Skip to content

Conversation

@pyup-bot
Copy link
Collaborator

@pyup-bot pyup-bot commented Dec 5, 2025

This PR pins langchain to the latest release 1.1.2.

Changelog

1.1.2

Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1


langchain/ollama1.0.3
Patch Changes

-   [9490](https://github.com/langchain-ai/langchainjs/pull/9490) [`57fe46f`](https://github.com/langchain-ai/langchainjs/commit/57fe46fdef09146814bf811dee6e439e01ced9a8) Thanks [christian-bromann](https://github.com/christian-bromann)! - separate thinking content into reasoning_content field


langchain/mongodb1.0.2
Patch Changes

-   [9502](https://github.com/langchain-ai/langchainjs/pull/9502) [`fa8c36e`](https://github.com/langchain-ai/langchainjs/commit/fa8c36e4ba3ab19c30a1ed9fd2e6392fc6778a2c) Thanks [hntrl](https://github.com/hntrl)! - bump mongodb dep


langchain/mcp-adapters1.0.2
Patch Changes

-   [9514](https://github.com/langchain-ai/langchainjs/pull/9514) [`6cecddf`](https://github.com/langchain-ai/langchainjs/commit/6cecddf07f3daa8c45a3da33f04759f8af0eec41) Thanks [strowk](https://github.com/strowk)! - fix: pass cwd to mcp sdk correctly


langchain/google-webauth2.0.1
Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1
 -   langchain/google-common2.0.1


langchain/google-vertexai2.0.1
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-gauth2.0.1


langchain/google-vertexai-web2.0.1
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-webauth2.0.1


langchain/google-genai2.0.1
Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1


langchain/google-gauth2.0.1
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-common2.0.1


langchain/google-common2.0.1
Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1


langchain/google-cloud-sql-pg1.0.2
Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1


langchain/core1.1.1
Patch Changes

-   [9495](https://github.com/langchain-ai/langchainjs/pull/9495) [`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319) Thanks [gsriram24](https://github.com/gsriram24)! - fix: use dynamic import for p-retry to support CommonJS environments

-   [9531](https://github.com/langchain-ai/langchainjs/pull/9531) [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb) Thanks [hntrl](https://github.com/hntrl)! - add `extras` to tools


langchain/community1.0.6
Patch Changes

-   [9501](https://github.com/langchain-ai/langchainjs/pull/9501) [`8b9f66f`](https://github.com/langchain-ai/langchainjs/commit/8b9f66f7212f5fc1607566c130d247c2e17ca546) Thanks [hntrl](https://github.com/hntrl)! - fix community exports (#9494)

-   [9498](https://github.com/langchain-ai/langchainjs/pull/9498) [`31240d4`](https://github.com/langchain-ai/langchainjs/commit/31240d4314ec3bc776fa8aea7c33870c6ffa5a72) Thanks [hntrl](https://github.com/hntrl)! - enable model gateway usage in IBM implementation

-   Updated dependencies \[]:
 -   langchain/classic1.0.5
 -   langchain/openai1.1.3


langchain/aws1.1.0
Minor Changes

-   [9129](https://github.com/langchain-ai/langchainjs/pull/9129) [`6f8fa47`](https://github.com/langchain-ai/langchainjs/commit/6f8fa47388fd5c5d2bc8476e29349720d8fe7784) Thanks [tinque](https://github.com/tinque)! - feat(aws): allow bedrock Application Inference Profile


langchain/anthropic1.2.0
Minor Changes

-   [9531](https://github.com/langchain-ai/langchainjs/pull/9531) [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb) Thanks [hntrl](https://github.com/hntrl)! - support advanced tool use

Patch Changes

-   Updated dependencies \[[`636b994`](https://github.com/langchain-ai/langchainjs/commit/636b99459bf843362298866211c63a7a15c2a319), [`38f0162`](https://github.com/langchain-ai/langchainjs/commit/38f0162b7b2db2be2c3a75ae468728adcb49fdfb)]:
 -   langchain/core1.1.1

1.1.1

Patch Changes

-   [9487](https://github.com/langchain-ai/langchainjs/pull/9487) [`4827945`](https://github.com/langchain-ai/langchainjs/commit/48279457ee44f36cdde175a537e2b12f5866627f) Thanks [hntrl](https://github.com/hntrl)! - constrain lower bound core peer dep


langchain/yandex1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/xai1.0.2
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4)]:
 -   langchain/openai1.1.3


langchain/weaviate1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/textsplitters1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/tavily1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/redis1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/qdrant1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/pinecone1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/ollama1.0.2
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   [9470](https://github.com/langchain-ai/langchainjs/pull/9470) [`960bd46`](https://github.com/langchain-ai/langchainjs/commit/960bd46d5916146c68a8a91fe7126e5408f06458) Thanks [loehde](https://github.com/loehde)! - fix(deps): update ollama dependency to version 0.6.3 and add dimensio…


langchain/nomic1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/mongodb1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/mixedbread-ai1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/mistralai1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/mcp-adapters1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/groq1.0.2
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/google-webauth1.0.4
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`708d360`](https://github.com/langchain-ai/langchainjs/commit/708d360df1869def7e4caaa5995d6e907bbf54cd), [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4), [`21a8374`](https://github.com/langchain-ai/langchainjs/commit/21a83742af89e6a7f29d303f63729d0e31b59fdd), [`10fa2af`](https://github.com/langchain-ai/langchainjs/commit/10fa2afec0b81efd3467e61b59ba5c82e1043de5)]:
 -   langchain/core1.1.0
 -   langchain/google-common2.0.0


langchain/google-vertexai1.0.4
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4)]:
 -   langchain/google-gauth2.0.0


langchain/google-vertexai-web1.0.4
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4)]:
 -   langchain/google-webauth2.0.0


langchain/google-gauth1.0.4
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4), [`21a8374`](https://github.com/langchain-ai/langchainjs/commit/21a83742af89e6a7f29d303f63729d0e31b59fdd)]:
 -   langchain/google-common2.0.0


langchain/google-common1.0.4
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   [9440](https://github.com/langchain-ai/langchainjs/pull/9440) [`21a8374`](https://github.com/langchain-ai/langchainjs/commit/21a83742af89e6a7f29d303f63729d0e31b59fdd) Thanks [manekinekko](https://github.com/manekinekko)! - update polynomial regex to mitigate ReDoS vulnerability in SseStream

-   Updated dependencies \[[`708d360`](https://github.com/langchain-ai/langchainjs/commit/708d360df1869def7e4caaa5995d6e907bbf54cd), [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4), [`10fa2af`](https://github.com/langchain-ai/langchainjs/commit/10fa2afec0b81efd3467e61b59ba5c82e1043de5)]:
 -   langchain/core1.1.0


langchain/google-cloud-sql-pg1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`708d360`](https://github.com/langchain-ai/langchainjs/commit/708d360df1869def7e4caaa5995d6e907bbf54cd), [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4), [`10fa2af`](https://github.com/langchain-ai/langchainjs/commit/10fa2afec0b81efd3467e61b59ba5c82e1043de5)]:
 -   langchain/core1.1.0


langchain/exa1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/deepseek1.0.2
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility

-   Updated dependencies \[[`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4)]:
 -   langchain/openai1.1.3


langchain/cohere1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/cloudflare1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/cerebras1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/baidu-qianfan1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/azure-dynamic-sessions1.0.1
Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/azure-cosmosdb1.1.0
Minor Changes

-   [9439](https://github.com/langchain-ai/langchainjs/pull/9439) [`521ba2c`](https://github.com/langchain-ai/langchainjs/commit/521ba2c5d82e253668d4df47f1c056f5e91b5ff6) Thanks [sinedied](https://github.com/sinedied)! - Implement addMessages for chat histories

Patch Changes

-   [9416](https://github.com/langchain-ai/langchainjs/pull/9416) [`0fe9beb`](https://github.com/langchain-ai/langchainjs/commit/0fe9bebee6710f719e47f913eec1ec4f638e4de4) Thanks [hntrl](https://github.com/hntrl)! - fix 'moduleResultion: "node"' compatibility


langchain/anthropic1.1.3
Patch Changes

-   [9488](https://github.com/langchain-ai/langchainjs/pull/9488) [`cfee39a`](https://github.com/langchain-ai/langchainjs/commit/cfee39a0b867e8cd4ae7bda3d64bba4124be4e10) Thanks [hntrl](https://github.com/hntrl)! - add opus-4.5 to model strings

1.0.6

Patch Changes

-   [9434](https://github.com/langchain-ai/langchainjs/pull/9434) [`f7cfece`](https://github.com/langchain-ai/langchainjs/commit/f7cfecec29bf0f121e1a8b0baface5327d731122) Thanks [deepansh946](https://github.com/deepansh946)! - Updated error handling behaviour of AgentNode


langchain/google-webauth1.0.3
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-common1.0.3


langchain/google-vertexai1.0.3
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-gauth1.0.3


langchain/google-vertexai-web1.0.3
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-webauth1.0.3


langchain/google-genai1.0.3
Patch Changes

-   [9444](https://github.com/langchain-ai/langchainjs/pull/9444) [`39404ac`](https://github.com/langchain-ai/langchainjs/commit/39404acf76e81360054910f417d01df02981a4e6) Thanks [hntrl](https://github.com/hntrl)! - add tier based usage metadata token count

-   [9444](https://github.com/langchain-ai/langchainjs/pull/9444) [`39404ac`](https://github.com/langchain-ai/langchainjs/commit/39404acf76e81360054910f417d01df02981a4e6) Thanks [hntrl](https://github.com/hntrl)! - fix streaming thought signature bug

-   [9444](https://github.com/langchain-ai/langchainjs/pull/9444) [`39404ac`](https://github.com/langchain-ai/langchainjs/commit/39404acf76e81360054910f417d01df02981a4e6) Thanks [hntrl](https://github.com/hntrl)! - add thinkingConfig support in ChatGoogleGenerativeAI

-   [9444](https://github.com/langchain-ai/langchainjs/pull/9444) [`39404ac`](https://github.com/langchain-ai/langchainjs/commit/39404acf76e81360054910f417d01df02981a4e6) Thanks [hntrl](https://github.com/hntrl)! - add cached token counts to usage metadata


langchain/google-gauth1.0.3
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-common1.0.3


langchain/google-common1.0.3



langchain/anthropic1.1.1
Patch Changes

-   [9451](https://github.com/langchain-ai/langchainjs/pull/9451) [`b1deda2`](https://github.com/langchain-ai/langchainjs/commit/b1deda21363b5a1a3f2b7bd77dc1d74764304666) Thanks [hntrl](https://github.com/hntrl)! - fix betas being passed to client when streaming

1.0.5

Patch Changes

-   [9403](https://github.com/langchain-ai/langchainjs/pull/9403) [`944bf56`](https://github.com/langchain-ai/langchainjs/commit/944bf56ff0926e102c56a3073bfde6b751c97794) Thanks [christian-bromann](https://github.com/christian-bromann)! - improvements to toolEmulator middleware

-   [9388](https://github.com/langchain-ai/langchainjs/pull/9388) [`831168a`](https://github.com/langchain-ai/langchainjs/commit/831168a5450bff706a319842626214281204346d) Thanks [hntrl](https://github.com/hntrl)! - use `profile.maxInputTokens` in summarization middleware

-   [9393](https://github.com/langchain-ai/langchainjs/pull/9393) [`f1e2f9e`](https://github.com/langchain-ai/langchainjs/commit/f1e2f9eeb365bae78c8b5991ed41bfed58f25da6) Thanks [christian-bromann](https://github.com/christian-bromann)! - align context editing with summarization interface

-   [9427](https://github.com/langchain-ai/langchainjs/pull/9427) [`bad7aea`](https://github.com/langchain-ai/langchainjs/commit/bad7aea86d3f60616952104c34a33de9561867c7) Thanks [dqbd](https://github.com/dqbd)! - fix(langchain): add tool call contents and tool call ID to improve token count approximation

-   [9396](https://github.com/langchain-ai/langchainjs/pull/9396) [`ed6b581`](https://github.com/langchain-ai/langchainjs/commit/ed6b581e525cdf5d3b29abb1e17ca6169554c1b5) Thanks [christian-bromann](https://github.com/christian-bromann)! - rename exit behavior from throw to error


langchain/openai1.1.2
Patch Changes

-   [9408](https://github.com/langchain-ai/langchainjs/pull/9408) [`415cb0b`](https://github.com/langchain-ai/langchainjs/commit/415cb0bfd26207583befdb02367bd12a46b33d51) Thanks [sinedied](https://github.com/sinedied)! - Fix missing and inconsistent user agent headers

-   [9301](https://github.com/langchain-ai/langchainjs/pull/9301) [`a2ad61e`](https://github.com/langchain-ai/langchainjs/commit/a2ad61e787a06a55a615f63589a65ada05927792) Thanks [sinedied](https://github.com/sinedied)! - support callable function for apiKey


langchain/google-webauth1.0.2
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-common1.0.2


langchain/google-vertexai1.0.2
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-gauth1.0.2


langchain/google-vertexai-web1.0.2
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-webauth1.0.2


langchain/google-genai1.0.2
Patch Changes

-   [9441](https://github.com/langchain-ai/langchainjs/pull/9441) [`269e5ba`](https://github.com/langchain-ai/langchainjs/commit/269e5bae04c76fdfbd42df66a97061bb0b93a834) Thanks [hntrl](https://github.com/hntrl)! - add function calling thought signature support


langchain/google-gauth1.0.2
Patch Changes

-   Updated dependencies \[]:
 -   langchain/google-common1.0.2


langchain/google-common1.0.2



langchain/community1.0.4
Patch Changes

-   [9326](https://github.com/langchain-ai/langchainjs/pull/9326) [`3e0cab6`](https://github.com/langchain-ai/langchainjs/commit/3e0cab61b32fae271936770b822cb9644f68b637) Thanks [ayanyev](https://github.com/ayanyev)! - Milvus vector store client: ignore auto-calculated fields in collection schema during payload validation

-   Updated dependencies \[[`415cb0b`](https://github.com/langchain-ai/langchainjs/commit/415cb0bfd26207583befdb02367bd12a46b33d51), [`a2ad61e`](https://github.com/langchain-ai/langchainjs/commit/a2ad61e787a06a55a615f63589a65ada05927792), [`34c472d`](https://github.com/langchain-ai/langchainjs/commit/34c472d129c9c3d58042fad6479fd15e0763feaf)]:
 -   langchain/openai1.1.2
 -   langchain/classic1.0.4


langchain/classic1.0.4
Patch Changes

-   [9379](https://github.com/langchain-ai/langchainjs/pull/9379) [`34c472d`](https://github.com/langchain-ai/langchainjs/commit/34c472d129c9c3d58042fad6479fd15e0763feaf) Thanks [kenowessels](https://github.com/kenowessels)! - OpenAPIToJSONSchema required from nested schema

-   Updated dependencies \[[`415cb0b`](https://github.com/langchain-ai/langchainjs/commit/415cb0bfd26207583befdb02367bd12a46b33d51), [`a2ad61e`](https://github.com/langchain-ai/langchainjs/commit/a2ad61e787a06a55a615f63589a65ada05927792)]:
 -   langchain/openai1.1.2


langchain/aws1.0.2
Patch Changes

-   [9382](https://github.com/langchain-ai/langchainjs/pull/9382) [`f464366`](https://github.com/langchain-ai/langchainjs/commit/f4643668158a702d086da1defcbfd6ee3f050810) Thanks [deepansh946](https://github.com/deepansh946)! - fix handling of multiple tool types in convertToConverseTools fn


langchain/anthropic1.1.0
Minor Changes

-   [9424](https://github.com/langchain-ai/langchainjs/pull/9424) [`f17b2c9`](https://github.com/langchain-ai/langchainjs/commit/f17b2c9db047fab2d1db2d9aa791ec220cc9dd0a) Thanks [hntrl](https://github.com/hntrl)! - add support for `betas` param

-   [9424](https://github.com/langchain-ai/langchainjs/pull/9424) [`f17b2c9`](https://github.com/langchain-ai/langchainjs/commit/f17b2c9db047fab2d1db2d9aa791ec220cc9dd0a) Thanks [hntrl](https://github.com/hntrl)! - add support for native structured output

Patch Changes

-   [9424](https://github.com/langchain-ai/langchainjs/pull/9424) [`f17b2c9`](https://github.com/langchain-ai/langchainjs/commit/f17b2c9db047fab2d1db2d9aa791ec220cc9dd0a) Thanks [hntrl](https://github.com/hntrl)! - bump sdk version

1.0.4

Patch Changes

- b401680: avoid invalid message order after summarization
- f63fc0f: fix(langchain): export ToolRuntime from langchain

langchain/openai==1.1.0
Minor Changes

- 8319201: hoist message/tool conversion utilities from classes

langchain/ollama==1.0.1
Patch Changes

- a2bce18: fix(ollama): support parsing structured output from tool calls

langchain/core==1.0.4
Patch Changes

- 8319201: Export standard converter function utility

langchain/community==1.0.2
Patch Changes

- b17762a: fix(community): export type properly in duckduckgo_search
- e4a3b3b: improve(pdf-loader): update error message to specify support for pdf-parse v1 only
- ecc7a8a: swap problematic eval package
- Updated dependencies [8319201]
- Updated dependencies [4906522]
- langchain/openai1.1.0
- langchain/classic1.0.2

langchain/classic==1.0.2
Patch Changes

- Updated dependencies [8319201]
- Updated dependencies [4906522]
- langchain/openai1.1.0
- langchain/textsplitters1.0.0

langchain/aws==1.0.1
Patch Changes

- bce4e45: fix(aws): conditional inference config and system message | ChatBedrockConverse

1.0.3

Patch Changes

- f1583cd: allow for model strings in summarization middleware
- e960f97: check message property when pulling chat models for vercel compat
- 66fc10c: fix(langchain): don't allow default or optional context schemas
- 0a8a23b: feat(langchain/core): support of ToolRuntime
- b38be50: Add missing ToolMessage in toolStrategy structured output
- 42930b5: fix(langchain): improved state schema typing

langchain/core==1.0.3
Patch Changes

- 0a8a23b: feat(langchain/core): support of ToolRuntime

1.0.2

What's Changed

Patch Changes

- 2e45c43: remove bad dynamic import for LS
- 28eceac: preserve full model name when deciding model provider

langchain/core==1.0.2
What's Changed

Patch Changes

- 6426eb6: fix chunks constructed with tool calls + chunks
- 619ae64: Add `BaseMessage.toFormattedString()`

langchain/core==0.3.79
What's Changed

Patch Changes

- 1063b43: fix chunks constructed with tool calls + chunks

langchain/community==1.0.1
What's Changed

Patch Changes

- Updated dependencies [dda9ea4]
- langchain/classic1.0.1
- langchain/openai1.0.0

langchain/classic==1.0.1
What's changed

Patch Changes

- dda9ea4: reinstate `OpenAIModerationChain`
- langchain/textsplitters1.0.0
- langchain/openai1.0.0

langchain/anthropic==0.3.33
What's changed

Patch Changes

- 247cfb6: support Haiku 4.5 topP parameter

1.0.0

🎉 **LangChain v1.0** is here! This release provides a focused, production-ready foundation for building agents. We've streamlined the framework around three core improvements: **`createAgent`**, **standard content blocks**, and a **simplified package structure**. See the [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for complete details.

✨ Major Features

`createAgent` - A new standard for building agents

`createAgent` is the new standard way to build agents in LangChain 1.0. It provides a simpler interface than `createReactAgent` from LangGraph while offering greater customization potential through middleware.

**Key features:**

- **Clean, intuitive API**: Build agents with minimal boilerplate
- **Built on LangGraph**: Get persistence, streaming, human-in-the-loop, and time travel out of the box
- **Middleware-first design**: Highly customizable through composable middleware
- **Improved structured output**: Generate structured outputs in the main agent loop without additional LLM calls

Example:

typescript
import { createAgent } from "langchain";

const agent = createAgent({
model: "anthropic:claude-sonnet-4-5-20250929",
tools: [getWeather],
systemPrompt: "You are a helpful assistant.",
});

const result = await agent.invoke({
messages: [{ role: "user", content: "What is the weather in Tokyo?" }],
});

console.log(result.content);


Under the hood, `createAgent` is built on the basic agent loop—calling a model using LangGraph, letting it choose tools to execute, and then finishing when it calls no more tools.

**Built on LangGraph features (work out of the box):**

- **Persistence**: Conversations automatically persist across sessions with built-in checkpointing
- **Streaming**: Stream tokens, tool calls, and reasoning traces in real-time
- **Human-in-the-loop**: Pause agent execution for human approval before sensitive actions
- **Time travel**: Rewind conversations to any point and explore alternate paths

**Structured output improvements:**

- Generate structured outputs in the main loop instead of requiring an additional LLM call
- Models can choose between calling tools or using provider-side structured output generation
- Significant cost reduction by eliminating extra LLM calls

Example:

typescript
import { createAgent } from "langchain";
import * as z from "zod";

const weatherSchema = z.object({
temperature: z.number(),
condition: z.string(),
});

const agent = createAgent({
model: "openai:gpt-4o-mini",
tools: [getWeather],
responseFormat: weatherSchema,
});

const result = await agent.invoke({
messages: [{ role: "user", content: "What is the weather in Tokyo?" }],
});

console.log(result.structuredResponse);


For more information, see [Agents documentation](https://docs.langchain.com/oss/javascript/langchain/agents).

Middleware

Middleware is what makes `createAgent` highly customizable, raising the ceiling for what you can build. Great agents require **context engineering**—getting the right information to the model at the right time. Middleware helps you control dynamic prompts, conversation summarization, selective tool access, state management, and guardrails through a composable abstraction.

**Prebuilt middleware** for common patterns:

typescript
import {
createAgent,
summarizationMiddleware,
humanInTheLoopMiddleware,
piiRedactionMiddleware,
} from "langchain";

const agent = createAgent({
model: "anthropic:claude-sonnet-4-5-20250929",
tools: [readEmail, sendEmail],
middleware: [
 piiRedactionMiddleware({ patterns: ["email", "phone", "ssn"] }),
 summarizationMiddleware({
   model: "anthropic:claude-sonnet-4-5-20250929",
   maxTokensBeforeSummary: 500,
 }),
 humanInTheLoopMiddleware({
   interruptOn: {
     sendEmail: {
       allowedDecisions: ["approve", "edit", "reject"],
     },
   },
 }),
] as const,
});


**Custom middleware** with lifecycle hooks:

| Hook            | When it runs             | Use cases                               |
| --------------- | ------------------------ | --------------------------------------- |
| `beforeAgent`   | Before calling the agent | Load memory, validate input             |
| `beforeModel`   | Before each LLM call     | Update prompts, trim messages           |
| `wrapModelCall` | Around each LLM call     | Intercept and modify requests/responses |
| `wrapToolCall`  | Around each tool call    | Intercept and modify tool execution     |
| `afterModel`    | After each LLM response  | Validate output, apply guardrails       |
| `afterAgent`    | After agent completes    | Save results, cleanup                   |

Example custom middleware:

typescript
import { createMiddleware } from "langchain";

const contextSchema = z.object({
userExpertise: z.enum(["beginner", "expert"]).default("beginner"),
});

const expertiseBasedToolMiddleware = createMiddleware({
wrapModelCall: async (request, handler) => {
 const userLevel = request.runtime.context.userExpertise;
 if (userLevel === "expert") {
   const tools = [advancedSearch, dataAnalysis];
   return handler(request.replace("openai:gpt-5", tools));
 }
 const tools = [simpleSearch, basicCalculator];
 return handler(request.replace("openai:gpt-5-nano", tools));
},
});

const agent = createAgent({
model: "anthropic:claude-sonnet-4-5-20250929",
tools: [simpleSearch, advancedSearch, basicCalculator, dataAnalysis],
middleware: [expertiseBasedToolMiddleware],
contextSchema,
});


For more information, see the [complete middleware guide](https://docs.langchain.com/oss/javascript/langchain/middleware).

Simplified Package

LangChain v1 streamlines the `langchain` package namespace to focus on essential building blocks for agents. The package exposes only the most useful and relevant functionality (most re-exported from `langchain/core` for convenience).

**What's in the core `langchain` package:**

- `createAgent` and agent-related utilities
- Core message types and content blocks
- Middleware infrastructure
- Tool definitions and schemas
- Prompt templates
- Output parsers
- Base runnable abstractions

🔄 Migration Notes

`langchain/classic` for Legacy Functionality

Legacy functionality has moved to [`langchain/classic`](https://www.npmjs.com/package/langchain/classic) to keep the core package lean and focused.

**What's in `langchain/classic`:**

- Legacy chains and chain implementations
- The indexing API
- [`langchain/community`](https://www.npmjs.com/package/langchain/community) exports
- Other deprecated functionality

**To migrate legacy code:**

1. Install `langchain/classic`:

bash
npm install langchain/classic


2. Update your imports:

typescript
import { ... } from "langchain"; // [!code --]
import { ... } from "langchain/classic"; // [!code ++]

import { ... } from "langchain/chains"; // [!code --]
import { ... } from "langchain/classic/chains"; // [!code ++]


Upgrading to v1

Install the v1 packages:

bash
npm install langchain1.0.0 langchain/core1.0.0


📚 Additional Resources

- [Release Notes](https://docs.langchain.com/oss/python/releases/langchain-v1)
- [Migration Guide](https://docs.langchain.com/oss/javascript/migrate/langchain-v1)
- [Agents Documentation](https://docs.langchain.com/oss/javascript/langchain/agents)
- [Middleware Guide](https://blog.langchain.com/agent-middleware/)

langchain/yandex==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/xai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/weaviate==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/vertexai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/vertexai-web==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/textsplitters==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/tavily==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/redis==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/qdrant==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/pinecone==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/openai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/ollama==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/nomic==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/mongodb==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/mixedbread-ai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/mistralai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/mcp-adapters==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/groq==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/google-webauth==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/google-genai==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/google-gauth==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/google-common==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/google-cloud-sql-pg==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/exa==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/deepseek==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/core==1.0.0
🎉 **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](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for more details.

✨ Major Features

Standard content blocks

A new unified API for accessing modern LLM features across all providers:

- **New `contentBlocks` property**: 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:

typescript
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](https://docs.langchain.com/oss/javascript/langchain/messages#content).

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/core` package 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:

1. Update to `langchain/corenext`:

bash
npm install langchain/core1.0.0


2. Use the new `contentBlocks` property to access rich content:

typescript
const response = await model.invoke(messages);
console.log(response.contentBlocks); // New API
console.log(response.content); // Legacy API still works


3. For middleware and `createAgent`, install `langchainnext`:

bash
npm install langchain1.0.0 langchain/core1.0.0


📚 Additional Resources

- [Release Notes](https://docs.langchain.com/oss/python/releases/langchain-v1)
- [Migration Guide](https://docs.langchain.com/oss/javascript/migrate/langchain-v1)
- [Content Blocks Documentation](https://docs.langchain.com/oss/javascript/langchain/messages#content)
- [Agents Documentation](https://docs.langchain.com/oss/javascript/langchain/agents)

langchain/community==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/cohere==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/cloudflare==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/classic==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/cerebras==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/baidu-qianfan==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/azure-dynamic-sessions==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/azure-cosmosdb==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/aws==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

langchain/anthropic==1.0.0
What's Changed

This release updates the package for compatibility with LangChain v1.0. See the v1.0 [release notes](https://docs.langchain.com/oss/javascript/releases/langchain-v1) for details on what's new.

1.0.0alpha.8

🚀 New Features

- **Context Editing Middleware** (9118): Added middleware for editing conversation context dynamically
- **Tool Call Limit Middleware** (9121): Implemented middleware to limit the number of tool calls during agent execution
- **Retry Model Request Hook** (9128): Added retry functionality for model requests in middleware
- **Call Count Tracking** (9090): Introduced call counts through private state for better monitoring and control
- **Custom Interrupted Tool Descriptions** (9116): Added ability to pass in a description factory for interrupted tool calls
- **PII Redaction Middleware** (9058): Added middleware for automatically redacting personally identifiable information
- **Perplexity Support**: Added Perplexity provider support to universal chat model

🐛 Bug Fixes

- **LLM Tool Selector Implementation** (9127): Updated implementation of LLMToolSelector middleware for improved reliability
- **LangGraph Integration** (9117): Fixed integration issues with LangGraph
- **Tool Instance Handling** (9119): Fixed tools in ModelRequest to return tool instances instead of serialized objects
- **TypeScript Type Inference** (9087): Exported all symbols to enable proper TypeScript type inference
- **Prompt Caching Immutability** (9086): Fixed PromptCachingMiddleware to return new message objects instead of modifying existing ones
- **Input Type Support** (9080): Improved input types to support a wider range of type definitions
- **Tools Node Creation** (9074): Fixed to only create tools node for client-provided tools
- **Planning Middleware Adjustments** (9070): Minor improvements to planning middleware behavior
- **Hub Prompt Schema Binding** (9057): Fixed schema binding for various types of pulled hub prompts

1.0.0alpha.7

🚀 New Features

- **Todo Middleware** (9051): Added new todo middleware functionality for agent workflows
- **LLM Tool Selector Middleware** (9050): Implemented `llmToolSelectorMiddleware` (bigTool) for intelligent tool selection
- **Middleware Tool Definition** (9046): Middleware can now define their own tools dynamically
- **Dynamic Prompt Middleware** (8993): Added built-in middleware for dynamic prompt generation
- **Unsupported Model Behavior** (9039): Added `unsupportedModelBehavior` property to anthropic middleware

🐛 Bug Fixes

- **System Prompt Consistency** (9045): Fixed system prompt handling across all agent components
- **Zod Interoperability** (9029): Improved compatibility between Zod v3 and v4
- **Structured Output Handling** (9033): Improved structured output processing for agents
- **Graph Support for Jumps** (9035): Added statically typed graph support for agent jumps
- **Tool Configuration Naming** (9034): Renamed `toolConfigs` to `interruptOn` for clarity
- **LLM Property Removal** (9017): Removed `llm` prop from middleware agent
- **Message Handling**: Fixed grabbing last AIMessage from list instead of just looking at last message
- **Memory Saver Export** (8996): Removed incorrect MemorySaver re-export
- **Middleware Naming** (8912): Fixed "middlewares" property naming to "middleware"
- **Cache Control Verification**: Actually verify cache control values in usage response
- **Message Instance Checking** (8905): Use `isInstance` for message validation

📦 Dependency and Build Fixes

- **OpenAI Provider Dependency** (8920): Removed dependency to openai provider package (alpha.6)
- **Internal ESLint Package** (8770): Created internal ESLint package (alpha.6)
- **Zod v4 Support** (8792): Updated to support Zod v4 (alpha.6)
- **Test Console Logs** (8998): Removed console logs in test files (alpha.7)


langchain/core==1.0.0-alpha.6
🚀 New Features

- **Google AI Standard Content** (9024): Added comprehensive standard content support for Google GenAI and Vertex AI
- **AWS Bedrock Standard Content** (9013): Implemented standard content support for AWS Bedrock Converse
- **Server Tool Blocks** (9000): Added server tool blocks to standard content system
- **Zod Interoperability** (9029): Improved compatibility between Zod v3 and v4

🐛 Bug Fixes

- **Response Metadata Type Mismatch** (9010): Fixed type mismatches in response metadata
- **Message Index Cleanup** (8972): Refined message exports

🔧 Technical Improvements

- **Google AI Integration**: Significantly enhanced Google GenAI and Vertex AI block translators
- **AWS Bedrock Integration**: Major improvements to Bedrock Converse support
- **Content Index Updates**: Enhanced content module exports

1.0.0alpha.5

What's Changed

* feat(langchain) new middleware concept for createAgent by christian-bromann in https://github.com/langchain-ai/langchainjs/pull/8851

**Full Changelog**: https://github.com/langchain-ai/langchainjs/compare/langchain==1.0.0-alpha.4...langchain==1.0.0-alpha.5

langchain/core==0.3.75
What's Changed
* fix(core): Fix deep nesting of runnables within traceables by jacoblee93 in https://github.com/langchain-ai/langchainjs/pull/8853

**Full Changelog**: https://github.com/langchain-ai/langchainjs/compare/langchain/core==0.3.74...langchain/core==0.3.75

langchain/community==0.3.55
What's Changed
* fix(community): bump firebase-admin devDependencies by hntrl in https://github.com/langchain-ai/langchainjs/pull/8861
* fix(community): URL encode paths in GitHub document loader by hntrl in https://github.com/langchain-ai/langchainjs/pull/8860

**Full Changelog**: https://github.com/langchain-ai/langchainjs/compare/langchain/community==0.3.54...langchain/community==0.3.55

langchain/anthropic==0.3.27
What's Changed
* fix(anthropic): opus-4.1 thinking by taiichiro-nagase in https://github.com/langchain-ai/langchainjs/pull/8856

New Contributors
* taiichiro-nagase made their first contribution in https://github.com/langchain-ai/langchainjs/pull/8856

**Full Changelog**: https://github.com/langchain-ai/langchainjs/compare/langchain==0.3.33...langchain/anthropic==0.3.27

1.0.0alpha.1

**Compare:** [https://github.com/langchain-ai/langchainjs/compare/langchain==0.3.30...langchain==1.0.0-alpha.1](https://github.com/langchain-ai/langchainjs/compare/langchain==0.3.30...langchain==1.0.0-alpha.1)

---

💥 Breaking changes

* **Require Node.js ≥ 20**
Langchain packages now require Node 20+ (`.nvmrc` is on Node 24 for development). Update your engines and CI accordingly. ([GitHub][1])

json
// package.json
{ "engines": { "node": ">=20" } }


* **Removed legacy subpath exports (cleaner surface area)**

* `langchain/schema/prompt_template` → **use** `langchain/prompts`. ([GitHub][2], [api.js.langchain.com][3])

 diff
 - import { PromptTemplate } from "langchain/schema/prompt_template";
 + import { PromptTemplate } from "langchain/prompts";
 
* `langchain/schema/query_constructor` → **use** `langchain/chains/query_constructor`. ([GitHub][2], [v03.api.js.langchain.com][4], [Langchain][5])

 diff
 - import type { AttributeInfo } from "langchain/schema/query_constructor";
 + import type { AttributeInfo } from "langchain/chains/query_constructor";
 
* `langchain/runnables/remote` export removed. If you used this entrypoint, migrate off this subpath (no 1:1 replacement export in `langchain` package). ([GitHub][6])
* `langchain/smith` export path removed from `langchain`. Use the separate `langsmith` package and opt-in (see below). ([GitHub][7])

* **Callbacks removed from `langchain`**
The `./callbacks` entrypoint is gone. Prefer LCEL observability (runnables), agent/tool messages, or provider-native hooks instead. ([GitHub][8])

diff
- import { ... } from "langchain/callbacks";
// Replace with runnable config / tracing via LangSmith (optional) or agent nodes.


---

✨ Features

* **`langchain` now exports most important user primitives**
The `langchain` package now exports the most important user primitives, including `tool`, `HumanMessage`, `AIMessage`, `SystemMessage`, `ToolNode`, `createAgent`, and more.

ts
import { tool, HumanMessage, createAgent } from "langchain";


* **`createAgent` is now part of core `langchain`**
The React-style agent lives under the `langchain` project (with examples + tests). Import directly from `langchain`. ([GitHub][9])

ts
import { createAgent, HumanMessage, tool } from "langchain";
import { z } from "zod";

const getWeather = tool({
 name: "getWeather",
 description: "Get current weather by city",
 schema: z.object({ city: z.string() }),
 func: async ({ city }) => `Sunny in ${city}`
});

const agent = await createAgent({
 // New: pass a model by name (string) or a model instance
 model: "claude-3-5-sonnet-20240620",
 tools: [getWeather],
 responseFormat: z.object({ answer: z.string() }),
});

const res = await agent.invoke(new HumanMessage("Weather in SF?"));
console.log(res);


Now you can pass in a **“model as string”** option to define the model to use. ([GitHub][10])

* **`ToolNode` exported from `langchain`**
Build agent graphs that execute tools as a node. This makes tool execution composable within LCEL/graph flows.

ts
import { ToolNode, tool, HumanMessage } from "langchain";

const fail = tool({
 name: "alwaysFails",
 description: "Demo failing tool",
 schema: {},
 func: async () => { throw new Error("Boom"); }
});

const node = new ToolNode([fail]);
const out = await node.invoke({ messages: [new HumanMessage("Try it")] });


* **Default tool-error handling in agents**
When `handleToolErrors` is **`true` (default)**, tool exceptions are caught and converted into a **`ToolMessage`** so the agent can recover. Set it to `false` to surface raw errors for strict workflows. ([GitHub][11])

ts
import { ToolNode } from "langchain/agents";

// default: handleToolErrors: true → returns a ToolMessage with error text
const forgiving = new ToolNode([/* tools */]);

// strict: throw on tool error
const strict = new ToolNode([/* tools */], { handleToolErrors: false });


---

🐛 Fixes

* **`langsmith` made optional**
LangSmith is no longer a hard dependency; the package is loaded dynamically only when you use features that need it. If you rely on eval/tracing/hub, add it explicitly:
`pnpm add langsmith` (or yarn/npm). ([GitHub][12])

* **Removed `js-tiktoken` dependency**
The package was dropped from deps; related types are sourced via the relevant provider packages (e.g. `langchain/openai`). If you had direct imports, adjust accordingly. ([GitHub][13])

---

🧹 Chores / Internal

* **New tsdown-based build system** (faster, simpler internal builds). ([GitHub][14])
* **Repo migrated to `pnpm`** (lockfile + scripts updated). ([GitHub][15])
* Rearranged packages and updated CI/workflows. ([GitHub][16])
* Removed experimental and unused files/exports (`./indexes`, `./document_transformers/openai_functions`, agents cleanup). User-visible API impact covered above via export removals; the rest is housekeeping to keep the surface tight. ([GitHub][18])
* Environment tests rewritten in TS and expanded to verify export maps across bundlers/runtimes. ([GitHub][19])

---

🧭 Migration quick-guide

1. **Node version**

* Set `engines.node` to `>=20` and update CI runners. ([GitHub][1])

2. **Imports / subpaths**

* `schema/prompt_template` → `langchain/prompts` (e.g., `PromptTemplate`). ([GitHub][2], [api.js.langchain.com][3])
* `schema/query_constructor` → `langchain/chains/query_constructor` (IR types, translators, etc.). ([GitHub][2], [v03.api.js.langchain.com][4], [Langchain][5])
* Remove `langchain/runnables/remote` usage; no longer exported. ([GitHub][6])
* Remove `langchain/smith` import; **install** and import from `langsmith` if needed. ([GitHub][7])

3. **Agents**

* Import prebuilt agents from `langchain` directly, e.g. `import { createAgent } from "langchain"`.
* You can pass **`model` as a model name string** to `createAgent`. ([GitHub][10])
  ts
  const agent = createAgent({
    model: "openai:gpt-4o-mini",
    tools: [/* tools */],
    responseFormat: z.object({ answer: z.string() }),
  });
  
* Use `ToolNode` to encapsulate tool execution in graphs.
* Decide on error policy: default soft-handling vs strict throws in `ToolNode` via `handleToolErrors`. ([GitHub][11])

4. **LangSmith & tokenization**

* Add `langsmith` explicitly if you use tracing/eval/hub. ([GitHub][12])
* If you previously relied on `js-tiktoken`, remove it from your app unless you need it directly. ([GitHub][13])

[1]: https://github.com/langchain-ai/langchainjs/pull/8773/files "break(*): bump required Node.js version to v20 by christian-bromann · Pull Request #8773 · langchain-ai/langchainjs · GitHub"
[2]: https://github.com/langchain-ai/langchainjs/pull/8624/files "chore(langchain): remove `./schema/*` export from `langchain` package by christian-bromann · Pull Request #8624 · langchain-ai/langchainjs · GitHub"
[3]: https://api.js.langchain.com/classes/langchain_core_prompts.PromptTemplate.html?utm_source=chatgpt.com "Class PromptTemplate<RunInput, PartialVariableName>"
[4]: https://v03.api.js.langchain.com/modules/langchain.chains_query_constructor.html?utm_source=chatgpt.com "Module chains/query_constructor"
[5]: https://js.langchain.com/docs/how_to/query_constructing_filters/?utm_source=chatgpt.com "How to construct filters"
[6]: https://github.com/langchain-ai/langchainjs/pull/8623/files "chore(langchain): remove `./runnables/remote` export from `langchain` package by christian-bromann · Pull Request #8623 · langchain-ai/langchainjs · GitHub"
[7]: https://github.com/langchain-ai/langchainjs/pull/8626/files "chore(langchain): remove `./smith` export path by christian-bromann · Pull Request #8626 · langchain-ai/langchainjs · GitHub"
[8]: https://github.com/langchain-ai/langchainjs/pull/8605/files "chore(v1): remove callbacks from langchain by christian-bromann · Pull Request #8605 · langchain-ai/langchainjs · GitHub"
[9]: https://github.com/langchain-ai/langchainjs/pull/8789/files "feat(agents): migrate createAgent to core LangChain project by christian-bromann · Pull Request #8789 · langchain-ai/langchainjs · GitHub"
[10]: https://github.com/langchain-ai/langchainjs/pull/8806/files "feat(agents): allow createReactAgent to take in a model as string property by christian-bromann · Pull Request #8806 · langchain-ai/langchainjs · GitHub"
[11]: https://github.com/langchain-ai/langchainjs/pull/8810/files "fix(langchain): handle tool errors when handleToolErrors is set to `true` (default) by christian-bromann · Pull Request #8810 · langchain-ai/langchainjs · GitHub"
[12]: https://github.com/langchain-ai/langchainjs/pull/8708/files "fix(langchain): make `langsmith` an optional dependency by christian-bromann · Pull Request #8708 · langchain-ai/langchainjs · GitHub"
[13]: https://github.com/langchain-ai/langchainjs/pull/8712/files "fix(langchain): remove `js-tiktoken` dependency by christian-bromann · Pull Request #8712 · langchain-ai/langchainjs · GitHub"
[14]: https://github.com/langchain-ai/langchainjs/pull/8604 "chore(v1): remove file system cache from langchain by christian-bromann · Pull Request #8604 · langchain-ai/langchainjs · GitHub"
[15]: https://github.com/langchain-ai/langchainjs/pull/8608 "chore: rearrange packages by hntrl · Pull Request #8608 · langchain-ai/langchainjs · GitHub"
[16]: https://github.com/langchain-ai/langchainjs/pull/8613 "fix(build): change script name to avoid double compilation by christian-bromann · Pull Request #8613 · langchain-ai/langchainjs · GitHub"
[17]: https://github.com/langchain-ai/langchainjs/pull/8740/files "chore(langchain): v1 clean up `./document_transformers/openai_functions` by christian-bromann · Pull Request #8740 · langchain-ai/langchainjs · GitHub"
[18]: https://github.com/langchain-ai/langchainjs/pull/8741/files "chore(langchain) v1 clean up `./indexes` by christian-bromann · Pull Request #8741 · langchain-ai/langchainjs · GitHub"
[19]: https://github.com/langchain-ai/langchainjs/pull/8614 "refactor: rewrite environment tests with TypeScript test runner and package verification by christian-bromann · Pull Request #8614 · langchain-ai/langchainjs · GitHub"
[20]: https://github.com/langchain-ai/langchainjs/pull/8599 "chore(internal): add new package for tsdown build by christian-bromann · Pull Request #8599 · langchain-ai/langchainjs · GitHub"


langchain/core==1.0.0-alpha.2
What's Changed
* chore(langchain): rebase main changes by hntrl in https://github.com/langchain-ai/langchainjs/pull/8811
* fix(langchain): port and export AgentRuntime by christian-bromann in https://github.com/langchain-ai/langchainjs/pull/8829

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants