader to POST+JSON and propagate API errors -
#10303
46fc5d8Thanks @mitchell-fox! - feat(community): add jql and maxTotal params to JiraProjectLoader -
#10051
e86ac89Thanks @FilipZmijewski! - fix(community): valid params check for ChatWatsonx by IBM (#70) -
Updated dependencies [
26488b5,aacbe87,ca826f6,a602c42,db7d017]:- @langchain/[email protected]
- @langchain/[email protected]
- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#10000
71d08c0Thanks @hntrl! - feat(google): add@langchain/google-- unified Google/Gemini integrationNew package that replaces the fragmented
@langchain/google-genai/@langchain/google-common/ Vertex AI package stack with a single integration.Published as 0.1.0 (early release). Existing Google packages will continue to receive maintenance updates.
-
- 1.1.2211 Feb 2026
Release notes2 sources agree
Open source →Patch Changes
- #9995
8f166b1Thanks @kaigritun! - fix(core): skip empty text blocks in ChatOpenAI contentBlocks
- #9995
- 1.1.2111 Feb 2026
Release notes2 sources agree
Open source →Patch Changes
-
#9990
d5e3db0Thanks @hntrl! - feat(core): Add SSRF protection module (@langchain/core/utils/ssrf) with utilities for validating URLs against private IPs, cloud metadata endpoints, and localhost.fix(community): Harden
RecursiveUrlLoaderagainst SSRF attacks by integratingvalidateSafeUrland replacing string-based URL comparison with origin-basedisSameOriginfrom the shared SSRF module.
-
- 1.1.209 Feb 2026
Release notes2 sources agree
Open source →Patch Changes
- #9957
71c3cbaThanks @jacoblee93! - feat(langchain,core): Update prompt pulling params, LangSmith version
- #9957
- 1.1.194 Feb 2026
Release notes2 sources agree
Open source →Patch Changes
- #9905
41bfea5Thanks @christian-bromann! - fix(classic/community/core): avoid long lived abort signals
- #9905
- 1.1.1830 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
-
#9900
a9b5059Thanks @hntrl! - fix(core): update method signatures to usePartial<CallOptions>for options parametersUpdated
invoke,stream,generate, andgeneratePromptmethod signatures acrossRunnable,BaseChatModel, andBaseLLMto correctly acceptPartial<CallOptions>instead of fullCallOptions. This aligns the implementation with theRunnableInterfacespecification and allows users to pass partial options (e.g.,{ signal: abortedSignal }) without TypeScript errors. -
#9900
a9b5059Thanks @hntrl! - Improved abort signal handling for chat models:- Added
ModelAbortErrorclass in@langchain/core/errorsthat contains partial output when a model invocation is aborted mid-stream invoke()now throwsModelAbortErrorwith accumulatedpartialOutputwhen aborted during streaming (when using streaming callback handlers)stream()throws a regularAbortErrorwhen aborted (since chunks are already yielded to the caller)- All provider implementations now properly check and propagate abort signals in both
_generate()and_streamResponseChunks()methods - Added standard tests for abort signal behavior
- Added
-
- 1.1.1724 Jan 2026
- 1.1.1620 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
-
#9830
70387a1Thanks @bracesproul! - fix: More undefined null errors and tests -
#9679
a7c6ec5Thanks @christian-bromann! - feat(openai): elevate OpenAI image generation outputs to proper image content blocks -
#9817
5e04543Thanks @Ashx098! - read error.status when response.status is absent to avoid retrying OpenAI SDK 4xx -
#9819
40b4467Thanks @MrDockal! - Tool call content returns compacted json -
#9815
17e30bdThanks @hntrl! - fix(core): respect tracingEnabled=false from RunTree when env tracing is enabled
-
- 1.1.1514 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
- #9781
230462dThanks @christian-bromann! - fix(core): preserve index and timestamp fields in _mergeDicts
- #9781
- 1.1.1414 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
- #9797
bd1ab45Thanks @christian-bromann! - handle undefined error objects in async-caller
- #9797
- 1.1.1313 Jan 2026
- 1.1.128 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
- #9517
23be5afThanks @christian-bromann! - fix(@langchain/core): add literal name type inference to tool()
- #9517
- 1.1.12-dev-17678223022527 Jan 2026pre-release
Nothing published for this version
- 1.1.117 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
- #9753
a46a249Thanks @christian-bromann! - fix(core): allow shared object references in serialization
- #9753
- 1.1.11-dev-17677487836947 Jan 2026pre-release
Nothing published for this version
- 1.1.106 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
- #9746
817fc9aThanks @bracesproul! - fix:_mergeDictserror when merging undefined values
- #9746
- 1.1.96 Jan 2026
Release notes2 sources agree
Open source →Patch Changes
-
#9725
56600b9Thanks @Orenoid! - fix(langchain): update merge logic for numeric values inmergeDicts -
#9736
dc5c2acThanks @hntrl! - fix(core): handle circular references inload -
#9739
c28d24aThanks @christian-bromann! - fix(core): use getBufferString for message summarization -
#9702
bfcb87dThanks @christian-bromann! - fix(core): improve interop with Zod
-
- 1.1.822 Dec 2025
Release notes
Open source →Patch Changes
- Updated dependencies [
3b0e4c4]:- @langchain/[email protected]
- Updated dependencies [
- 1.1.8-dev-176677512811026 Dec 2025pre-release
Nothing published for this version
- 1.1.8-dev-176672683237726 Dec 2025pre-release
Nothing published for this version
- 1.1.718 Dec 2025
Release notes
Open source →Patch Changes
- Updated dependencies [
3fe4c43]:- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#9686
df9c42bThanks @hntrl! - add usage_metadata to metadata in LangChainTracer -
#9665
8d2982bThanks @jacoblee93! - feat(core): Make runnable transform trace in a single payload in LangChainTracer -
#9675
af664beThanks @jacoblee93! - Bump LangSmith dep to 0.4.0
- Updated dependencies [
- 1.1.616 Dec 2025
Release notes
Open source →Patch Changes
- Updated dependencies [
e654022]:- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#9668
a7b2a7dThanks @bracesproul! - fix: Cannot merge two undefined objects error -
#9657
a496c5fThanks @dqbd! - fix(core): avoid writing to TransformStream in EventStreamCallbackHandler when underlying ReadableStream is closed -
#9658
1da1325Thanks @dqbd! - fix(core): ensure streaming test chat models respect AbortSignal
- Updated dependencies [
- 1.1.513 Dec 2025
Release notes
Open source →Patch Changes
- #10134
a46d28cThanks @YJack0000! - feat(groq): add reasoning_effort support to ChatGroq
Additional notes
Open source →Patch Changes
- Updated dependencies [
a9f123a,09e7f6d]:- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#9641
005c729Thanks @christian-bromann! - fix(community/core): various security fixes -
#7907
ab78246Thanks @jasonphillips! - fix(core): handle subgraph nesting better in graph_mermaid -
#9589
8cc81c7Thanks @nathannewyen! - test(core): add test for response_metadata in streamEvents -
#9644
f32e499Thanks @hntrl! - add bindTools to FakeListChatModel -
#9508
a28d83dThanks @shubham-021! - Fix toFormattedString() to properly display nested objects in tool call arguments instead of [object Object] -
#9165
2e5ad70Thanks @pawel-twardziak! - fix(mcp-adapters): preserve timeout from RunnableConfig in MCP tool calls -
#9647
e456c66Thanks @hntrl! - handle missing parent runs in tracer to prevent LangSmith 400 errors
- #10134
- 1.1.5-dev-176543379487611 Dec 2025pre-release
Nothing published for this version
- 1.1.5-dev-176543286139811 Dec 2025pre-release
Nothing published for this version
- 1.1.5-dev-176543181667011 Dec 2025pre-release
Nothing published for this version
- 1.1.45 Dec 2025
Additional notes
Open source →Patch Changes
- Updated dependencies [
988ca7d]:- @langchain/[email protected]
- Updated dependencies [
- 1.1.35 Dec 2025
Release notes
Open source →Patch Changes
- Updated dependencies [
3205b35]:- @langchain/[email protected]
Additional notes2 sources agree
Open source →Patch Changes
-
#9534
bd2c46eThanks @christian-bromann! - fix(@langchain/core): update and bundlep-retry,ansi-styles,camelcaseanddecamelizedependencies -
#9544
487378bThanks @hntrl! - fix tool chunk concat behavior (#9450) -
#9505
138e7fbThanks @chosh-dev! - feat: replace btoa with toBase64Url for encoding in drawMermaidImage
- Updated dependencies [
- 1.1.23 Dec 2025
Release notes
Open source →Patch Changes
- Updated dependencies [
05936ab,798cb70,80c790b]:- @langchain/[email protected]
Additional notes2 sources agree
Open source → - Updated dependencies [
- 1.1.12 Dec 2025
Release notes
Open source →Patch Changes
- #10701
880e396Thanks @hntrl! - fix(redis): improve RediSearch query escaping and filter validation- add shared query escaping and field validation helpers for Redis filter builders
- apply escaping and type validation to
buildCustomQuerytag/text/numeric paths - add regression tests covering escaped values, wildcard handling, and invalid filter inputs
Additional notes
Open source →Patch Changes
- Updated dependencies [
80b43ec]:- @langchain/[email protected]
- #10701
- 1.1.024 Nov 2025
Release notes
Open source →Minor Changes
- #10924
2e28115Thanks @christian-bromann! - feat(deepseek): enable native OpenAI-compatible streamEvents events
Patch Changes
- Updated dependencies [
2e28115]:- @langchain/[email protected]
Additional notes
Open source →Minor Changes
- #10924
2e28115Thanks @christian-bromann! - feat(cohere): add native streamEvents event conversion
Additional notes
Open source →Minor Changes
- #10924
2e28115Thanks @christian-bromann! - feat(cloudflare): add native streamEvents event conversion
Additional notes
Open source →Minor Changes
-
#10873
a74d574Thanks @baptistejamin! - chore(mistralai): upgrade to @mistralai/mistralai v2Also populates
response_metadata.modelon chat completions (was missing before).
Additional notes2 sources agree
Open source →Minor Changes
- #9475
708d360Thanks @christian-bromann! - allow to concat system messages
Patch Changes
- #10924
- 1.0.618 Nov 2025
Additional notes2 sources agree
Open source → - 1.0.514 Nov 2025
- 1.0.411 Nov 2025
Release notes2 sources agree
Open source →Patch Changes
- 8319201: Export standard converter function utility
- 1.0.36 Nov 2025
Additional notes2 sources agree
Open source →Patch Changes
- 0a8a23b: feat(@langchain/core): support of ToolRuntime
- 1.0.227 Oct 2025
Additional notes2 sources agree
Open source →Patch Changes
- 6426eb6: fix chunks constructed with tool calls + chunks
- 619ae64: Add
BaseMessage.toFormattedString()
- 1.0.117 Oct 2025
- 1.0.017 Oct 2025
Release notes2 sources agree
Open source →🎉 LangChain v1.0 is here! This release provides a focused, production-ready foundation for building agents with significant improvements to the core abstractions and APIs. See the release notes for more details.
✨ Major Features
Standard content blocks
A new unified API for accessing modern LLM features across all providers:
- New
contentBlocksproperty: Provides provider-agnostic access to reasoning traces, citations, built-in tools (web search, code interpreters, etc.), and other advanced LLM features - Type-safe: Full TypeScript support with type hints for all content block types
- Backward compatible: Content blocks can be loaded lazily with no breaking changes to existing code
Example:
const response = await model.invoke([ { role: "user", content: "What is the weather in Tokyo?" }, ]); // Access structured content blocks for (const block of response.contentBlocks) { if (block.type === "thinking") { console.log("Model reasoning:", block.thinking); } else if (block.type === "text") { console.log("Response:", block.text); } }For more information, see our guide on content blocks.
Enhanced Message API
Improvements to the core message types:
- Structured content: Better support for multimodal content with the new content blocks API
- Provider compatibility: Consistent message format across all LLM providers
- Rich metadata: Enhanced metadata support for tracking message provenance and transformations
🔧 Improvements
- Better structured output generation: Core abstractions for generating structured outputs in the main agent loop
- Improved type safety: Enhanced TypeScript definitions across all core abstractions
- Performance optimizations: Reduced overhead in message processing and runnable composition
- Better error handling: More informative error messages and better error recovery
📦 Package Changes
The
@langchain/corepackage remains focused on essential abstractions:- Core message types and content blocks
- Base runnable abstractions
- Tool definitions and schemas
- Middleware infrastructure
- Callback system
- Output parsers
- Prompt templates
🔄 Migration Notes
Backward Compatibility: This release maintains backward compatibility with existing code. Content blocks are loaded lazily, so no changes are required to existing applications.
New Features: To take advantage of new features like content blocks and middleware:
-
Update to
@langchain/core@next:npm install @langchain/[email protected] -
Use the new
contentBlocksproperty to access rich content:const response = await model.invoke(messages); console.log(response.contentBlocks); // New API console.log(response.content); // Legacy API still works -
For middleware and
createAgent, installlangchain@next:npm install [email protected] @langchain/[email protected]
📚 Additional Resources
- New
- 1.0.0-alpha.715 Oct 2025pre-release
Nothing published for this version
- 1.0.0-alpha.626 Sept 2025pre-release
Nothing published for this version
- 1.0.0-alpha.518 Sept 2025pre-release
Nothing published for this version
- 1.0.0-alpha.415 Sept 2025pre-release
Nothing published for this version
- 1.0.0-alpha.39 Sept 2025pre-release
Nothing published for this version
- 1.0.0-alpha.22 Sept 2025pre-release
Nothing published for this version
- 1.0.0-alpha.127 Aug 2025pre-release
Nothing published for this version
- 0.3.8023 Dec 2025
Nothing published for this version
- 0.3.7927 Oct 2025
Release notes2 sources agree
Open source →Patch Changes
- 1063b43: fix chunks constructed with tool calls + chunks
- 0.3.7829 Sept 2025
Release notes2 sources agree
Open source →Patch Changes
- 1519a97: update chunk concat logic to match on missing ID fields
- 079e11d: omit tool call chunks without tool call id
- 0.3.7717 Sept 2025
Nothing published for this version
- 0.3.7615 Sept 2025
Release notes2 sources agree
Open source →Patch Changes
- 41bd944: support base64 embeddings format
- e90bc0a: fix(core): prevent tool call chunks from merging incorrectly in AIMes…
- 3a99a40: Fix deserialization of RemoveMessage if represented as a plain object
- 58e9522: make mustache prompt with nested object working correctly
- e44dc1b: handle backticks in structured output
- 0.3.755 Sept 2025
Release notes2 sources agree
Open source →Patch Changes
- d6d841f: fix(core): Fix deep nesting of runnables within traceables
- 0.3.744 Sept 2025
Release notes2 sources agree
Open source →Patch Changes
- 4e53005: fix(core): Always inherit parent run id onto callback manager from context
- 0.3.732 Sept 2025
Release notes2 sources agree
Open source →Patch Changes
- a5a2e10: add root export to satisfy bundler requirements
- 0.3.7219 Aug 2025
Nothing published for this version
- 0.3.7115 Aug 2025
Nothing published for this version
- 0.3.71-rc.015 Aug 2025pre-release
Nothing published for this version