# @langchain/groq

## 1.1.5

### Patch Changes

- [#10134](https://github.com/langchain-ai/langchainjs/pull/10134) [`a46d28c`](https://github.com/langchain-ai/langchainjs/commit/a46d28c769da3875916987618058765a572cd163) Thanks [@YJack0000](https://github.com/YJack0000)! - feat(groq): add reasoning_effort support to ChatGroq

## 1.1.4

### Patch Changes

- [#10210](https://github.com/langchain-ai/langchainjs/pull/10210) [`6d5d1bf`](https://github.com/langchain-ai/langchainjs/commit/6d5d1bf96a9b76a595661a8a1ea7ea4f89c9a500) Thanks [@colifran](https://github.com/colifran)! - feat(groq): implement standard schema support for structured output

## 1.1.3

### Patch Changes

- [#10106](https://github.com/langchain-ai/langchainjs/pull/10106) [`9f30267`](https://github.com/langchain-ai/langchainjs/commit/9f30267e95a2a42fac71f1d3674b84c5a190dbbc) Thanks [@hntrl](https://github.com/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.

## 1.1.2

### Patch Changes

- [#10080](https://github.com/langchain-ai/langchainjs/pull/10080) [`b583729`](https://github.com/langchain-ai/langchainjs/commit/b583729e99cf0c035630f6b311c4d069a1980cca) Thanks [@hntrl](https://github.com/hntrl)! - Add string-model constructor overloads for chat models (with supporting tests where applicable).

## 1.1.1

### Patch Changes

- [#10078](https://github.com/langchain-ai/langchainjs/pull/10078) [`7be50a7`](https://github.com/langchain-ai/langchainjs/commit/7be50a7014d7622e0ab8d303dfc9c633ebc96333) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(\*): update model profiles

## 1.1.0

### Minor Changes

- [#9923](https://github.com/langchain-ai/langchainjs/pull/9923) [`dd31da9`](https://github.com/langchain-ai/langchainjs/commit/dd31da9c09683996090cbb5388731c091c8f2f81) Thanks [@eusoubrasileiro](https://github.com/eusoubrasileiro)! - feat(groq): add native JSON Schema structured output for gpt-oss models

## 1.0.4

### Patch Changes

- [#9900](https://github.com/langchain-ai/langchainjs/pull/9900) [`a9b5059`](https://github.com/langchain-ai/langchainjs/commit/a9b50597186002221aaa4585246e569fa44c27c8) Thanks [@hntrl](https://github.com/hntrl)! - Improved abort signal handling for chat models:
  - Added `ModelAbortError` class in `@langchain/core/errors` that contains partial output when a model invocation is aborted mid-stream
  - `invoke()` 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)
  - All provider implementations now properly check and propagate abort signals in both `_generate()` and `_streamResponseChunks()` methods
  - Added standard tests for abort signal behavior

- [#9900](https://github.com/langchain-ai/langchainjs/pull/9900) [`a9b5059`](https://github.com/langchain-ai/langchainjs/commit/a9b50597186002221aaa4585246e569fa44c27c8) Thanks [@hntrl](https://github.com/hntrl)! - fix(providers): add proper abort signal handling for invoke and stream operations
  - Added early abort check (`signal.throwIfAborted()`) at the start of `_generate` methods to immediately throw when signal is already aborted
  - Added abort signal checks inside streaming loops in `_streamResponseChunks` to return early when signal is aborted
  - Propagated abort signals to underlying SDK calls where applicable (Google GenAI, Google Common/VertexAI, Cohere)
  - Added standard tests for abort signal behavior in `@langchain/standard-tests`

  This enables proper cancellation behavior for both invoke and streaming operations, and allows fallback chains to correctly proceed to the next runnable when the previous one is aborted.

## 1.0.3

### Patch Changes

- [#9777](https://github.com/langchain-ai/langchainjs/pull/9777) [`3efe79c`](https://github.com/langchain-ai/langchainjs/commit/3efe79c62ff2ffe0ada562f7eecd85be074b649a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(core): properly elevate reasoning tokens

## 1.0.2

### 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

## 1.0.1

### Patch Changes

- [#9387](https://github.com/langchain-ai/langchainjs/pull/9387) [`ac0d4fe`](https://github.com/langchain-ai/langchainjs/commit/ac0d4fe3807e05eb2185ae8a36da69498e6163d4) Thanks [@hntrl](https://github.com/hntrl)! - Add `ModelProfile` and `.profile` properties to ChatModel

## 1.0.0

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.

## 0.2.4

### Patch Changes

- 2808057: fix(groq): Support generic messages in messageToGroqRole