mirror of
https://github.com/langchain-ai/langgraphjs.git
synced 2026-07-22 00:55:26 -04:00
@langchain/langgraph-cli@1.2.0
1696 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 github-actions[bot]
|
1f11df2668 |
chore: version packages (#2364)
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/angular@1.0.0 ### Major Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the Angular event streaming integration. Angular applications can now build on the shared event streaming runtime with `useStream`, `injectStream`, `StreamService`, `provideStream`, `provideStreamDefaults`, `injectProjection`, and selector helpers for messages, values, tool calls, custom channels, extensions, media, message metadata, and submission queues. The integration supports thread switching, run submission, reattachment, interrupts, WebSocket and SSE/custom transports, headless tools, subgraphs, subagents, and typed event projections. This release also adds Angular-specific media helpers, including `injectMediaUrl` and selectors for audio, images, video, and files. The package now exports the shared stream, media, transport, headless-tool, and type inference types needed to compose strongly typed streaming UIs. The documentation has been refreshed with guides for dependency injection, `injectStream`, selectors, transports, custom transports, interrupts, submission queues, headless tools, subagents/subgraphs, type safety, testing, and migration from the previous SDK surface. ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph-sdk@1.9.0 ## @langchain/react@1.0.0 ### Major Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the React event streaming integration. React applications can now use the shared event streaming runtime through `useStream`, `useProjection`, `useSuspenseStream`, `StreamProvider`, and focused selector hooks for messages, values, tool calls, custom channels, extensions, media, message metadata, and submission queues. The new integration supports thread-scoped runs, reattachment, interrupts, WebSocket and SSE/custom transports, headless tools, subgraphs, subagents, typed stream extensions, and strongly typed state/tool-call inference. This release also adds media helpers for streaming UI experiences, including `useMediaURL`, `useAudioPlayer`, and `useVideoPlayer`, plus selectors for audio, images, video, and files. Shared transport, media, protocol event, message metadata, and discovery types are exported from the package so React components can compose richer streaming interfaces without deep imports. The package documentation and tests have been expanded around custom transports, selectors, interrupts, multimodal streaming, suspense, submission queues, headless tools, subagents, type safety, and migration from the previous streaming API. ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph-sdk@1.9.0 ## @langchain/svelte@1.0.0 ### Major Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the Svelte event streaming integration. Svelte applications can now use the shared event streaming runtime through `useStream`, `useProjection`, context helpers, and selector runes for messages, values, tool calls, custom channels, extensions, media, message metadata, and submission queues. The integration supports thread-scoped runs, reattachment, interrupts, WebSocket and SSE/custom transports, headless tools, subgraphs, subagents, typed stream extensions, and strongly typed state/tool-call inference. This release also adds Svelte media helpers, including `useMediaURL`, `useAudioPlayer`, and `useVideoPlayer`, plus selectors for audio, images, video, and files. Shared transport, media, protocol event, message metadata, and discovery types are exported from the package so Svelte components can compose streaming interfaces without deep imports. The package now includes focused documentation and tests for context, custom transports, selectors, interrupts, hydration, submission queues, subscriptions, headless tools, subagents, type safety, and migration from the previous streaming API. ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph-sdk@1.9.0 ## @langchain/vue@1.0.0 ### Major Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the Vue event streaming integration. Vue applications can now use the shared event streaming runtime through `useStream`, `useProjection`, `provideStream`, `useStreamContext`, and selector composables for messages, values, tool calls, custom channels, extensions, media, message metadata, and submission queues. The integration supports thread-scoped runs, reattachment, interrupts, WebSocket and SSE/custom transports, headless tools, subgraphs, subagents, typed stream extensions, and strongly typed state/tool-call inference. This release also adds Vue media helpers, including `useMediaURL`, `useAudioPlayer`, and `useVideoPlayer`, plus selectors for audio, images, video, and files. Shared transport, media, protocol event, message metadata, and discovery types are exported from the package so Vue components can build rich streaming UIs without deep imports. The package documentation and tests now cover API usage, custom transports, forking, interrupts, multimodal streaming, selectors, shared streams, subagents, suspense, submission queues, transports, type safety, and migration from the previous streaming API. ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph-sdk@1.9.0 ## @langchain/langgraph-api@1.2.0 ### Minor Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the thread-scoped event streaming protocol used by the new SDK streaming clients. This release adds protocol routes for WebSocket and SSE/HTTP streaming, including thread-local command handling, filtered subscriptions, event replay, state inspection, checkpoint listing/forking, interrupt input, agent tree queries, and run start/resume commands. Stream events are normalized into the canonical protocol shape with ordered sequence IDs so clients can safely dedupe, resume subscriptions, and coordinate multiple projections from the same run. The experimental embed server now supports the same protocol flow, so embedded graphs can serve the new SDK transports without standing up a separate LangGraph API deployment. The server also gains protocol session tests and fixture graphs covering deep agents, interrupts, subgraphs, and SDK transport behavior. ### Patch Changes - Updated dependencies \[]: - @langchain/langgraph-ui@1.2.0 ## @langchain/langgraph@1.3.0 ### Minor Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the in-process event streaming runtime behind `streamEvents`. LangGraph now exposes the core primitives for event-based streaming, including `StreamChannel`, `StreamMux`, `GraphRunStream`, `SubgraphRunStream`, native stream transformers, and protocol event conversion utilities. These APIs let graphs emit ordered protocol events, derive additional projections, expose custom stream channels, and bridge in-process runs to remote SDK clients. The runtime includes built-in transformers for messages, values, lifecycle events, and subgraph discovery. It also adds support for transformer registration during graph execution, forwarding remote `StreamChannel` output, subgraph-aware event routing, event log multiplexing, and checkpoint-aware values streams. This release also expands test coverage across Pregel streaming, event conversion, stream muxing, stream channels, run streams, lifecycle transformers, subgraph transformers, and type-level streaming behavior. ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph-checkpoint@1.0.2 - @langchain/langgraph-sdk@1.9.0 ## @langchain/langgraph-sdk@1.9.0 ### Minor Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add the framework-agnostic event streaming SDK. The SDK now includes a thread-focused streaming client built around `ThreadStream`, `SubscriptionHandle`, message assembly, media assembly, typed stream extensions, and pluggable protocol transports. Applications can stream over SSE or WebSocket, provide custom agent-server adapters, subscribe to values/messages/tools/custom/lifecycle/checkpoint channels, inspect and fork state, respond to interrupts, and replay or dedupe ordered event streams. This release also adds the reusable stream runtime used by the React, Vue, Svelte, and Angular packages: `StreamController`, `StreamStore`, `ChannelRegistry`, projection factories, subagent/subgraph discovery, submission queue coordination, message metadata tracking, root message projection, media projections, and helper types for agent/deep-agent state and tool-call inference. The client package has been reorganized into focused modules for assistants, threads, runs, store, protocol streaming, transports, media, messages, and UI helpers. New SDK documentation covers configuration, assistants, threads, runs, store, streaming, transports, extensions, interrupts, messages, media, subagents, and subgraphs. ### Patch Changes - [#2363](https://github.com/langchain-ai/langgraphjs/pull/2363) [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Add a `returnMinimal` option to `threads.update`. ## @langchain/langgraph-checkpoint@1.0.2 ### Patch Changes - [#2314](https://github.com/langchain-ai/langgraphjs/pull/2314) [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Improve `MemorySaver` diagnostics when checkpoint writes are missing a `thread_id`. The in-memory checkpointer now explains why `configurable.thread_id` is required and includes a concrete `graph.stream(..., { configurable: { thread_id } })` example in the error message. This makes the new thread-oriented event streaming flows easier to debug when an application forgets to provide durable thread configuration. ## @langchain/langgraph-cli@1.2.0 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb)]: - @langchain/langgraph-api@1.2.0 ## @langchain/langgraph-ui@1.2.0 ## @example/ai-elements@0.1.15 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb)]: - @langchain/langgraph@1.3.0 - @langchain/react@1.0.0 ## @examples/assistant-ui-claude@0.1.15 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb)]: - @langchain/langgraph@1.3.0 - @langchain/react@1.0.0 ## @examples/ui-angular@0.0.25 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph@1.3.0 - @langchain/langgraph-sdk@1.9.0 - @langchain/angular@1.0.0 ## @examples/ui-multimodal@0.0.1 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb)]: - @langchain/langgraph@1.3.0 - @langchain/react@1.0.0 ## @examples/ui-react@0.0.1 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb), [`d1e2fda`](https://github.com/langchain-ai/langgraphjs/commit/d1e2fda1b1165e122362780a62ab8d2ebff9f9b9)]: - @langchain/langgraph@1.3.0 - @langchain/langgraph-sdk@1.9.0 - @langchain/react@1.0.0 ## langgraph@1.0.32 ### Patch Changes - Updated dependencies \[[`085a07f`](https://github.com/langchain-ai/langgraphjs/commit/085a07f569b6d7d79728eb7eb6eb3a0c67fcdefb)]: - @langchain/langgraph@1.3.0 --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
Christian Bromann
|
085a07f569 |
feat(core): event based streaming (#2314)
All stream v2 changes consolidated. --------- Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
dependabot[bot]
|
fe09385cb1 |
chore(deps): bump the langchain group across 1 directory with 9 updates (#2358)
Bumps the langchain group with 9 updates in the / directory: | Package | From | To | | --- | --- | --- | | [@langchain/anthropic](https://github.com/langchain-ai/langchainjs) | `1.3.26` | `1.3.28` | | [@langchain/core](https://github.com/langchain-ai/langchainjs) | `1.1.40` | `1.1.43` | | [langchain](https://github.com/langchain-ai/langchainjs) | `1.3.0` | `1.3.5` | | [@langchain/openai](https://github.com/langchain-ai/langchainjs) | `1.4.1` | `1.4.5` | | [@langchain/groq](https://github.com/langchain-ai/langchainjs) | `1.1.5` | `1.2.0` | | [@langchain/mistralai](https://github.com/langchain-ai/langchainjs) | `1.0.7` | `1.0.8` | | [@langchain/ollama](https://github.com/langchain-ai/langchainjs) | `1.2.6` | `1.2.7` | | [@langchain/classic](https://github.com/langchain-ai/langchainjs) | `1.0.27` | `1.0.32` | | [langsmith](https://github.com/langchain-ai/langsmith-sdk) | `0.5.20` | `0.6.0` | Updates `@langchain/anthropic` from 1.3.26 to 1.3.28 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/anthropic's releases</a>.</em></p> <blockquote> <h2><code>@langchain/anthropic</code><a href="https://github.com/1"><code>@1</code></a>.3.27</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10726">#10726</a> <a href="https://github.com/langchain-ai/langchainjs/commit/ad153c185b6cf813d4b7695740d9a4453d2cb63f"><code>ad153c1</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - feat(anthropic): add Claude Opus 4.7 compatibility updates</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/589f29ce844eb252c2d5e6b0f8d26de37763a0d7"><code>589f29c</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/2e9e6969e248a53ede0659a41d0ac8dbaf291ab4"><code>2e9e696</code></a>]:</p> <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.41</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits">compare view</a></li> </ul> </details> <br /> Updates `@langchain/core` from 1.1.40 to 1.1.43 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/core's releases</a>.</em></p> <blockquote> <h2><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.41</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10733">#10733</a> <a href="https://github.com/langchain-ai/langchainjs/commit/589f29ce844eb252c2d5e6b0f8d26de37763a0d7"><code>589f29c</code></a> Thanks <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a>! - fix(core): Update inheritance behavior for tracer metadata for special keys</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10711">#10711</a> <a href="https://github.com/langchain-ai/langchainjs/commit/2e9e6969e248a53ede0659a41d0ac8dbaf291ab4"><code>2e9e696</code></a> Thanks <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a>! - feat(core): Add chat model and llm invocation params to traced metadata</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits">compare view</a></li> </ul> </details> <br /> Updates `langchain` from 1.3.0 to 1.3.5 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">langchain's releases</a>.</em></p> <blockquote> <h2>langchain@1.3.4</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10713">#10713</a> <a href="https://github.com/langchain-ai/langchainjs/commit/49ac9e7404e5a9269b9ac047711ee96dd928b231"><code>49ac9e7</code></a> Thanks <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a>! - feat(langchain): Adds ls_agent_type to create agent runs as tracing metadata</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/589f29ce844eb252c2d5e6b0f8d26de37763a0d7"><code>589f29c</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/2e9e6969e248a53ede0659a41d0ac8dbaf291ab4"><code>2e9e696</code></a>]:</p> <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.41</li> </ul> </li> </ul> <h2>langchain@1.3.3</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/9386">#9386</a> <a href="https://github.com/langchain-ai/langchainjs/commit/71e53f1c07bc60e2c2304b10f0edd3c85c62b192"><code>71e53f1</code></a> Thanks <a href="https://github.com/Josh-Engle"><code>@Josh-Engle</code></a>! - Prevent local file corruption when using <code>LocalFileStore</code></p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d3e080995bb267bf3797067ab53c96bc2a6c8e3f"><code>d3e0809</code></a>]:</p> <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.40</li> </ul> </li> </ul> <h2>langchain@1.3.2</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10693">#10693</a> <a href="https://github.com/langchain-ai/langchainjs/commit/5a6e0ab6617587f3aed19d07bf3ed91994dcdac8"><code>5a6e0ab</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - fix(agents): derive middleware hook state from invocation state</p> <p>Prevents middleware state from leaking across threads by deriving middleware hook input state from the current invocation state instead of cross-node cached state.</p> </li> </ul> <h2>langchain@1.3.1</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10673">#10673</a> <a href="https://github.com/langchain-ai/langchainjs/commit/f0693657b7e5bdbf888a46d04e68431e446c7bc0"><code>f069365</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - bump langgraph dependency to 1.2.8</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6845a1ef129450cd6e75bb8a8e7390a416ab3d9c"><code>6845a1e</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10690">#10690</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/5a6e0ab6617587f3aed19d07bf3ed91994dcdac8"><code>5a6e0ab</code></a> fix(agents): derive middleware hook state from invocation state (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10693">#10693</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/607696e8143ad30faeebb800028e244a11d46638"><code>607696e</code></a> chore(ci): add label-gated publish-preview workflow (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10696">#10696</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/1f8b2c0b863645da45114d8756dc5b66fcb43c98"><code>1f8b2c0</code></a> chore(ci): add label-gated publish-preview workflow (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10695">#10695</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/2ff51cf0688e45d5d237b2b435334b5fd987afa9"><code>2ff51cf</code></a> fix(aws): normalize Bedrock Converse object errors for tracing (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10688">#10688</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/4a91db32a80a1b9da3bea4f6333eff63980b28b4"><code>4a91db3</code></a> chore(deps): bump langsmith from 0.5.9 to 0.5.18 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10687">#10687</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/312d60536da66827791e9b0f4a9d5d9091439183"><code>312d605</code></a> chore(deps): bump axios from 1.13.6 to 1.15.0 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10686">#10686</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/3e071bb44ec9c80a0eb964eff089434f4edd78b2"><code>3e071bb</code></a> chore: remove suppressed CodeQL query filter and deduplicate paths-ignore (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/1">#1</a>...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/e5b6e1c8568115cdda53eccafbdcd23537f554c5"><code>e5b6e1c</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10682">#10682</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/2301260ae90ead5c5f725c8dae1487b6722607e2"><code>2301260</code></a> fix(openai): add index to streaming reasoning content blocks for proper chunk...</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/langchain@1.3.0...@langchain/aws@1.3.5">compare view</a></li> </ul> </details> <br /> Updates `@langchain/openai` from 1.4.1 to 1.4.5 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/openai's releases</a>.</em></p> <blockquote> <h2><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.4</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10681">#10681</a> <a href="https://github.com/langchain-ai/langchainjs/commit/2301260ae90ead5c5f725c8dae1487b6722607e2"><code>2301260</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - fix(openai): add index to streaming reasoning content blocks for proper chunk merging</li> </ul> <h2><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.3</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10670">#10670</a> <a href="https://github.com/langchain-ai/langchainjs/commit/6b8ef6c95e061af47af206926598c983d878f72a"><code>6b8ef6c</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(openai): preserve plain string responses content</li> </ul> <h2><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.2</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10614">#10614</a> <a href="https://github.com/langchain-ai/langchainjs/commit/d6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1"><code>d6bf4fc</code></a> Thanks <a href="https://github.com/colifran"><code>@colifran</code></a>! - feat(openai): imput placeholder filenames for openai file inputs</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d3d0922c24afcd3006fb94dcadd3ebe08fbf2383"><code>d3d0922</code></a>]:</p> <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.39</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits">compare view</a></li> </ul> </details> <br /> Updates `@langchain/groq` from 1.1.5 to 1.2.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/groq's releases</a>.</em></p> <blockquote> <h2><code>@langchain/groq</code><a href="https://github.com/1"><code>@1</code></a>.2.0</h2> <h3>Minor Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10603">#10603</a> <a href="https://github.com/langchain-ai/langchainjs/commit/66effb028baf5c923501801c989c7377efb8b77a"><code>66effb0</code></a> Thanks <a href="https://github.com/apps/dependabot"><code>@dependabot</code></a>! - chore(deps): bump groq-sdk from 0.37.0 to 1.1.2</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/daece6df71e0095c7a354270667a0b851a8cee4d"><code>daece6d</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10560">#10560</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/9781bff525bffdd3b6a75adfa8a30fdb4bfc505e"><code>9781bff</code></a> fix(google): align ChatGoogle mediaResolution with Gemini scalar type (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10550">#10550</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/3bd85c17869e95d5d1a67c5fccc0c4cab2646616"><code>3bd85c1</code></a> feat(langchain): add ChatGoogle support to initChatModel (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10654">#10654</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/d3d0922c24afcd3006fb94dcadd3ebe08fbf2383"><code>d3d0922</code></a> feat(core): support for headless tools (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10430">#10430</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/793bc69a8af8198de9d157c21070871660e6bb13"><code>793bc69</code></a> feat(aws): impute file name for document content blocks#963 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10658">#10658</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/d6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1"><code>d6bf4fc</code></a> feat(openai): impute placeholder filenames for openai file inputs (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10614">#10614</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/0a7a7298b719f579854e41adddb04f17dc82640b"><code>0a7a729</code></a> fix(examples): update dependencies (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10651">#10651</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6f8dafcb9deee169473eadaae6416ad255277a5b"><code>6f8dafc</code></a> Bump vitest (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10649">#10649</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/e89cfd29f36e0b2fee20a7443e6c30c88039d735"><code>e89cfd2</code></a> chore(deps): bump <code>@cloudflare/workers-types</code> from 4.20260207.0 to 4.20260402.1...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/0de2c14d38716d9c66c546e18a490c5bfda75134"><code>0de2c14</code></a> chore(deps): bump <code>@aws-sdk/client-bedrock-agent-runtime</code> from 3.1006.0 to 3.10...</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/groq@1.1.5...@langchain/groq@1.2.0">compare view</a></li> </ul> </details> <br /> Updates `@langchain/mistralai` from 1.0.7 to 1.0.8 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/mistralai's releases</a>.</em></p> <blockquote> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.3</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d3e080995bb267bf3797067ab53c96bc2a6c8e3f"><code>d3e0809</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/71e53f1c07bc60e2c2304b10f0edd3c85c62b192"><code>71e53f1</code></a>]: <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.40</li> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.31</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.2</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies []: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.30</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.1</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies []: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.29</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.0</h2> <h3>Minor Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10590">#10590</a> <a href="https://github.com/langchain-ai/langchainjs/commit/ed8cda659c893219d853a402f0fcd46e06cf7c28"><code>ed8cda6</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - feat: scaffold <code>@langchain/neo4j</code> provider package</li> </ul> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e"><code>d7a98cd</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/884c2d3d1b2c49225d73ddec2235ad174db36f86"><code>884c2d3</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e"><code>0fb6fa4</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/d3d0922c24afcd3006fb94dcadd3ebe08fbf2383"><code>d3d0922</code></a>]: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.28</li> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.39</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/7ea8874715f76c17d3ec3d2ff0503dd12abbc5e9"><code>7ea8874</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9716">#9716</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/5707c3edc6a4d43934da0d3e7b9666b2fc144440"><code>5707c3e</code></a> docs(internal): add AGENTS.md file (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9742">#9742</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/8ef152555a945c95322f28209957b69605c04c91"><code>8ef1525</code></a> feat(google-common): support thinkingLevel parameter for Gemini models (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9738">#9738</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/c28d24a8770f6d0e543cde116b0e38b3baf21301"><code>c28d24a</code></a> fix(core): use getBufferString for message summarization (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9739">#9739</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f6974516b041ed12befd26e1a4cbe457865a2780"><code>f697451</code></a> fix(langchain): keep tool call / AIMessage pairings when summarizing (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9740">#9740</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/536c7ddacd6c7f80d2edf18ab9caeeab71827ccd"><code>536c7dd</code></a> fix(langchain): default strict to true in providerStrategy for OpenAI compati...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/75b3b90c5fa62cbbfa678dfb01f031caed4488ef"><code>75b3b90</code></a> fix(openai): pass runManager to _streamResponseChunks in responses API (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9737">#9737</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/13c9d5bfa3acac7ffb37642e9a50d84dc9004e88"><code>13c9d5b</code></a> fix(openai): pass through provider-native content in ToolMessage without stri...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/5cfbedf064ffdc960cb2e5a97e37d7a5900560de"><code>5cfbedf</code></a> fix(langchain): support callbacks property in stream (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9728">#9728</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/9ac29de3d3f70c75933913d94ad9a47c6ce39c1d"><code>9ac29de</code></a> fix(langchain-aws): add support for Amazon Nova embedding models (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9701">#9701</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/mistralai@1.0.7...@langchain/classic@1.0.8">compare view</a></li> </ul> </details> <br /> Updates `@langchain/ollama` from 1.2.6 to 1.2.7 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/ollama's releases</a>.</em></p> <blockquote> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.3</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d3e080995bb267bf3797067ab53c96bc2a6c8e3f"><code>d3e0809</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/71e53f1c07bc60e2c2304b10f0edd3c85c62b192"><code>71e53f1</code></a>]: <ul> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.40</li> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.31</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.2</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies []: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.30</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.1</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies []: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.29</li> </ul> </li> </ul> <h2><code>@langchain/neo4j</code><a href="https://github.com/0"><code>@0</code></a>.1.0</h2> <h3>Minor Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10590">#10590</a> <a href="https://github.com/langchain-ai/langchainjs/commit/ed8cda659c893219d853a402f0fcd46e06cf7c28"><code>ed8cda6</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - feat: scaffold <code>@langchain/neo4j</code> provider package</li> </ul> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e"><code>d7a98cd</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/884c2d3d1b2c49225d73ddec2235ad174db36f86"><code>884c2d3</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e"><code>0fb6fa4</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/d3d0922c24afcd3006fb94dcadd3ebe08fbf2383"><code>d3d0922</code></a>]: <ul> <li><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.28</li> <li><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.39</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/bd72d8eb8bde1b2282c9ec88f2ebadd0747dc7b7"><code>bd72d8e</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9762">#9762</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/578574906bdbd9cfce95e34030c1a3d97e63d1c1"><code>5785749</code></a> fix(internal): fix changeset config (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9768">#9768</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/ddd72b8122e9dc68242b8467292bbee62e1dda2e"><code>ddd72b8</code></a> chore(standard-tests): move standard-tests into ./internal (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9755">#9755</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/739d4e88cc78b8f578ab019b526c97d63d9c2144"><code>739d4e8</code></a> Feat/xai responses implementation (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9718">#9718</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/e0360d9bdc0e7725d59625902bcfc98c39931e2a"><code>e0360d9</code></a> fix(langchain): ensure models only make on write_todo call at a time (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9761">#9761</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/8619adb81f16977b3ab8d4607ad5c30f79c41e3d"><code>8619adb</code></a> fix: add properties to check valid props (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9757">#9757</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/23be5afd59b5f4806edef11937ce5e2ba300f7ee"><code>23be5af</code></a> feat(langchain): consolidate type generics in bags (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9517">#9517</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/85820be04995b4047a798ec44da6077cd1908d7a"><code>85820be</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9754">#9754</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/a46a24983fd0fea649d950725a2673b3c435275f"><code>a46a249</code></a> fix(core): allow shared object references in serialization (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9753">#9753</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/3c8ba0d97f1c08e8f8c67ffddff5d57daba46f85"><code>3c8ba0d</code></a> chore(internal): Turborepo improvements (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/9744">#9744</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/ollama@1.2.6...langchain@1.2.7">compare view</a></li> </ul> </details> <br /> Updates `@langchain/classic` from 1.0.27 to 1.0.32 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases">@langchain/classic's releases</a>.</em></p> <blockquote> <h2><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.31</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/9386">#9386</a> <a href="https://github.com/langchain-ai/langchainjs/commit/71e53f1c07bc60e2c2304b10f0edd3c85c62b192"><code>71e53f1</code></a> Thanks <a href="https://github.com/Josh-Engle"><code>@Josh-Engle</code></a>! - Prevent local file corruption when using <code>LocalFileStore</code></li> </ul> <h2><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.30</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/2301260ae90ead5c5f725c8dae1487b6722607e2"><code>2301260</code></a>]: <ul> <li><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.4</li> </ul> </li> </ul> <h2><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.29</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/6b8ef6c95e061af47af206926598c983d878f72a"><code>6b8ef6c</code></a>]: <ul> <li><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.3</li> </ul> </li> </ul> <h2><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.28</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10591">#10591</a> <a href="https://github.com/langchain-ai/langchainjs/commit/d7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e"><code>d7a98cd</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - feat: add <code>@langchain/perplexity</code> standalone provider package</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10594">#10594</a> <a href="https://github.com/langchain-ai/langchainjs/commit/884c2d3d1b2c49225d73ddec2235ad174db36f86"><code>884c2d3</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - feat(fireworks): extract standalone provider package</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10593">#10593</a> <a href="https://github.com/langchain-ai/langchainjs/commit/0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e"><code>0fb6fa4</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - feat(together-ai): migrate Together AI into provider package</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/d6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1"><code>d6bf4fc</code></a>]:</p> <ul> <li><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.2</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits">compare view</a></li> </ul> </details> <br /> Updates `langsmith` from 0.5.20 to 0.6.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langsmith-sdk/releases">langsmith's releases</a>.</em></p> <blockquote> <h2>v0.6.0</h2> <h2>What's Changed</h2> <ul> <li>chore(js): bump JS to 0.4.3 by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2253">langchain-ai/langsmith-sdk#2253</a></li> <li>Revert "feat: add js prompt caching" by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2258">langchain-ai/langsmith-sdk#2258</a></li> <li>Revert "feat: Replace UUID5 with deterministic UUID7 for replicas" by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2257">langchain-ai/langsmith-sdk#2257</a></li> <li>release(js): bump to 0.4.4 by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2259">langchain-ai/langsmith-sdk#2259</a></li> <li>feat: add prompt cache back and setup environment tests by <a href="https://github.com/langchain-infra"><code>@langchain-infra</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2260">langchain-ai/langsmith-sdk#2260</a></li> <li>feat(python): Bump pydantic to v2 by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2248">langchain-ai/langsmith-sdk#2248</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.5.2...v0.6.0">https://github.com/langchain-ai/langsmith-sdk/compare/v0.5.2...v0.6.0</a></p> <h2>v0.6.0rc0</h2> <h2>What's Changed</h2> <ul> <li>feat(js): Add support for tracing AI SDK 6 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2237">langchain-ai/langsmith-sdk#2237</a></li> <li>fix(js): Remove default Jestlike timeout by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2243">langchain-ai/langsmith-sdk#2243</a></li> <li>feat(js): Add support for tracing tool loop agent by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2244">langchain-ai/langsmith-sdk#2244</a></li> <li>feat: Replace UUID5 with deterministic UUID7 for replicas by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2249">langchain-ai/langsmith-sdk#2249</a></li> <li>feat: add prompt caching to python sdk by <a href="https://github.com/langchain-infra"><code>@langchain-infra</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2246">langchain-ai/langsmith-sdk#2246</a></li> <li>feat: add js prompt caching by <a href="https://github.com/langchain-infra"><code>@langchain-infra</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2251">langchain-ai/langsmith-sdk#2251</a></li> <li>fix(claude): correctly parse llm and tool inputs in claude agent sdk by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2255">langchain-ai/langsmith-sdk#2255</a></li> <li>bump(python): 0.5.2 by <a href="https://github.com/angus-langchain"><code>@angus-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2256">langchain-ai/langsmith-sdk#2256</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.5.1...v0.6.0rc0">https://github.com/langchain-ai/langsmith-sdk/compare/v0.5.1...v0.6.0rc0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langsmith-sdk/commits/v0.6.0">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Connor Braa
|
d1e2fda1b1 |
feat(sdk): add returnMinimal to threads update (#2363)
Adds a first-class `returnMinimal` option to JS SDK `threads.update`. When enabled, the SDK sends `Prefer: return=minimal` and resolves with `undefined` for the 204 response. Includes a patch changeset and focused fetch test coverage. |
||
|
github-actions[bot]
|
740ce21852 |
chore: version packages (#2362)
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/angular@0.4.7 ### Patch Changes - [#2354](https://github.com/langchain-ai/langgraphjs/pull/2354) [`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): pin framework SDKs to langgraph-sdk version ## @langchain/react@0.3.5 ### Patch Changes - [#2354](https://github.com/langchain-ai/langgraphjs/pull/2354) [`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): pin framework SDKs to langgraph-sdk version ## @langchain/svelte@0.4.7 ### Patch Changes - [#2354](https://github.com/langchain-ai/langgraphjs/pull/2354) [`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): pin framework SDKs to langgraph-sdk version ## @langchain/vue@0.4.7 ### Patch Changes - [#2354](https://github.com/langchain-ai/langgraphjs/pull/2354) [`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): pin framework SDKs to langgraph-sdk version ## @example/ai-elements@0.1.14 ### Patch Changes - Updated dependencies \[[`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6)]: - @langchain/react@0.3.5 ## @examples/assistant-ui-claude@0.1.14 ### Patch Changes - Updated dependencies \[[`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6)]: - @langchain/react@0.3.5 ## @examples/ui-angular@0.0.24 ### Patch Changes - Updated dependencies \[[`733d28e`](https://github.com/langchain-ai/langgraphjs/commit/733d28ea637135876375fa005a8d8a5605a692e6)]: - @langchain/angular@0.4.7 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
733d28ea63 |
fix(sdk): pin framework SDKs to langgraph-sdk version (#2354)
As a safe guard for the upcoming major release of the framework SDK packages we pin the 0.x packages to whatever the latest langgraph-sdk was at the time. |
||
|
github-actions[bot]
|
1b66d654dd |
chore: version packages (#2347)
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/langgraph-sdk@1.8.10 ### Patch Changes - [#2340](https://github.com/langchain-ai/langgraphjs/pull/2340) [`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Respect `fetchStateHistory` when restoring subagent history. ## @langchain/angular@0.4.6 ### Patch Changes - [#2340](https://github.com/langchain-ai/langgraphjs/pull/2340) [`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Respect `fetchStateHistory` when restoring subagent history. - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/langgraph-sdk@1.8.10 ## @langchain/react@0.3.4 ### Patch Changes - [#2340](https://github.com/langchain-ai/langgraphjs/pull/2340) [`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Respect `fetchStateHistory` when restoring subagent history. - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/langgraph-sdk@1.8.10 ## @langchain/svelte@0.4.6 ### Patch Changes - [#2340](https://github.com/langchain-ai/langgraphjs/pull/2340) [`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Respect `fetchStateHistory` when restoring subagent history. - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/langgraph-sdk@1.8.10 ## @langchain/vue@0.4.6 ### Patch Changes - [#2340](https://github.com/langchain-ai/langgraphjs/pull/2340) [`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4) Thanks [@cwlbraa](https://github.com/cwlbraa)! - Respect `fetchStateHistory` when restoring subagent history. - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/langgraph-sdk@1.8.10 ## @example/ai-elements@0.1.13 ### Patch Changes - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/react@0.3.4 ## @examples/assistant-ui-claude@0.1.13 ### Patch Changes - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/react@0.3.4 ## @examples/ui-angular@0.0.23 ### Patch Changes - Updated dependencies \[[`6bab458`](https://github.com/langchain-ai/langgraphjs/commit/6bab458d4a03ce2d7b2708488b92226899eb94d4)]: - @langchain/langgraph-sdk@1.8.10 - @langchain/angular@0.4.6 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Connor Braa
|
6bab458d4a |
fix(sdk): respect fetchStateHistory for subagent history (#2340)
## Summary - skip eager subagent history restoration when `fetchStateHistory` is `false` - reuse numeric `fetchStateHistory` limits for subagent namespace discovery - add orchestrator regression coverage for both cases ## Context - Slack thread: https://langchain.slack.com/archives/C09BAECNA14/p1776755205756119 - [Agent Builder trace](https://langchain-us.datadoghq.com/apm/entity/service%3Aagent_builder_prod?dependencyMap.showNetworkMetrics=false&fromUser=false&graphType=flamegraph&groupMapByOperation=null&historicalData=true&panels=qson%3A%28data%3A%28activePanelKey%3Atrace%2Cresource%3A%28resourceName%3APOST%2520%252Fthreads%252F%257Bthread_id%257D%252Fhistory%2CresourceID%3A2bfaa153eac24153%2CoperationName%3Astarlette.request%29%2Ctrace%3A%28traceID%3A69ef784f000000001773743cf39a72b5%2CspanID%3A8969752200629810217%2ChasSearchOrFacetActions%3A%21f%29%29%2Cversion%3A%210%29&resources=qson%3A%28data%3A%28visible%3A%21t%2Chits%3A%28selected%3Arate%2CgroupBy%3A%5Bresource_name%5D%29%2Cerrors%3A%28selected%3Atotal%2CgroupBy%3A%5Bresource_name%5D%29%2Clatency%3A%28selected%3Ap95%2CgroupBy%3A%5Bresource_name%5D%29%2CtopN%3Aall%29%2Cversion%3A%211%29&shouldShowLegend=true&spanID=8969752200629810217&spanKind=server&spanViewType=logs&summary=qson%3A%28data%3A%28visible%3A%21t%2Cchanges%3A%28%29%2Cerrors%3A%28selected%3Acount%2CgroupBy%3A%5B%5D%29%2Chits%3A%28selected%3Arate%2CgroupBy%3A%5B%5D%29%2Clatency%3A%28selected%3Alatency%2Cslot%3A%28agg%3A95%29%2Cdistribution%3A%28isLogScale%3A%21f%29%2CshowTraceOutliers%3A%21t%2CgroupBy%3A%5B%5D%2Coperation%3Astarlette.request%29%2Csublayer%3A%28slot%3A%28layers%3AserviceAndInferred%29%2Cselected%3Apercentage%29%2ClagMetrics%3A%28selectedMetric%3A%21s%2CselectedGroupBy%3A%21s%29%29%2Cversion%3A%211%29&timeHint=1777301587169&trace=AwAAAZ3PbgThpE93_wAAABhBWjNQYmdkWUFBQ2ZVVkFJVExwS3lYTVgAAAAkMTE5ZGNmODctODg4Ny00ZTY5LThlN2MtNGEzOWU2ZTE3ZjY0AAUrsg&traceID=69ef784f000000001773743cf39a72b5&traceQuery=&start=1777062982891&end=1777322182891&paused=false) ## Test Plan - `corepack pnpm exec vitest run src/ui/orchestrator.test.ts --typecheck.enabled=false` from `libs/sdk` - `corepack pnpm run lint -- libs/sdk-react/src/stream.lgp.tsx libs/sdk/src/react/stream.lgp.tsx libs/sdk/src/ui/orchestrator.ts libs/sdk/src/ui/manager.ts libs/sdk/src/ui/orchestrator.test.ts` - `corepack pnpm run format:check -- libs/sdk-react/src/stream.lgp.tsx libs/sdk/src/react/stream.lgp.tsx libs/sdk/src/ui/orchestrator.ts libs/sdk/src/ui/manager.ts libs/sdk/src/ui/orchestrator.test.ts .changeset/tame-subagent-history.md` |
||
|
github-actions[bot]
|
0120a78d58 |
chore: version packages (#2343)
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/langgraph-checkpoint-mongodb@1.3.0 ### Minor Changes - [#2326](https://github.com/langchain-ai/langgraphjs/pull/2326) [`36916ed`](https://github.com/langchain-ai/langgraphjs/commit/36916ed86e63eb07249a68ecf0508e3b986ba587) Thanks [@tadjik1](https://github.com/tadjik1)! - feat: add MongoDBStore for long-term memory New `MongoDBStore` class for persisting data across threads and sessions — user preferences, learned facts, agent memory, and more. - Store and retrieve JSON documents organized by hierarchical namespaces - Search with field-based filtering and comparison operators - Vector similarity search with manual embedding (bring your own embedding model) or auto embedding (MongoDB generates embeddings via Voyage AI) - Automatic document expiration via configurable TTL --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
Sergey Zelenov
|
36916ed86e |
feat(langgraph-checkpoint-mongodb): add MongoDBStore for long-term memory with manual and auto embedding (#2326)
## Summary Adds `MongoDBStore` - a `BaseStore` implementation backed by MongoDB for long-term cross-thread memory. While the existing `MongoDBSaver` persists graph execution state within a single thread (checkpoints), `MongoDBStore` enables agents to store and retrieve data across threads and sessions - user preferences, learned facts, agent instructions, and more. Fixes [NODE-7497](https://jira.mongodb.org/browse/NODE-7497) Built on top of the initial implementation by @PavelSafronov and @RaschidJFR (PR #2320). Their work provided the foundation for the store, auto embedding integration, and Docker test setup. ## Review notes This PR is organized into two self-contained commits that can be reviewed independently: 1. **[`add MongoDBStore with core CRUD and field-based search`](https://github.com/langchain-ai/langgraphjs/commit/1415f7f6c7df0338644444feffa14f8123e2f0a8)** - the store itself with all non-embedding functionality, namespace prefix matching, matchConditions, tests 2. **[`add manual and auto embedding support`](https://github.com/langchain-ai/langgraphjs/pull/2326/changes/7bc2ecd80840b1bd291d7dfcdc012a704b614040)** - adds vector search on top of the first commit, including IndexConfig, embedding logic in put/search, vector search index creation, tests ## What's included ### Core store (commit 1) - `MongoDBStore` extending `BaseStore` with Put, Get, Delete, Search, and ListNamespaces operations - Hierarchical namespace organization with unique `(namespace, key)` index - Field-based search with comparison operators (`$eq`, `$ne`, `$gt`, `$gte`, `$lt`, `$lte`) - Namespace prefix matching in search using dot-notation array indexing - ListNamespaces with `matchConditions` support (prefix, suffix, and wildcard filtering) - TTL support via MongoDB TTL index with optional refresh-on-read - Factory method `fromConnString` for convenient setup - Refactors existing `MongoDBSaver` into separate `checkpoint.ts` file ### Embedding support (commit 2) Two modes for vector similarity search via MongoDB `$vectorSearch`, both requiring `indexConfig`: **Manual embedding** - app provides an `EmbeddingsInterface`: - Store computes vectors on put via `embedDocuments()` - Search computes query vector via `embedQuery()` and uses `queryVector` in `$vectorSearch` **Auto embedding** - no `EmbeddingsInterface` needed: - Store writes plain text to the embedding field - MongoDB generates embeddings server-side via Voyage AI (requires `model` in `indexConfig`) - Search sends query text via `query.text` in `$vectorSearch` - Requires MongoDB 8.2+ with auto embedding support --------- Co-authored-by: Hunter Lovell <40191806+hntrl@users.noreply.github.com> |
||
|
John Kennedy
|
7f3320cda8 |
fix: patch 6 medium-severity security alerts (#2333)
## Security Alert Patch (medium-tier follow-up) Follow-up to #2329, which patched the critical+high tier. This PR resolves the remaining **6 medium-severity Dependabot alerts** via `pnpm.overrides` plus one published-path constraint bump. All fixes are patch/minor bumps within the current major — no breaking changes. ### Packages Updated | Package | Old Constraint | New Constraint | Strategy | Scope | CVEs Resolved | |---------|---------------|----------------|----------|-------|---------------| | `axios` | `>=1.13.5` (override) | `>=1.15.0` (override); resolved 1.13.6 → **1.15.1** | C (override) | dev-only (via `@langchain/scripts` devDep) | CVE-2025-62718 (SSRF via NO_PROXY bypass), CVE-2026-40175 (cloud metadata exfiltration) | | `dompurify` | (transitive, resolved 3.3.3) | `>=3.4.0` (new override); resolved **3.4.0** | C (override) | dev-only (private `@example/ai-elements` via mermaid) | GHSA-39q2-94rc-95cp (ADD_TAGS bypasses FORBID_TAGS) | | `follow-redirects` | (transitive, resolved 1.15.11) | `>=1.16.0` (new override); resolved **1.16.0** | C (override) | dev-only (via `@langchain/scripts` devDep) | GHSA-r4q5-vmmm-2653 (auth header leak on cross-domain redirect) | | `langsmith` (published path) | `langsmith: >=0.3.33 <1.0.0` in `libs/langgraph-api/package.json` | `>=0.5.19 <1.0.0` | **A (manifest bump)** | **published** — direct dep of `@langchain/langgraph-api` | CVE-2026-40190 (prototype pollution), GHSA-rr7j-v2q5-chgv (streaming redaction bypass) | | `langsmith` (dev chains) | (transitive 0.4.12, 0.5.16 resolved via `@langchain/classic`, `langchain@1.3.0`) | `langsmith@<0.5.19: >=0.5.19 <1` (new override) | C (override) | dev-only | same as above (flushes vulnerable transitive copies) | *Strategy C overrides follow the existing repo pattern — axios, qs, undici, minimatch, brace-expansion, protobufjs, basic-ftp, vite, and defu are already overridden the same way.* ### Published-path rationale `@langchain/langgraph-api` exercises `langsmith` at runtime for tracing and streaming, which touches the affected internal code paths (lodash `set()` prototype-pollution guard, token-event redaction). Therefore the fix is Strategy A (raise the published lower bound) rather than A-lockfile — this protects end users who pin `@langchain/langgraph-api`. The lockfile already resolved `langsmith@0.5.20` before this change, so installs are unchanged at HEAD; the bump is a downstream-safety constraint tightening. ### Deferred (not fixed in this PR) - **`protobufjs@6.11.5`** (CRITICAL, CVE-2026-41242) — reached via `@xenova/transformers@2.17.2` in `libs/langgraph-core` devDeps + examples. `@xenova/transformers` is abandoned; the successor is `@huggingface/transformers@3`. Forcing a 6.x → 7.x override would cross a breaking API boundary. **Upstream issue — requires a manual migration, tracked separately.** (See #2329 body for full context.) - **`elliptic@6.6.1`** (LOW, GHSA-848j-6mx2-7j84) — `first_patched_version` is `null`; upstream has not released a fix. Defer until a patched version ships. ### CVE Details - **CVE-2025-62718** / GHSA-3p68-rc4w-qgx5 — Axios NO_PROXY Hostname Normalization Bypass Leads to SSRF — https://github.com/advisories/GHSA-3p68-rc4w-qgx5 - **CVE-2026-40175** / GHSA-fvcv-3m26-pcqx — Axios Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — https://github.com/advisories/GHSA-fvcv-3m26-pcqx - **GHSA-39q2-94rc-95cp** — DOMPurify `ADD_TAGS` bypasses `FORBID_TAGS` via short-circuit evaluation — https://github.com/advisories/GHSA-39q2-94rc-95cp - **GHSA-r4q5-vmmm-2653** — follow-redirects leaks custom authentication headers to cross-domain redirect targets — https://github.com/advisories/GHSA-r4q5-vmmm-2653 - **CVE-2026-40190** / GHSA-fw9q-39r9-c252 — LangSmith prototype pollution via incomplete `__proto__` guard in internal lodash `set()` — https://github.com/advisories/GHSA-fw9q-39r9-c252 - **GHSA-rr7j-v2q5-chgv** — LangSmith streaming token events bypass output redaction — https://github.com/advisories/GHSA-rr7j-v2q5-chgv ### Linear Tickets Linear ticket lookup returned no matches for the resolved CVEs/GHSAs. No ticket IDs included in the title. ### Verification - [x] Lockfile regenerated via `pnpm install --lockfile-only` - [x] `pnpm lint` (oxlint) — 0 warnings, 0 errors - [x] `pnpm format:check` (oxfmt) — clean - [x] `pnpm audit --prod` — **No known vulnerabilities found** - [x] `pnpm typecheck` on `libs/langgraph-api` — clean - [x] No staged secrets (`gitleaks git --staged`) 🤖 Submitted by langster-patch Co-authored-by: John Kennedy <jkennedyvz@users.noreply.github.com> |
||
|
dependabot[bot]
|
786fe03646 | chore(deps): bump vite from 7.3.2 to 8.0.5 (#2322) | ||
|
github-actions[bot]
|
aba243a403 |
chore: version packages (#2313)
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/langgraph@1.2.9 ### Patch Changes - [#2315](https://github.com/langchain-ai/langgraphjs/pull/2315) [`9102d52`](https://github.com/langchain-ai/langgraphjs/commit/9102d526c858a4cdbe9b47dcdd062b93da93e49f) Thanks [@hntrl](https://github.com/hntrl)! - propagate tracer metadata defaults from configurable - [#2311](https://github.com/langchain-ai/langgraphjs/pull/2311) [`b7c196b`](https://github.com/langchain-ai/langgraphjs/commit/b7c196b2142fb888dfcd9ceb1dfb4365d803c8b6) Thanks [@open-swe](https://github.com/apps/open-swe)! - fix: export missing types for typescript 6.0 declaration file compatibility - Updated dependencies \[[`458d66b`](https://github.com/langchain-ai/langgraphjs/commit/458d66bf665468854abb8133594d4d4f966054ed)]: - @langchain/langgraph-sdk@1.8.9 ## @langchain/langgraph-sdk@1.8.9 ### Patch Changes - [#2302](https://github.com/langchain-ai/langgraphjs/pull/2302) [`458d66b`](https://github.com/langchain-ai/langgraphjs/commit/458d66bf665468854abb8133594d4d4f966054ed) Thanks [@AdrianSajjan](https://github.com/AdrianSajjan)! - fix(sdk): preserve messages on interrupt values events Add a regression test for interrupt-only `values` payloads to ensure previously streamed messages are not overwritten when `__interrupt__` is emitted. ## @example/ai-elements@0.1.12 ### Patch Changes - Updated dependencies \[[`9102d52`](https://github.com/langchain-ai/langgraphjs/commit/9102d526c858a4cdbe9b47dcdd062b93da93e49f), [`b7c196b`](https://github.com/langchain-ai/langgraphjs/commit/b7c196b2142fb888dfcd9ceb1dfb4365d803c8b6)]: - @langchain/langgraph@1.2.9 ## @examples/assistant-ui-claude@0.1.12 ### Patch Changes - Updated dependencies \[[`9102d52`](https://github.com/langchain-ai/langgraphjs/commit/9102d526c858a4cdbe9b47dcdd062b93da93e49f), [`b7c196b`](https://github.com/langchain-ai/langgraphjs/commit/b7c196b2142fb888dfcd9ceb1dfb4365d803c8b6)]: - @langchain/langgraph@1.2.9 ## @examples/ui-angular@0.0.22 ### Patch Changes - Updated dependencies \[[`458d66b`](https://github.com/langchain-ai/langgraphjs/commit/458d66bf665468854abb8133594d4d4f966054ed), [`9102d52`](https://github.com/langchain-ai/langgraphjs/commit/9102d526c858a4cdbe9b47dcdd062b93da93e49f), [`b7c196b`](https://github.com/langchain-ai/langgraphjs/commit/b7c196b2142fb888dfcd9ceb1dfb4365d803c8b6)]: - @langchain/langgraph-sdk@1.8.9 - @langchain/langgraph@1.2.9 ## langgraph@1.0.31 ### Patch Changes - Updated dependencies \[[`9102d52`](https://github.com/langchain-ai/langgraphjs/commit/9102d526c858a4cdbe9b47dcdd062b93da93e49f), [`b7c196b`](https://github.com/langchain-ai/langgraphjs/commit/b7c196b2142fb888dfcd9ceb1dfb4365d803c8b6)]: - @langchain/langgraph@1.2.9 --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
dependabot[bot]
|
ac9947f64d |
chore(deps): bump langsmith from 0.5.19 to 0.5.20 (#2323)
Bumps [langsmith](https://github.com/langchain-ai/langsmith-sdk) from 0.5.19 to 0.5.20. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langsmith-sdk/commits">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/langgraphjs/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
a9db0172df |
chore(deps): bump hono from 4.12.12 to 4.12.14 (#2321)
Bumps [hono](https://github.com/honojs/hono) from 4.12.12 to 4.12.14. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/honojs/hono/releases">hono's releases</a>.</em></p> <blockquote> <h2>v4.12.14</h2> <h2>Security fixes</h2> <p>This release includes fixes for the following security issues:</p> <h3>Improper handling of JSX attribute names in hono/jsx SSR</h3> <p>Affects: hono/jsx. Fixes missing validation of JSX attribute names during server-side rendering, which could allow malformed attribute keys to corrupt the generated HTML output and inject unintended attributes or elements. GHSA-458j-xx4x-4375</p> <h2>Other changes</h2> <ul> <li>fix(aws-lambda): handle invalid header names in request processing (<a href="https://redirect.github.com/honojs/hono/issues/4883">#4883</a>) fa2c74fe</li> </ul> <h2>v4.12.13</h2> <h2>What's Changed</h2> <ul> <li>fix(types): infer response type from last handler in app.on 9-/10-handler overloads by <a href="https://github.com/T4ko0522"><code>@T4ko0522</code></a> in <a href="https://redirect.github.com/honojs/hono/pull/4865">honojs/hono#4865</a></li> <li>feat(trailing-slash): add <code>skip</code> option by <a href="https://github.com/yusukebe"><code>@yusukebe</code></a> in <a href="https://redirect.github.com/honojs/hono/pull/4862">honojs/hono#4862</a></li> <li>feat(cache): add <code>onCacheNotAvailable</code> option by <a href="https://github.com/yusukebe"><code>@yusukebe</code></a> in <a href="https://redirect.github.com/honojs/hono/pull/4876">honojs/hono#4876</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/T4ko0522"><code>@T4ko0522</code></a> made their first contribution in <a href="https://redirect.github.com/honojs/hono/pull/4865">honojs/hono#4865</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/honojs/hono/compare/v4.12.12...v4.12.13">https://github.com/honojs/hono/compare/v4.12.12...v4.12.13</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/honojs/hono/commit/cf2d2b7edcf07adef2db7614557f4d7f9e2be7ba"><code>cf2d2b7</code></a> 4.12.14</li> <li><a href="https://github.com/honojs/hono/commit/66daa2edef8965544c04fcad82c596ab2acdb5ee"><code>66daa2e</code></a> Merge commit from fork</li> <li><a href="https://github.com/honojs/hono/commit/fa2c74fe5c3ce996d025d9d97bf5670c207bb82e"><code>fa2c74f</code></a> fix(aws-lambda): handle invalid header names in request processing (<a href="https://redirect.github.com/honojs/hono/issues/4883">#4883</a>)</li> <li><a href="https://github.com/honojs/hono/commit/3779927c17201dc6bfd20697f0e1ec65407da779"><code>3779927</code></a> 4.12.13</li> <li><a href="https://github.com/honojs/hono/commit/faa6c46a1aa3a8b792b29e20fc93bcd6d2a4d720"><code>faa6c46</code></a> feat(cache): add <code>onCacheNotAvailable</code> option (<a href="https://redirect.github.com/honojs/hono/issues/4876">#4876</a>)</li> <li><a href="https://github.com/honojs/hono/commit/f23e97b7f300bcb8571ae864010b8f7cdb5d0d5d"><code>f23e97b</code></a> feat(trailing-slash): add <code>skip</code> option (<a href="https://redirect.github.com/honojs/hono/issues/4862">#4862</a>)</li> <li><a href="https://github.com/honojs/hono/commit/1aa32fb91e7bc1366811d80ebcce61ec0d0c68cb"><code>1aa32fb</code></a> fix(types): infer response type from last handler in app.on 9- and 10-handler...</li> <li>See full diff in <a href="https://github.com/honojs/hono/compare/v4.12.12...v4.12.14">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/langgraphjs/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Hunter Lovell
|
9102d526c8 |
fix(langgraph): propagate tracer metadata defaults from configurable (#2315)
## Summary This updates Pregel callback manager initialization to pass `tracerInheritableMetadata` defaults derived from `config.configurable`, and narrows `ensureLangGraphConfig` metadata mirroring to the allowlisted LangGraph identifiers used in stream/runtime metadata. ## Changes ### `@langchain/langgraph` (`libs/langgraph-core`) - Updated Pregel callback manager setup to configure core callbacks with `tracerInheritableMetadata` based on configurable primitive values, excluding internal and secret-like keys. - Hoisted tracing default logic into `_getTracingMetadataDefaults` and `_excludeAsMetadata` for parity with the Python implementation shape. - Restricted `ensureLangGraphConfig` configurable-to-metadata propagation to the identifier allowlist: - `thread_id` - `checkpoint_id` - `checkpoint_ns` - `task_id` - `run_id` - `assistant_id` - `graph_id` - Updated config tests to assert the narrowed metadata propagation behavior. |
||
|
dependabot[bot]
|
7da383a8e6 |
chore(deps-dev): bump vite from 7.3.1 to 7.3.2 (#2297)
Bumps [vite](https://github.com/vitejs/vite/tree/HEAD/packages/vite) from 7.3.1 to 7.3.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/vitejs/vite/releases">vite's releases</a>.</em></p> <blockquote> <h2>v7.3.2</h2> <p>Please refer to <a href="https://github.com/vitejs/vite/blob/v7.3.2/packages/vite/CHANGELOG.md">CHANGELOG.md</a> for details.</p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/vitejs/vite/blob/v7.3.2/packages/vite/CHANGELOG.md">vite's changelog</a>.</em></p> <blockquote> <h2><!-- raw HTML omitted --><a href="https://github.com/vitejs/vite/compare/v7.3.1...v7.3.2">7.3.2</a> (2026-04-06)<!-- raw HTML omitted --></h2> <h3>Bug Fixes</h3> <ul> <li>avoid path traversal with optimize deps sourcemap handler (<a href="https://redirect.github.com/vitejs/vite/issues/22161">#22161</a>) (<a href="https://github.com/vitejs/vite/commit/09d8c903bde12fee2710314d3b42bc789c686df7">09d8c90</a>)</li> <li>backport <a href="https://redirect.github.com/vitejs/vite/issues/22159">#22159</a>, apply server.fs check to env transport (<a href="https://redirect.github.com/vitejs/vite/issues/22162">#22162</a>) (<a href="https://github.com/vitejs/vite/commit/19db0f29c3a3ac4e64cc95c270716c77fd223ad1">19db0f2</a>)</li> <li>check <code>server.fs</code> after stripping query as well (<a href="https://redirect.github.com/vitejs/vite/issues/22160">#22160</a>) (<a href="https://github.com/vitejs/vite/commit/f8103cc946f137a54e395fe3f5d08e8209231ed6">f8103cc</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/vitejs/vite/commit/cc383e07b66d4c5a9768fcb570e0af812cb8d999"><code>cc383e0</code></a> release: v7.3.2</li> <li><a href="https://github.com/vitejs/vite/commit/09d8c903bde12fee2710314d3b42bc789c686df7"><code>09d8c90</code></a> fix: avoid path traversal with optimize deps sourcemap handler (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/22161">#22161</a>)</li> <li><a href="https://github.com/vitejs/vite/commit/f8103cc946f137a54e395fe3f5d08e8209231ed6"><code>f8103cc</code></a> fix: check <code>server.fs</code> after stripping query as well (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/22160">#22160</a>)</li> <li><a href="https://github.com/vitejs/vite/commit/19db0f29c3a3ac4e64cc95c270716c77fd223ad1"><code>19db0f2</code></a> fix: backport <a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/22159">#22159</a>, apply server.fs check to env transport (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/22162">#22162</a>)</li> <li>See full diff in <a href="https://github.com/vitejs/vite/commits/v7.3.2/packages/vite">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
5a0d0d0155 |
chore(deps): bump langsmith from 0.5.18 to 0.5.19 (#2319)
Bumps [langsmith](https://github.com/langchain-ai/langsmith-sdk) from 0.5.18 to 0.5.19. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langsmith-sdk/commits">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/langgraphjs/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Adrian Sajjan
|
458d66bf66 |
Prevent values from getting overrwritten on interrupt event (#2302)
Issue: In multi-agent sustem with handoffs like this example: https://docs.langchain.com/oss/python/langchain/multi-agent/handoffs#multiple-agent-subgraphs, if we trigger an interrupt from an agent within a swarm workflow, the interrupt is propagated and sent twice, the last interrupt contains values from the main graphs state, which is always going to be behind the state of the agent from where interrupt is triggered. So, temporarily, the message data becomes empty, it gets refilled when interrupt is resumed Fixes: Do not update values when interrupt is recieved, just update the interrupt in the state with the latest __interrupt data. --------- Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
open-swe[bot]
|
b7c196b214 |
fix: export missing types for typescript 6.0 declaration file compatibility (#2311)
## Description TypeScript 6.0 requires that any type emitted to a declaration file is reachable via the package's `exports` field. Several types used in `StateGraph`'s public API (class extends clause, constructor overloads, method signatures) were not exported from the package entrypoints, causing TS6 consumers to fail when exporting `StateGraph` instances from their own packages. Adds exports for: `ToStateDefinition`, `StateGraphNodeSpec`, `NodeSpec`, `AddNodeOptions`, `StateGraphAddNodeOptions`, `StateGraphArgsWithStateSchema`, `StateGraphArgsWithInputOutputSchemas`, `CachePolicy`, `AnyStateSchema`, `StateSchemaFieldToChannel`, `StateSchemaFieldsToStateDefinition`. ## Test Plan - [ ] Verify a TS6 project can export a `StateGraph` instance without declaration file errors - [ ] Build passes with `pnpm build` --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Christian Bromann <git@bromann.dev> |
||
|
dependabot[bot]
|
aa2cfc8bf7 |
chore(deps): bump langsmith from 0.5.16 to 0.5.18 (#2307)
Bumps [langsmith](https://github.com/langchain-ai/langsmith-sdk) from 0.5.16 to 0.5.18. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langsmith-sdk/commits">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/langchain-ai/langgraphjs/network/alerts). </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
9c1e3278fe |
chore(deps): bump @hono/node-server from 1.19.11 to 1.19.13 (#2300)
Bumps [@hono/node-server](https://github.com/honojs/node-server) from 1.19.11 to 1.19.13. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/honojs/node-server/releases"><code>@hono/node-server</code>'s releases</a>.</em></p> <blockquote> <h2>v1.19.13</h2> <h2>Security Fix</h2> <p>Fixed an issue in Serve Static Middleware where inconsistent handling of repeated slashes (<code>//</code>) between the router and static file resolution could allow middleware to be bypassed. Users of Serve Static Middleware are encouraged to upgrade to this version.</p> <p>See GHSA-92pp-h63x-v22m for details.</p> <h2>v1.19.12</h2> <h2>What's Changed</h2> <ul> <li>chore: ignore claude setting by <a href="https://github.com/yusukebe"><code>@yusukebe</code></a> in <a href="https://redirect.github.com/honojs/node-server/pull/314">honojs/node-server#314</a></li> <li>fix: request draining for early 413 responses by <a href="https://github.com/usualoma"><code>@usualoma</code></a> in <a href="https://redirect.github.com/honojs/node-server/pull/329">honojs/node-server#329</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/honojs/node-server/compare/v1.19.11...v1.19.12">https://github.com/honojs/node-server/compare/v1.19.11...v1.19.12</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/honojs/node-server/commit/fd64e659a34ec661fd9ccda00d1b9dff88dfaf90"><code>fd64e65</code></a> 1.19.13</li> <li><a href="https://github.com/honojs/node-server/commit/025c30f55d589ddbe6048b151d77e904f67a8cc2"><code>025c30f</code></a> Merge commit from fork</li> <li><a href="https://github.com/honojs/node-server/commit/6cdb5a724952f3df5748e435637792068ebea6d9"><code>6cdb5a7</code></a> 1.19.12</li> <li><a href="https://github.com/honojs/node-server/commit/70250f780ec99d2ddc0dd8275a42f8e091e06e94"><code>70250f7</code></a> fix: request draining for early 413 responses (<a href="https://redirect.github.com/honojs/node-server/issues/329">#329</a>)</li> <li><a href="https://github.com/honojs/node-server/commit/cfc08b330a1f2e0a2d8cc7797cde389465b5f4fb"><code>cfc08b3</code></a> chore: ignore claude setting (<a href="https://redirect.github.com/honojs/node-server/issues/314">#314</a>)</li> <li>See full diff in <a href="https://github.com/honojs/node-server/compare/v1.19.11...v1.19.13">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
96a92c01a6 |
chore(deps): bump hono from 4.12.7 to 4.12.12 (#2301)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
github-actions[bot]
|
9e9807523f |
chore: version packages (#2294)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
open-swe[bot]
|
e42c2c8836 |
feat: enhance runtime with executionInfo and serverInfo (#2275)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> Co-authored-by: Hunter Lovell <40191806+hntrl@users.noreply.github.com> |
||
|
github-actions[bot]
|
2a5b85bf55 |
chore: version packages (#2293)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
d74ef958ba | chore(sdk): strengthen framework browser stream tests (#2289) | ||
|
Christian Bromann
|
33293c7f3f | fix(sdk): buffer subagent messages instead of dropping them (#2292) | ||
|
github-actions[bot]
|
89fed91da2 |
chore: version packages (#2291)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
4cddca61ce | fix(vue): actually make it reactive (#2290) | ||
|
github-actions[bot]
|
3a81396657 |
chore: version packages (#2288)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
591d2dc70e | fix(sdk): subagent stream reactivity (#2287) | ||
|
github-actions[bot]
|
29f071d826 |
chore: version packages (#2286)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
a5dfdb61c7 | fix(sdk): detect interrupt for Python agents (#2285) | ||
|
github-actions[bot]
|
7176861f72 |
chore: version packages (#2284)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
github-actions[bot]
|
ed1107df54 |
chore: version packages (#2283)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
2b62610710 | feat(sdk): support for headless tools (#2281) | ||
|
github-actions[bot]
|
37e10413af |
chore: version packages (#2280)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
3bbb3ff65a | fix(sdk): better type inferrence (#2279) | ||
|
Christian Bromann
|
0d04099958 | fix(vue): Make subagents accessible once they are spun up (#2278) | ||
|
github-actions[bot]
|
b9bd6aec1d |
chore: version packages (#2277)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
e72c8e769e |
chore(deps-dev): bump the svelte group across 1 directory with 3 updates (#2272)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Christian Bromann <git@bromann.dev> |
||
|
Christian Bromann
|
05810fe087 |
Fix Vue subagent grouping during streaming (#2274)
Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Christian Bromann <christian-bromann@users.noreply.github.com> |
||
|
dependabot[bot]
|
2bb2ed4565 |
chore(deps): bump the vue group across 1 directory with 4 updates (#2273)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Hunter Lovell <hunter@hntrl.io> |
||
|
dependabot[bot]
|
271f9750f0 |
chore(deps): bump the langchain group across 1 directory with 7 updates (#2270)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
github-actions[bot]
|
981853c019 |
chore: version packages (#2264)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
73ae630253 |
chore(deps): bump the angular group with 13 updates (#2271)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
936b48b280 | fix(sdk): restore snake_case interrupt aliases (#2263) | ||
|
github-actions[bot]
|
0b51ec611f |
chore: version packages (#2254)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Bryan Dartout
|
d9d807ebb0 |
fix(sdk): accumulate parallel interrupts in StreamManager (#2204)
Co-authored-by: Christian Bromann <git@bromann.dev> |