[PR #161] Update dependency @langchain/ollama to v1.2.5 #138

New issue

Open

opened 2026-03-03 13:59:04 +03:00 by kerem · 0 comments

kerem commented

2026-03-03 13:59:04 +03:00

Owner

📋 Pull Request Information

Original PR: https://github.com/Kuingsmile/word-GPT-Plus/pull/161
Author: @renovate[bot]
Created: 1/31/2026
Status: 🔄 Open

Base: master ← Head: renovate/langchain-ollama-1.x-lockfile

📝 Commits (1)

eb3e221 Update dependency @langchain/ollama to v1.2.5

📊 Changes

1 file changed (+3 additions, -3 deletions)

View changed files

📝 yarn.lock (+3 -3)

📄 Description

This PR contains the following updates:

Package	Change	Age	Confidence
@langchain/ollama (source)	`1.2.1` → `1.2.5`

Release Notes

langchain-ai/langchainjs (@langchain/ollama)

`v1.2.5`

Patch Changes

Updated dependencies [817fc9a]:
- @langchain/core@1.1.10

`v1.2.4`

Patch Changes

#9887 1fa865b Thanks @Muhammad-Kamran-Khan! - Fix validation to allow file_url and file_id without filename metadata in Responses API, and prevent sending filename when not allowed.
#9873 28efb57 Thanks @hntrl! - Add reasoningEffort call option as a convenience shorthand for reasoning.effort
- Adds reasoningEffort to BaseChatOpenAICallOptions for easier configuration of reasoning models
- Automatically coalesces reasoningEffort into reasoning.effort when calling reasoning models (o1, o3, etc.)
- If both reasoningEffort and reasoning.effort are provided, reasoning.effort takes precedence
- Marked as @deprecated to encourage use of the full reasoning.effort option
#9876 4e42452 Thanks @sflanker! - fix(openai): pass runManager to responses._generate function in ChatOpenAI
#9900 a9b5059 Thanks @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 a9b5059 Thanks @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.

`v1.2.3`

Compare Source

Patch Changes

#10065 e2b3d90 Thanks @MatanTsach! - fix(ollama): preserve tool_calls when AIMessage content is a string

`v1.2.2`

Compare Source

Patch Changes

#9777 3efe79c Thanks @christian-bromann! - fix(core): properly elevate reasoning tokens

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Kuingsmile/word-GPT-Plus/pull/161 **Author:** [@renovate[bot]](https://github.com/apps/renovate) **Created:** 1/31/2026 **Status:** 🔄 Open **Base:** `master` ← **Head:** `renovate/langchain-ollama-1.x-lockfile` --- ### 📝 Commits (1) - [`eb3e221`](https://github.com/Kuingsmile/word-GPT-Plus/commit/eb3e22141dfc4962e3bb93efa4eb12c44b48408a) Update dependency @langchain/ollama to v1.2.5 ### 📊 Changes **1 file changed** (+3 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `yarn.lock` (+3 -3) </details> ### 📄 Description This PR contains the following updates: | Package | Change | [Age](https://docs.renovatebot.com/merge-confidence/) | [Confidence](https://docs.renovatebot.com/merge-confidence/) | |---|---|---|---| | [@langchain/ollama](https://redirect.github.com/langchain-ai/langchainjs/tree/main/libs/langchain-ollama/) ([source](https://redirect.github.com/langchain-ai/langchainjs)) | [`1.2.1` → `1.2.5`](https://renovatebot.com/diffs/npm/@langchain%2follama/1.2.1/1.2.5) | ![age](https://developer.mend.io/api/mc/badges/age/npm/@langchain%2follama/1.2.5?slim=true) | ![confidence](https://developer.mend.io/api/mc/badges/confidence/npm/@langchain%2follama/1.2.1/1.2.5?slim=true) | --- ### Release Notes <details> <summary>langchain-ai/langchainjs (@langchain/ollama)</summary> ### [`v1.2.5`](https://redirect.github.com/langchain-ai/langchainjs/releases/tag/langchain%401.2.5) ##### Patch Changes - Updated dependencies \[[`817fc9a`](https://redirect.github.com/langchain-ai/langchainjs/commit/817fc9a56d4699f3563a6e153b13eadf7bcc661b)]: - [@langchain/core](https://redirect.github.com/langchain/core)@1.1.10 ### [`v1.2.4`](https://redirect.github.com/langchain-ai/langchainjs/releases/tag/%40langchain/openai%401.2.4) ##### Patch Changes - [#9887](https://redirect.github.com/langchain-ai/langchainjs/pull/9887) [`1fa865b`](https://redirect.github.com/langchain-ai/langchainjs/commit/1fa865b1cb8a30c2269b83cdb5fc84d374c3fca9) Thanks [@Muhammad-Kamran-Khan](https://redirect.github.com/Muhammad-Kamran-Khan)! - Fix validation to allow file\_url and file\_id without filename metadata in Responses API, and prevent sending filename when not allowed. - [#9873](https://redirect.github.com/langchain-ai/langchainjs/pull/9873) [`28efb57`](https://redirect.github.com/langchain-ai/langchainjs/commit/28efb57448933368094ca41c63d9262ac0f348a6) Thanks [@hntrl](https://redirect.github.com/hntrl)! - Add `reasoningEffort` call option as a convenience shorthand for `reasoning.effort` - Adds `reasoningEffort` to `BaseChatOpenAICallOptions` for easier configuration of reasoning models - Automatically coalesces `reasoningEffort` into `reasoning.effort` when calling reasoning models (o1, o3, etc.) - If both `reasoningEffort` and `reasoning.effort` are provided, `reasoning.effort` takes precedence - Marked as `@deprecated` to encourage use of the full `reasoning.effort` option - [#9876](https://redirect.github.com/langchain-ai/langchainjs/pull/9876) [`4e42452`](https://redirect.github.com/langchain-ai/langchainjs/commit/4e42452e4c020408bd6687667e931497b05aaff5) Thanks [@sflanker](https://redirect.github.com/sflanker)! - fix(openai): pass runManager to responses.\_generate function in ChatOpenAI - [#9900](https://redirect.github.com/langchain-ai/langchainjs/pull/9900) [`a9b5059`](https://redirect.github.com/langchain-ai/langchainjs/commit/a9b50597186002221aaa4585246e569fa44c27c8) Thanks [@hntrl](https://redirect.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://redirect.github.com/langchain-ai/langchainjs/pull/9900) [`a9b5059`](https://redirect.github.com/langchain-ai/langchainjs/commit/a9b50597186002221aaa4585246e569fa44c27c8) Thanks [@hntrl](https://redirect.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. ### [`v1.2.3`](https://redirect.github.com/langchain-ai/langchainjs/releases/tag/%40langchain/ollama%401.2.3) [Compare Source](https://redirect.github.com/langchain-ai/langchainjs/compare/@langchain/ollama@1.2.2...@langchain/ollama@1.2.3) ##### Patch Changes - [#10065](https://redirect.github.com/langchain-ai/langchainjs/pull/10065) [`e2b3d90`](https://redirect.github.com/langchain-ai/langchainjs/commit/e2b3d90a7b27dbb6a303e52bab08a1c881c2c850) Thanks [@MatanTsach](https://redirect.github.com/MatanTsach)! - fix(ollama): preserve tool\_calls when AIMessage content is a string ### [`v1.2.2`](https://redirect.github.com/langchain-ai/langchainjs/releases/tag/%40langchain/openai%401.2.2) [Compare Source](https://redirect.github.com/langchain-ai/langchainjs/compare/@langchain/ollama@1.2.1...@langchain/ollama@1.2.2) ##### Patch Changes - [#9777](https://redirect.github.com/langchain-ai/langchainjs/pull/9777) [`3efe79c`](https://redirect.github.com/langchain-ai/langchainjs/commit/3efe79c62ff2ffe0ada562f7eecd85be074b649a) Thanks [@christian-bromann](https://redirect.github.com/christian-bromann)! - fix(core): properly elevate reasoning tokens </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR was generated by [Mend Renovate](https://mend.io/renovate/). View the [repository job log](https://developer.mend.io/github/Kuingsmile/word-GPT-Plus).  --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>