NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #4362 most downloaded on npm
Core LangChain.js abstractions and schemas
Latest stable
1.4.2
Last release 3 days ago
18 Nov 2026
Ships fairly regularly
a new release about every 2 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
371 releases · first in 2023
Drag across the ruler to compare, or tap a release to open it.
### Patch Changes - #10552 `589ab9b` Thanks @christian-bromann! - fix(langchain): accept cross-version runnable models in createAgent
589ab9b Thanks @christian-bromann! - fix(langchain): accept cross-version runnable models in createAgentExtract phase from message output items and surface it on text content blocks
#10511 6933769 Thanks @hntrl! - cache Zod-to-JSON-Schema conversions in toJsonSchema()
#10541 50d5f32 Thanks @jacoblee93! - revert: Revert "feat(core): Add all chat model/llm invocation params to metadata"
#10509 5552999 Thanks @hntrl! - feat(openai): add support for phase parameter on Responses API messages
phase from message output items and surface it on text content blocksresponse.output_item.added eventsextras dict in the core standard content translator#10528 8331833 Thanks @christian-bromann! - fix(core): normalize single-block content in mergeContent
Your coding agent can read these notes before it upgrades. Set up the MCP server →
_mergeLists now falls back to id-based matching when items don't have an index field. Previously, providers routing through the OpenAI-compatible API
#10512 bbbfea1 Thanks @hntrl! - fix(core): fix streaming chunk merge for providers without index on tool call deltas
_mergeLists now falls back to id-based matching when items don't have an index field. Previously, providers routing through the OpenAI-compatible API without index on streaming tool call deltas (e.g. Anthropic models via ChatOpenAI) would accumulate hundreds of individual raw deltas in tool_call_chunks and additional_kwargs.tool_calls instead of merging them into a single entry per tool call. In a real trace with 3 concurrent subagents, this caused a single AI message to balloon from ~4KB to 146KB -- with 826 uncollapsed streaming fragments carrying a few bytes each.
Also fixes SystemMessage.concat() which used ...this to spread all instance properties (including lc_kwargs) into the new constructor, causing each chained concat() call to nest one level deeper. After 7 middleware concat() calls (typical in deepagents), a 7KB system prompt would serialize to 81KB due to content being duplicated at every nesting level.
Replaces all exported Zod type references (z3.ZodType, z4.$ZodType, etc.) in @langchain/core's public API with minimal structural ("duck-type") interf
#10327 5dc11b5 Thanks @hntrl! - fix(core): replace exported zod type references with structural duck-type interfaces to fix TypeScript OOM
Replaces all exported Zod type references (z3.ZodType, z4.$ZodType, etc.) in @langchain/core's public API with minimal structural ("duck-type") interfaces. This prevents TypeScript from performing expensive deep structural comparisons (~3,400+ lines of mutually recursive generics) when downstream packages resolve a different Zod version than @langchain/core, which was causing OOM crashes and unresponsive language servers in monorepo setups.
#10433 7af0b65 Thanks @tanushree-sharma! - feat: Add LangSmith integration metadata to createAgent and initChatModel
### Patch Changes - #10312 `bfb7944` Thanks @jacoblee93! - feat(core): Add all invocation params as part of metadata
bfb7944 Thanks @jacoblee93! - feat(core): Add all invocation params as part of metadata### Patch Changes - #10412 `6db417b` Thanks @pawel-twardziak! - fix(core): respect timeout option in streamEvents v2 - #10424 `d69dfcc` Thanks @pawel-
#10412 6db417b Thanks @pawel-twardziak! - fix(core): respect timeout option in streamEvents v2
#10424 d69dfcc Thanks @pawel-twardziak! - fix(core): preserve multimodal content in getBufferString as placeholders
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Fixed _mergeLists in message base to treat empty string "" IDs the same as null/undefined when merging tool call chunks. This fixes old completions-st
#10330 26488b5 Thanks @hntrl! - fix(core): treat empty string tool call chunk IDs as missing during merge
Fixed _mergeLists in message base to treat empty string "" IDs the same as null/undefined when merging tool call chunks. This fixes old completions-style streaming where follow-up chunks carry id: "" instead of undefined, which previously prevented chunks from being merged by index.
#10167 ca826f6 Thanks @colifran! - feat: implement type inference for tool streams
#10334 a602c42 Thanks @maahir30! - fix(core): add JSDoc docstrings to fakeModel builder API and export FakeBuiltModel
#10254 db7d017 Thanks @pawel-twardziak! - fix(core): preserve thoughtSignature in array content during streaming with thinking models
Nothing published for this version
Adds a new @langchain/core/testing/matchers export containing custom Vitest matchers (toBeHumanMessage, toBeAIMessage, toBeSystemMessage, toBeToolMess
#10271 7373b4c Thanks @jacoblee93! - feat(core): Use uuid7 instead of v4 for generating run ids
#10262 b0175a5 Thanks @maahir30! - fix: Move fakeModel from utils/testing to testing namespace
move to updated namespace
#10185 414f6ed Thanks @maahir30! - feat: add custom Vitest matchers for LangChain message and tool call assertions
Adds a new @langchain/core/testing/matchers export containing custom Vitest matchers (toBeHumanMessage, toBeAIMessage, toBeSystemMessage, toBeToolMessage, toHaveToolCalls, toHaveToolCallCount, toContainToolCall, toHaveToolMessages, toHaveBeenInterrupted, toHaveStructuredResponse) that external users can register via expect.extend(langchainMatchers) in their Vitest setup files. Re-exported from langchain for convenience.
TypeScript infers unique symbol type when Symbol.for() is used without an explicit type annotation, causing type incompatibility when multiple version
#10243 96c630d Thanks @hntrl! - fix: add explicit : symbol type annotations to Symbol.for() declarations for cross-version compatibility
TypeScript infers unique symbol type when Symbol.for() is used without an explicit type annotation, causing type incompatibility when multiple versions of the same package are present in a dependency tree. By adding explicit : symbol annotations, all declarations now use the general symbol type, making them compatible across versions while maintaining identical runtime behavior.
Changes:
: symbol to MESSAGE_SYMBOL in messages/base.ts: symbol to MIDDLEWARE_BRAND in agents/middleware/types.ts (also changed from Symbol() to Symbol.for() for cross-realm compatibility)#10256 a8b9ccc Thanks @colifran! - fix(core): standard schema type guards don't support callable schemas
#10204 a1f22bb Thanks @colifran! - feat(core): implement standard schema support for structured output
The uuid v10 package has ambiguous exports in its package.json which causes Metro (used by Expo/React Native) to resolve the wrong entry point, result
#10106 9f30267 Thanks @hntrl! - Add package version metadata to runnable traces. Each package now stamps its version in this.metadata.versions at construction time, making version info available in LangSmith trace metadata.
#10154 403a99f Thanks @kanweiwei! - fix(core): add usage_metadata to AIMessage lc_aliases
#10169 3b1fd54 Thanks @hntrl! - fix(core, langchain): bump uuid dependency from ^10.0.0 to ^11.0.0 to fix Metro bundler error
The uuid v10 package has ambiguous exports in its package.json which causes Metro (used by Expo/React Native) to resolve the wrong entry point, resulting in Cannot read properties of undefined (reading 'v1'). The uuid v11 package fixes its exports map to work correctly with Metro's package exports resolution.
#10044 77bd982 Thanks @hntrl! - fix(core): remove inherited LangChainTracer handlers when tracingEnabled is false
When a RunTree explicitly disables tracing via tracingEnabled: false, CallbackManager._configureSync now strips any inherited LangChainTracer handlers so child runs don't produce traces.
### Patch Changes - #10140 `10a876c` Thanks @hntrl! - Merge content blocks by string index during streaming. - #10102 `b46d96a` Thanks @colifran! - fe
Updated dependencies \[`9270c48`, `589ab9b`]:
Updated dependencies \[`6933769`, `50d5f32`, `5552999`, `8331833`]:
Updated dependencies \[`478652c`, `3d35eb1`, `bbbfea1`, `52e501b`]:
#10002 27186c5 Thanks @aditya-gg04! - fix(core): support reasoning/thinking blocks in StringOutputParser
#10077 05396f7 Thanks @christian-bromann! - feat(core): add ContextOverflowError, raise in anthropic and openai
#10081 5a6f26b Thanks @hntrl! - feat(core): add namespace-based symbol branding for error class hierarchies
Introduces createNamespace utility for hierarchical symbol-based branding of class hierarchies.
All LangChain error classes now use this pattern, replacing hand-rolled duck-type isInstance checks
with reliable cross-realm Symbol.for-based identity.
LangChainError base class that all LangChain errors extendcreateNamespace / Namespace API in @langchain/core/utils/namespaceModelAbortError, ContextOverflowError to use namespace brandingContextOverflowError.fromError() static factory methodaddLangChainErrorFields in favor of LangChainError subclassesGoogleError, ConfigurationError, etc.) to namespace brandingContextOverflowError.fromError()Nothing published for this version
Updated dependencies \[`6db417b`, `af9bbd3`, `d69dfcc`]:
#10425 792d573 Thanks @pawel-twardziak! - fix(community): auto-detect VL model endpoint and add apiUrl override for ChatAlibabaTongyi
#10004 a40ddc7 Thanks @aditya-gg04! - fix/community-better-sqlite3-node24-support
#10298 aad77ab Thanks @pawel-twardziak! - fix(community): Add multimodal content support to Bedrock Anthropic formatter
#10399 1edc658 Thanks @pawel-twardziak! - add missing AWS inference profile region prefixes (au, jp, global)
#10413 7a3774a Thanks @shivamtiwari3! - fix(community): update PPTXLoader to use officeparser v6 API (fixes #10168)
Updated dependencies [6db417b, af9bbd3, d69dfcc]:
70a4400 Thanks @christian-bromann! - fix(core): fix web_search_call and file_search_call contentBlocks for OpenAI Responses APIUpdated dependencies \[`26488b5`, `aacbe87`, `ca826f6`, `a602c42`, `db7d017`]:
#10304 7560180 Thanks @MunemHashmi! - fix(community): use generous default max_length for Milvus metadata VarChar fields
#10253 07b8619 Thanks @pawel-twardziak! - fix(community): switch JiraProjectLoader to POST+JSON and propagate API errors
#10303 46fc5d8 Thanks @mitchell-fox! - feat(community): add jql and maxTotal params to JiraProjectLoader
#10051 e86ac89 Thanks @FilipZmijewski! - fix(community): valid params check for ChatWatsonx by IBM (#70)
Updated dependencies [26488b5, aacbe87, ca826f6, a602c42, db7d017]:
#10000 71d08c0 Thanks @hntrl! - feat(google): add @langchain/google -- unified Google/Gemini integration
New 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.
Updated dependencies [`0c268f5`, `8103487`]:
8f166b1 Thanks @kaigritun! - fix(core): skip empty text blocks in ChatOpenAI contentBlocksUpdated dependencies [`b5135cc`]:
b5135cc]:
#9990 d5e3db0 Thanks @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 RecursiveUrlLoader against SSRF attacks by integrating validateSafeUrl and replacing string-based URL comparison with origin-based isSameOrigin from the shared SSRF module.
Updated dependencies [`95b191b`]:
95b191b]:
71c3cba Thanks @jacoblee93! - feat(langchain,core): Update prompt pulling params, LangSmith versionUpdated dependencies [`2caf64d`]:
2caf64d]:
41bfea5 Thanks @christian-bromann! - fix(classic/community/core): avoid long lived abort signalsUpdated dependencies [`d71c542`]:
d71c542]:
#9900 a9b5059 Thanks @hntrl! - fix(core): update method signatures to use Partial<CallOptions> for options parameters
Updated invoke, stream, generate, and generatePrompt method signatures across Runnable, BaseChatModel, and BaseLLM to correctly accept Partial<CallOptions> instead of full CallOptions. This aligns the implementation with the RunnableInterface specification and allows users to pass partial options (e.g., { signal: abortedSignal }) without TypeScript errors.
#9900 a9b5059 Thanks @hntrl! - Improved abort signal handling for chat models:
ModelAbortError class in @langchain/core/errors that contains partial output when a model invocation is aborted mid-streaminvoke() now throws ModelAbortError with accumulated partialOutput when aborted during streaming (when using streaming callback handlers)stream() throws a regular AbortError when aborted (since chunks are already yielded to the caller)_generate() and _streamResponseChunks() methodsUpdated dependencies [`4109812`, `4109812`]:
Updated dependencies [`bbed273`]:
bbed273]:
#9830 70387a1 Thanks @bracesproul! - fix: More undefined null errors and tests
#9679 a7c6ec5 Thanks @christian-bromann! - feat(openai): elevate OpenAI image generation outputs to proper image content blocks
#9817 5e04543 Thanks @Ashx098! - read error.status when response.status is absent to avoid retrying OpenAI SDK 4xx
#9819 40b4467 Thanks @MrDockal! - Tool call content returns compacted json
#9815 17e30bd Thanks @hntrl! - fix(core): respect tracingEnabled=false from RunTree when env tracing is enabled
Updated dependencies [`663b9a2`, `5d509ad`]:
230462d Thanks @christian-bromann! - fix(core): preserve index and timestamp fields in _mergeDicts### Patch Changes - #9797 `bd1ab45` Thanks @christian-bromann! - handle undefined error objects in async-caller
bd1ab45 Thanks @christian-bromann! - handle undefined error objects in async-callerUpdated dependencies [`ffebdc2`]:
ffebdc2]:
Updated dependencies [`6bd3a18`, `7d6e1b0`, `80c5c93`]:
23be5af Thanks @christian-bromann! - fix(@langchain/core): add literal name type inference to tool()Nothing published for this version
Updated dependencies [`53dbfc2`]:
53dbfc2]:
a46a249 Thanks @christian-bromann! - fix(core): allow shared object references in serializationNothing published for this version
Updated dependencies [`c26c87e`]:
c26c87e]:
817fc9a Thanks @bracesproul! - fix: _mergeDicts error when merging undefined valuesUpdated dependencies [`5c9fdf2`, `fe8eec1`, `5c9fdf2`]:
#9725 56600b9 Thanks @Orenoid! - fix(langchain): update merge logic for numeric values in mergeDicts
#9736 dc5c2ac Thanks @hntrl! - fix(core): handle circular references in load
#9739 c28d24a Thanks @christian-bromann! - fix(core): use getBufferString for message summarization
#9702 bfcb87d Thanks @christian-bromann! - fix(core): improve interop with Zod
Updated dependencies [`3b0e4c4`]:
3b0e4c4]:
Nothing published for this version
Nothing published for this version
Updated dependencies [`3fe4c43`]:
3fe4c43]:
#9686 df9c42b Thanks @hntrl! - add usage_metadata to metadata in LangChainTracer
#9665 8d2982b Thanks @jacoblee93! - feat(core): Make runnable transform trace in a single payload in LangChainTracer
#9675 af664be Thanks @jacoblee93! - Bump LangSmith dep to 0.4.0
Updated dependencies [`e654022`]:
e654022]:
#9668 a7b2a7d Thanks @bracesproul! - fix: Cannot merge two undefined objects error
#9657 a496c5f Thanks @dqbd! - fix(core): avoid writing to TransformStream in EventStreamCallbackHandler when underlying ReadableStream is closed
#9658 1da1325 Thanks @dqbd! - fix(core): ensure streaming test chat models respect AbortSignal
### Patch Changes - #10134 `a46d28c` Thanks @YJack0000! - feat(groq): add reasoning_effort support to ChatGroq
a46d28c Thanks @YJack0000! - feat(groq): add reasoning_effort support to ChatGroq#9641 005c729 Thanks @christian-bromann! - fix(community/core): various security fixes
#7907 ab78246 Thanks @jasonphillips! - fix(core): handle subgraph nesting better in graph_mermaid
#9589 8cc81c7 Thanks @nathannewyen! - test(core): add test for response_metadata in streamEvents
#9644 f32e499 Thanks @hntrl! - add bindTools to FakeListChatModel
#9508 a28d83d Thanks @shubham-021! - Fix toFormattedString() to properly display nested objects in tool call arguments instead of [object Object]
#9165 2e5ad70 Thanks @pawel-twardziak! - fix(mcp-adapters): preserve timeout from RunnableConfig in MCP tool calls
#9647 e456c66 Thanks @hntrl! - handle missing parent runs in tracer to prevent LangSmith 400 errors
Nothing published for this version
Nothing published for this version
Nothing published for this version
### Patch Changes - #10210 `6d5d1bf` Thanks @colifran! - feat(groq): implement standard schema support for structured output
Updated dependencies \[`3205b35`]:
3205b35]:
#9534 bd2c46e Thanks @christian-bromann! - fix(@langchain/core): update and bundle p-retry, ansi-styles, camelcase and decamelize dependencies
#9544 487378b Thanks @hntrl! - fix tool chunk concat behavior (#9450)
#9505 138e7fb Thanks @chosh-dev! - feat: replace btoa with toBase64Url for encoding in drawMermaidImage
Updated dependencies \[`05936ab`, `798cb70`, `80c790b`]:
add shared query escaping and field validation helpers for Redis filter builders
880e396 Thanks @hntrl! - fix(redis): improve RediSearch query escaping and filter validation
buildCustomQuery tag/text/numeric pathsUpdated dependencies \[`2e28115`]:
2e28115 Thanks @christian-bromann! - feat(deepseek): enable native OpenAI-compatible streamEvents events2e28115]:
2e28115 Thanks @christian-bromann! - feat(cohere): add native streamEvents event conversion2e28115 Thanks @christian-bromann! - feat(cloudflare): add native streamEvents event conversion#10873 a74d574 Thanks @baptistejamin! - chore(mistralai): upgrade to @mistralai/mistralai v2
Also populates response_metadata.model on chat completions (was missing before).
708d360 Thanks @christian-bromann! - allow to concat system messagesRemove @types/uuid from package manifests that rely on @langchain/core/utils/uuid or do not require uuid type stubs directly, and refresh the lockfile
### Patch Changes - #9308 `04bd55c` Thanks @ro0sterjam! - respect JSON schema references in interopZodTransformInputSchema - #9387 `ac0d4fe` Thanks @h
8319201: Export standard converter function utility
Remove @types/uuid from package manifests that rely on @langchain/core/utils/uuid or do not require uuid type stubs directly, and refresh the lockfile
One column per quarter.