[PR #417] [CLOSED] build(deps): bump the patch-deps-updates-main group across 1 directory with 9 updates #442

Closed
opened 2026-06-05 17:23:06 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/deepagentsjs/pull/417
Author: @dependabot[bot]
Created: 4/2/2026
Status: Closed

Base: mainHead: dependabot/npm_and_yarn/patch-deps-updates-main-f79728a7b3


📝 Commits (1)

  • 8518604 build(deps): bump the patch-deps-updates-main group across 1 directory with 9 updates

📊 Changes

1 file changed (+163 additions, -550 deletions)

View changed files

📝 pnpm-lock.yaml (+163 -550)

📄 Description

Bumps the patch-deps-updates-main group with 9 updates in the / directory:

Package From To
@langchain/core 1.1.33 1.1.38
@langchain/langgraph 1.2.3 1.2.6
@langchain/langgraph-checkpoint 1.0.0 1.0.1
tsdown 0.21.4 0.21.7
@langchain/langgraph-sdk 1.8.0 1.8.3
langchain 1.2.36 1.2.39
@langchain/anthropic 1.3.23 1.3.26
modal 0.7.1 0.7.3
langsmith 0.5.7 0.5.16

Updates @langchain/core from 1.1.33 to 1.1.38

Release notes

Sourced from @​langchain/core's releases.

@​langchain/core@​1.1.38

Patch Changes

@​langchain/core@​1.1.37

Patch Changes

  • #10511 6933769 Thanks @​hntrl! - cache Zod-to-JSON-Schema conversions in toJsonSchema()

  • #10541 50d5f32 Thanks @​jacoblee93! - revert: Revert "feat(core): Add all chat model/llm invocation params to metadata"

  • #10509 5552999 Thanks @​hntrl! - feat(openai): add support for phase parameter on Responses API messages

    • Extract phase from message output items and surface it on text content blocks
    • Support phase in streaming via response.output_item.added events
    • Round-trip phase through both raw provider and standard content paths
    • Move phase into extras dict in the core standard content translator
  • #10528 8331833 Thanks @​christian-bromann! - fix(core): normalize single-block content in mergeContent

@​langchain/core@​1.1.36

Patch Changes

  • #10512 bbbfea1 Thanks @​hntrl! - fix(core): fix streaming chunk merge for providers without index on tool call deltas

    _mergeLists now falls back to id-based matching when items don't have an index field. Previously, providers routing through the OpenAI-compatible API without index on streaming tool call deltas (e.g. Anthropic models via ChatOpenAI) would accumulate hundreds of individual raw deltas in tool_call_chunks and additional_kwargs.tool_calls instead of merging them into a single entry per tool call. In a real trace with 3 concurrent subagents, this caused a single AI message to balloon from ~4KB to 146KB -- with 826 uncollapsed streaming fragments carrying a few bytes each.

    Also fixes SystemMessage.concat() which used ...this to spread all instance properties (including lc_kwargs) into the new constructor, causing each chained concat() call to nest one level deeper. After 7 middleware concat() calls (typical in deepagents), a 7KB system prompt would serialize to 81KB due to content being duplicated at every nesting level.

@​langchain/core@​1.1.35

Patch Changes

  • #10327 5dc11b5 Thanks @​hntrl! - fix(core): replace exported zod type references with structural duck-type interfaces to fix TypeScript OOM

    Replaces all exported Zod type references (z3.ZodType, z4.$ZodType, etc.) in @langchain/core's public API with minimal structural ("duck-type") interfaces. This prevents TypeScript from performing expensive deep structural comparisons (~3,400+ lines of mutually recursive generics) when downstream packages resolve a different Zod version than @langchain/core, which was causing OOM crashes and unresponsive language servers in monorepo setups.

  • #10433 7af0b65 Thanks @​tanushree-sharma! - feat: Add LangSmith integration metadata to createAgent and initChatModel

@​langchain/core@​1.1.34

Patch Changes

Commits
  • 6b914bc chore: version packages (#10553)
  • 7ed93b8 fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (#10543)
  • 9270c48 fix(openai): preserve reasoning_content in ChatOpenAICompletions (#10551)
  • f548053 fix(langchain): bump langgraph dep (#10555)
  • 11a295f fix(langchain): add support for dynamic structured output (#10554)
  • 589ab9b fix(langchain): accept cross-version runnable models in createAgent (#10552)
  • cd86fea fix: implement tool choice required on anthropic (#10519)
  • b57760c chore: version packages (#10516)
  • 6e2d29e tests(@​langchain/google): Lyria 3 (#10522)
  • 68e0a19 fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (#10545)
  • Additional commits viewable in compare view

Updates @langchain/langgraph from 1.2.3 to 1.2.6

Release notes

Sourced from @​langchain/langgraph's releases.

@​langchain/langgraph@​1.2.6

Patch Changes

  • #2241 6ee23e8 Thanks @​pawel-twardziak! - feat: add browser support for interrupt, writer, and other Node-only exports

    Export interrupt, writer, pushMessage, getStore, getWriter, getConfig, getPreviousState, getCurrentTaskInput from web.ts and add a "browser" condition to the "." package export so browser bundlers resolve to web.js instead of pulling in node:async_hooks.

  • #2245 77af976 Thanks @​hntrl! - revert abort signal change that was causing problematic errors

  • #2242 bdcf290 Thanks @​hntrl! - clean up resolved checkpointer promises to reduce memory retention

  • Updated dependencies [88726df, 7dfcbff]:

    • @​langchain/langgraph-sdk@​1.8.1

@​langchain/langgraph@​1.2.5

Patch Changes

  • #2213 a09932a Thanks @​hntrl! - fix(core): prevent AbortSignal listener leak in stream() and streamEvents()

    Pregel.stream() and streamEvents() called combineAbortSignals() but discarded the dispose function, leaking one abort listener on the caller's signal per invocation. Over many invocations this caused unbounded memory growth as each leaked listener retained references to its associated graph execution state.

    • Use AbortSignal.any() on Node 20+ which handles listener lifecycle automatically via GC
    • Fall back to manual listener management on Node 18, with proper dispose() called when the stream completes or is cancelled
  • #2210 4d2e948 Thanks @​jackjin1997! - Fix AnyValue.update() returning false instead of true when values are received, aligning with all other channel implementations.

  • Updated dependencies [414a7ad]:

    • @​langchain/langgraph-sdk@​1.8.0

@​langchain/langgraph@​1.2.4

Patch Changes

Changelog

Sourced from @​langchain/langgraph's changelog.

1.2.6

Patch Changes

  • #2241 6ee23e8 Thanks @​pawel-twardziak! - feat: add browser support for interrupt, writer, and other Node-only exports

    Export interrupt, writer, pushMessage, getStore, getWriter, getConfig, getPreviousState, getCurrentTaskInput from web.ts and add a "browser" condition to the "." package export so browser bundlers resolve to web.js instead of pulling in node:async_hooks.

  • #2245 77af976 Thanks @​hntrl! - revert abort signal change that was causing problematic errors

  • #2242 bdcf290 Thanks @​hntrl! - clean up resolved checkpointer promises to reduce memory retention

  • Updated dependencies [88726df, 7dfcbff]:

    • @​langchain/langgraph-sdk@​1.8.1

1.2.5

Patch Changes

  • #2213 a09932a Thanks @​hntrl! - fix(core): prevent AbortSignal listener leak in stream() and streamEvents()

    Pregel.stream() and streamEvents() called combineAbortSignals() but discarded the dispose function, leaking one abort listener on the caller's signal per invocation. Over many invocations this caused unbounded memory growth as each leaked listener retained references to its associated graph execution state.

    • Use AbortSignal.any() on Node 20+ which handles listener lifecycle automatically via GC
    • Fall back to manual listener management on Node 18, with proper dispose() called when the stream completes or is cancelled
  • #2210 4d2e948 Thanks @​jackjin1997! - Fix AnyValue.update() returning false instead of true when values are received, aligning with all other channel implementations.

  • Updated dependencies [414a7ad]:

    • @​langchain/langgraph-sdk@​1.8.0

1.2.4

Patch Changes

Commits
  • 9905dd1 chore: version packages (#2238)
  • bdcf290 fix(langgraph): clean up resolved checkpointer promises to reduce memory rete...
  • 77af976 Revert "fix(core): prevent AbortSignal listener leak in stream() and streamEv...
  • 6ee23e8 fix: add createAgent and middleware to browser entry points (#2241)
  • 20feb58 feat: Add LangSmith integration metadata to langgraph (#2193)
  • d4456c0 chore: version packages (#2232)
  • a09932a fix(core): prevent AbortSignal listener leak in stream() and streamEvents() (...
  • 4d2e948 fix(langgraph-core): correct AnyValue channel update() return value (#2210)
  • c8185dd chore: version packages (#2216)
  • fe4dd5b Revert "chore: version packages (#2203)"
  • Additional commits viewable in compare view

Updates @langchain/langgraph-checkpoint from 1.0.0 to 1.0.1

Release notes

Sourced from @​langchain/langgraph-checkpoint's releases.

@​langchain/langgraph-checkpoint-sqlite@​1.0.1

Patch Changes

@​langchain/langgraph-checkpoint-postgres@​1.0.1

Patch Changes

@​langchain/langgraph-checkpoint@​1.0.1

Patch Changes

Changelog

Sourced from @​langchain/langgraph-checkpoint's changelog.

1.0.1

Patch Changes

Commits
Maintainer changes

This version was pushed to npm by [GitHub Actions](https://www.npmjs.com/~GitHub Actions), a new releaser for @​langchain/langgraph-checkpoint since your current version.

Install script changes

This version modifies prepublish script that runs during installation. Review the package contents before updating.


Updates tsdown from 0.21.4 to 0.21.7

Release notes

Sourced from tsdown's releases.

v0.21.7

   🚀 Features

  • Add module option for attw and publint to allow passing imported modules directly  -  by @​sxzz (31e90)

   🐞 Bug Fixes

  • deps: Add skipNodeModulesBundle dep subpath e2e tests and fix docs  -  by @​sxzz (deff7)
    View changes on GitHub

v0.21.6

   🚀 Features

   🐞 Bug Fixes

    View changes on GitHub

v0.21.5

   🚀 Features

   🐞 Bug Fixes

... (truncated)

Commits
  • 42467bd chore: release v0.21.7
  • 88d73a7 chore: upgrade deps
  • 5b1535e chore: remove jsr
  • 5d32818 docs: fix dead external links in docs and skills
  • c7483a0 docs: update link to Rolldown plugin development guide (#874)
  • deff72c fix(deps): add skipNodeModulesBundle dep subpath e2e tests and fix docs
  • 31e90c1 feat: add module option for attw and publint to allow passing imported modu...
  • 375a51c chore: release v0.21.6
  • e1403c0 chore: upgrade deps
  • 0005096 fix(entry): correctly output relative paths in logger output
  • Additional commits viewable in compare view

Updates @langchain/langgraph-sdk from 1.8.0 to 1.8.3

Release notes

Sourced from @​langchain/langgraph-sdk's releases.

@​langchain/langgraph-sdk@​1.8.3

Patch Changes

@​langchain/langgraph-sdk@​1.8.2

Patch Changes

@​langchain/langgraph-sdk@​1.8.1

Patch Changes

Changelog

Sourced from @​langchain/langgraph-sdk's changelog.

1.8.3

Patch Changes

1.8.2

Patch Changes

1.8.1

Patch Changes

Commits
  • 0b51ec6 chore: version packages (#2254)
  • d9d807e fix(sdk): accumulate parallel interrupts in StreamManager (#2204)
  • d88f29b chore(repo): migrate linting and formatting from ESLint/Prettier to oxlint/ox...
  • 7d88f57 chore: version packages (#2251)
  • 8eaf410 fix(sdk): skip post-stream getHistory for zero-arity onFinish (#2250)
  • 9905dd1 chore: version packages (#2238)
  • 7dfcbff fix(skd): normalize interrupts between JS and Python (#2243)
  • 88726df Extract shared WithClassMessages\<T> type to @langchain/langgraph-sdk/ui (...
  • See full diff in compare view

Updates langchain from 1.2.36 to 1.2.39

Release notes

Sourced from langchain's releases.

langchain@1.2.39

Patch Changes

langchain@1.2.38

Patch Changes

langchain@1.2.37

Patch Changes

  • #10475 3d35eb1 Thanks @​hntrl! - fix(langchain): add "aws" alias to MODEL_PROVIDER_CONFIG so hub/node auto-detects ChatBedrockConverse from Python-serialized prompts

  • #10258 ae4122f Thanks @​irfiacre! - Align Zod Importation For 'libs/langchain/src/agents/nodes/utils.ts'

  • Updated dependencies [bbbfea1]:

    • @​langchain/core@​1.1.36
Commits
  • 6b914bc chore: version packages (#10553)
  • 7ed93b8 fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (#10543)
  • 9270c48 fix(openai): preserve reasoning_content in ChatOpenAICompletions (#10551)
  • f548053 fix(langchain): bump langgraph dep (#10555)
  • 11a295f fix(langchain): add support for dynamic structured output (#10554)
  • 589ab9b fix(langchain): accept cross-version runnable models in createAgent (#10552)
  • cd86fea fix: implement tool choice required on anthropic (#10519)
  • b57760c chore: version packages (#10516)
  • 6e2d29e tests(@​langchain/google): Lyria 3 (#10522)
  • 68e0a19 fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (#10545)
  • Additional commits viewable in compare view

Updates @langchain/anthropic from 1.3.23 to 1.3.26

Release notes

Sourced from @​langchain/anthropic's releases.

@​langchain/anthropic@​1.3.26

Patch Changes

@​langchain/anthropic@​1.3.25

Patch Changes

@​langchain/anthropic@​1.3.24

Patch Changes

  • #10420 08657f2 Thanks @​pawel-twardziak! - Fix temperature/topK/topP handling: guard all three so undefined values are not set on the request object, and fix broken topK/topP validation when thinking is enabled.
  • Updated dependencies [6db417b, d69dfcc]:
    • @​langchain/core@​1.1.33
Commits
  • 6b914bc chore: version packages (#10553)
  • 7ed93b8 fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (#10543)
  • 9270c48 fix(openai): preserve reasoning_content in ChatOpenAICompletions (#10551)
  • f548053 fix(langchain): bump langgraph dep (#10555)
  • 11a295f fix(langchain): add support for dynamic structured output (#10554)
  • 589ab9b fix(langchain): accept cross-version runnable models in createAgent (#10552)
  • cd86fea fix: implement tool choice required on anthropic (#10519)
  • b57760c chore: version packages (#10516)
  • 6e2d29e tests(@​langchain/google): Lyria 3 (#10522)
  • 68e0a19 fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (#10545)
  • Additional commits viewable in compare view

Updates modal from 0.7.1 to 0.7.3

Changelog

Sourced from modal's changelog.

js/v0.7.3, go/v0.7.3

  • Migrated SDKs from github.com/modal-labs/libmodal to github.com/modal-labs/modal-client.

modal-js/v0.7.2, modal-go/v0.7.2

  • Updated Sandbox methods to wait for newly created sandboxes to be ready and not error immediately when it's not avaliable yet.
  • Fixed a bug in modal-js so that canceling sandbox.stdout or sandbox.stderr cleans up background resources.
  • Updated Sandbox (JS) to raise a better error when the sandbox was terminated.
Commits
Attestation changes

This version has no provenance attestation, while the previous version (0.7.1) was attested. Review the package versions before updating.


Updates langsmith from 0.5.7 to 0.5.16

Commits
Install script changes

This version modifies prepublish script that runs during installation. Review the package contents before updating.


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 commands and options

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 <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
  • @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
  • @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
  • @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
  • @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

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

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/deepagentsjs/pull/417 **Author:** [@dependabot[bot]](https://github.com/apps/dependabot) **Created:** 4/2/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `dependabot/npm_and_yarn/patch-deps-updates-main-f79728a7b3` --- ### 📝 Commits (1) - [`8518604`](https://github.com/langchain-ai/deepagentsjs/commit/8518604792310faa3fc60a6f3e5b362a8837d140) build(deps): bump the patch-deps-updates-main group across 1 directory with 9 updates ### 📊 Changes **1 file changed** (+163 additions, -550 deletions) <details> <summary>View changed files</summary> 📝 `pnpm-lock.yaml` (+163 -550) </details> ### 📄 Description Bumps the patch-deps-updates-main group with 9 updates in the / directory: | Package | From | To | | --- | --- | --- | | [@langchain/core](https://github.com/langchain-ai/langchainjs) | `1.1.33` | `1.1.38` | | [@langchain/langgraph](https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core) | `1.2.3` | `1.2.6` | | [@langchain/langgraph-checkpoint](https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/checkpoint) | `1.0.0` | `1.0.1` | | [tsdown](https://github.com/rolldown/tsdown) | `0.21.4` | `0.21.7` | | [@langchain/langgraph-sdk](https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk) | `1.8.0` | `1.8.3` | | [langchain](https://github.com/langchain-ai/langchainjs) | `1.2.36` | `1.2.39` | | [@langchain/anthropic](https://github.com/langchain-ai/langchainjs) | `1.3.23` | `1.3.26` | | [modal](https://github.com/modal-labs/modal-client) | `0.7.1` | `0.7.3` | | [langsmith](https://github.com/langchain-ai/langsmith-sdk) | `0.5.7` | `0.5.16` | Updates `@langchain/core` from 1.1.33 to 1.1.38 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases"><code>@​langchain/core</code>'s releases</a>.</em></p> <blockquote> <h2><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.38</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10552">#10552</a> <a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(langchain): accept cross-version runnable models in createAgent</li> </ul> <h2><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.37</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10511">#10511</a> <a href="https://github.com/langchain-ai/langchainjs/commit/6933769836fe3cec835588e5f8db9883200865f6"><code>6933769</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - cache Zod-to-JSON-Schema conversions in toJsonSchema()</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10541">#10541</a> <a href="https://github.com/langchain-ai/langchainjs/commit/50d5f32fd30cabebf058b1c13255c1daadde6107"><code>50d5f32</code></a> Thanks <a href="https://github.com/jacoblee93"><code>@​jacoblee93</code></a>! - revert: Revert &quot;feat(core): Add all chat model/llm invocation params to metadata&quot;</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10509">#10509</a> <a href="https://github.com/langchain-ai/langchainjs/commit/555299917c90322e25d7671bad2e20c9b104bad6"><code>5552999</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - feat(openai): add support for phase parameter on Responses API messages</p> <ul> <li>Extract <code>phase</code> from message output items and surface it on text content blocks</li> <li>Support phase in streaming via <code>response.output_item.added</code> events</li> <li>Round-trip phase through both raw provider and standard content paths</li> <li>Move phase into <code>extras</code> dict in the core standard content translator</li> </ul> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10528">#10528</a> <a href="https://github.com/langchain-ai/langchainjs/commit/8331833c93ba907063c9fe28e9f935ed5dfec11c"><code>8331833</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(core): normalize single-block content in mergeContent</p> </li> </ul> <h2><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.36</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10512">#10512</a> <a href="https://github.com/langchain-ai/langchainjs/commit/bbbfea185c0777ae06df2b24a1a84f941d499c2a"><code>bbbfea1</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix(core): fix streaming chunk merge for providers without <code>index</code> on tool call deltas</p> <p><code>_mergeLists</code> now falls back to <code>id</code>-based matching when items don't have an <code>index</code> field. Previously, providers routing through the OpenAI-compatible API without <code>index</code> on streaming tool call deltas (e.g. Anthropic models via <code>ChatOpenAI</code>) would accumulate hundreds of individual raw deltas in <code>tool_call_chunks</code> and <code>additional_kwargs.tool_calls</code> instead of merging them into a single entry per tool call. In a real trace with 3 concurrent subagents, this caused a single AI message to balloon from ~4KB to 146KB -- with 826 uncollapsed streaming fragments carrying a few bytes each.</p> <p>Also fixes <code>SystemMessage.concat()</code> which used <code>...this</code> to spread all instance properties (including <code>lc_kwargs</code>) into the new constructor, causing each chained <code>concat()</code> call to nest one level deeper. After 7 middleware <code>concat()</code> calls (typical in deepagents), a 7KB system prompt would serialize to 81KB due to content being duplicated at every nesting level.</p> </li> </ul> <h2><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.35</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10327">#10327</a> <a href="https://github.com/langchain-ai/langchainjs/commit/5dc11b55cccfe35e4dad910a33e904cf49b3088a"><code>5dc11b5</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix(core): replace exported zod type references with structural duck-type interfaces to fix TypeScript OOM</p> <p>Replaces all exported Zod type references (<code>z3.ZodType</code>, <code>z4.$ZodType</code>, etc.) in <code>@langchain/core</code>'s public API with minimal structural (&quot;duck-type&quot;) interfaces. This prevents TypeScript from performing expensive deep structural comparisons (~3,400+ lines of mutually recursive generics) when downstream packages resolve a different Zod version than <code>@langchain/core</code>, which was causing OOM crashes and unresponsive language servers in monorepo setups.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10433">#10433</a> <a href="https://github.com/langchain-ai/langchainjs/commit/7af0b65d5ab9a173b528d6a821d269a79fbabdc6"><code>7af0b65</code></a> Thanks <a href="https://github.com/tanushree-sharma"><code>@​tanushree-sharma</code></a>! - feat: Add LangSmith integration metadata to createAgent and initChatModel</p> </li> </ul> <h2><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.34</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10312">#10312</a> <a href="https://github.com/langchain-ai/langchainjs/commit/bfb7944a105470eee98fe4a0eef91e586600e1de"><code>bfb7944</code></a> Thanks <a href="https://github.com/jacoblee93"><code>@​jacoblee93</code></a>! - feat(core): Add all invocation params as part of metadata</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6b914bceb4acd4664b12091770a2ddcbf5d8457e"><code>6b914bc</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10553">#10553</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/7ed93b8b8a6e9eb0da3e103d74087c692fee2773"><code>7ed93b8</code></a> fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10543">#10543</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/9270c48d7a95db6e7e2570a7e681c94479a673d0"><code>9270c48</code></a> fix(openai): preserve reasoning_content in ChatOpenAICompletions (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10551">#10551</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f54805305787fa383c3ce1e287daafdb5464a98b"><code>f548053</code></a> fix(langchain): bump langgraph dep (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10555">#10555</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/11a295fdadec3809f40c10492e3fd474e832c468"><code>11a295f</code></a> fix(langchain): add support for dynamic structured output (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10554">#10554</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a> fix(langchain): accept cross-version runnable models in createAgent (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10552">#10552</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/cd86fea8de2130d0df60805baada81958d47c747"><code>cd86fea</code></a> fix: implement tool choice required on anthropic (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10519">#10519</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/b57760c55a721ed65a456bbad11172e35adee177"><code>b57760c</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10516">#10516</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6e2d29e28a8f2a84f6fbbe5755d6b4fe2d5d4fd1"><code>6e2d29e</code></a> tests(<code>@​langchain/google</code>): Lyria 3 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10522">#10522</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/68e0a19238be592514b6c01243c41aefaa6a7668"><code>68e0a19</code></a> fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10545">#10545</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/core@1.1.33...@langchain/core@1.1.38">compare view</a></li> </ul> </details> <br /> Updates `@langchain/langgraph` from 1.2.3 to 1.2.6 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/releases"><code>@​langchain/langgraph</code>'s releases</a>.</em></p> <blockquote> <h2><code>@​langchain/langgraph</code><a href="https://github.com/1"><code>@​1</code></a>.2.6</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2241">#2241</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/6ee23e819b5da43a5a0c62560f85a9037a427630"><code>6ee23e8</code></a> Thanks <a href="https://github.com/pawel-twardziak"><code>@​pawel-twardziak</code></a>! - feat: add browser support for interrupt, writer, and other Node-only exports</p> <p>Export <code>interrupt</code>, <code>writer</code>, <code>pushMessage</code>, <code>getStore</code>, <code>getWriter</code>, <code>getConfig</code>, <code>getPreviousState</code>, <code>getCurrentTaskInput</code> from <code>web.ts</code> and add a <code>&quot;browser&quot;</code> condition to the <code>&quot;.&quot;</code> package export so browser bundlers resolve to <code>web.js</code> instead of pulling in <code>node:async_hooks</code>.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2245">#2245</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/77af97650c0f1671338911994c2e355b29489528"><code>77af976</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - revert abort signal change that was causing problematic errors</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2242">#2242</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/bdcf290198ce5cea4367ee8c9f1cbbbcf14d05e4"><code>bdcf290</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - clean up resolved checkpointer promises to reduce memory retention</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/88726dfe222aed64e5cd5dfa6f77f886b5a0d205"><code>88726df</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/7dfcbffd4805b2b4cc41f07f30be57ed732786b4"><code>7dfcbff</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.1</li> </ul> </li> </ul> <h2><code>@​langchain/langgraph</code><a href="https://github.com/1"><code>@​1</code></a>.2.5</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2213">#2213</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/a09932a203062d52e98e6dc5fd80ab572b123700"><code>a09932a</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix(core): prevent AbortSignal listener leak in stream() and streamEvents()</p> <p><code>Pregel.stream()</code> and <code>streamEvents()</code> called <code>combineAbortSignals()</code> but discarded the <code>dispose</code> function, leaking one abort listener on the caller's signal per invocation. Over many invocations this caused unbounded memory growth as each leaked listener retained references to its associated graph execution state.</p> <ul> <li>Use <code>AbortSignal.any()</code> on Node 20+ which handles listener lifecycle automatically via GC</li> <li>Fall back to manual listener management on Node 18, with proper <code>dispose()</code> called when the stream completes or is cancelled</li> </ul> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2210">#2210</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/4d2e9483208e105b7c45ab1cbc8ac8d540fbb23d"><code>4d2e948</code></a> Thanks <a href="https://github.com/jackjin1997"><code>@​jackjin1997</code></a>! - Fix <code>AnyValue.update()</code> returning <code>false</code> instead of <code>true</code> when values are received, aligning with all other channel implementations.</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/414a7adf908ba4f7ffef4985df3a95f14202591b"><code>414a7ad</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.0</li> </ul> </li> </ul> <h2><code>@​langchain/langgraph</code><a href="https://github.com/1"><code>@​1</code></a>.2.4</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(sdk): fetch subagent history</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.7.5</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/blob/main/libs/langgraph-core/CHANGELOG.md"><code>@​langchain/langgraph</code>'s changelog</a>.</em></p> <blockquote> <h2>1.2.6</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2241">#2241</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/6ee23e819b5da43a5a0c62560f85a9037a427630"><code>6ee23e8</code></a> Thanks <a href="https://github.com/pawel-twardziak"><code>@​pawel-twardziak</code></a>! - feat: add browser support for interrupt, writer, and other Node-only exports</p> <p>Export <code>interrupt</code>, <code>writer</code>, <code>pushMessage</code>, <code>getStore</code>, <code>getWriter</code>, <code>getConfig</code>, <code>getPreviousState</code>, <code>getCurrentTaskInput</code> from <code>web.ts</code> and add a <code>&quot;browser&quot;</code> condition to the <code>&quot;.&quot;</code> package export so browser bundlers resolve to <code>web.js</code> instead of pulling in <code>node:async_hooks</code>.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2245">#2245</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/77af97650c0f1671338911994c2e355b29489528"><code>77af976</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - revert abort signal change that was causing problematic errors</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2242">#2242</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/bdcf290198ce5cea4367ee8c9f1cbbbcf14d05e4"><code>bdcf290</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - clean up resolved checkpointer promises to reduce memory retention</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/88726dfe222aed64e5cd5dfa6f77f886b5a0d205"><code>88726df</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/7dfcbffd4805b2b4cc41f07f30be57ed732786b4"><code>7dfcbff</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.1</li> </ul> </li> </ul> <h2>1.2.5</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2213">#2213</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/a09932a203062d52e98e6dc5fd80ab572b123700"><code>a09932a</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix(core): prevent AbortSignal listener leak in stream() and streamEvents()</p> <p><code>Pregel.stream()</code> and <code>streamEvents()</code> called <code>combineAbortSignals()</code> but discarded the <code>dispose</code> function, leaking one abort listener on the caller's signal per invocation. Over many invocations this caused unbounded memory growth as each leaked listener retained references to its associated graph execution state.</p> <ul> <li>Use <code>AbortSignal.any()</code> on Node 20+ which handles listener lifecycle automatically via GC</li> <li>Fall back to manual listener management on Node 18, with proper <code>dispose()</code> called when the stream completes or is cancelled</li> </ul> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2210">#2210</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/4d2e9483208e105b7c45ab1cbc8ac8d540fbb23d"><code>4d2e948</code></a> Thanks <a href="https://github.com/jackjin1997"><code>@​jackjin1997</code></a>! - Fix <code>AnyValue.update()</code> returning <code>false</code> instead of <code>true</code> when values are received, aligning with all other channel implementations.</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/414a7adf908ba4f7ffef4985df3a95f14202591b"><code>414a7ad</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.0</li> </ul> </li> </ul> <h2>1.2.4</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(sdk): fetch subagent history</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>, <a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a>]:</p> <ul> <li><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.7.5</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/9905dd102e7f68d00fc026d950e8fda033c9dded"><code>9905dd1</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2238">#2238</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/bdcf290198ce5cea4367ee8c9f1cbbbcf14d05e4"><code>bdcf290</code></a> fix(langgraph): clean up resolved checkpointer promises to reduce memory rete...</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/77af97650c0f1671338911994c2e355b29489528"><code>77af976</code></a> Revert &quot;fix(core): prevent AbortSignal listener leak in stream() and streamEv...</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/6ee23e819b5da43a5a0c62560f85a9037a427630"><code>6ee23e8</code></a> fix: add createAgent and middleware to browser entry points (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2241">#2241</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/20feb58300765f2eec2c028f6d3deec8b548706d"><code>20feb58</code></a> feat: Add LangSmith integration metadata to langgraph (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2193">#2193</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/d4456c06f42572ca6885f91fa5b1f0dbc8052385"><code>d4456c0</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2232">#2232</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/a09932a203062d52e98e6dc5fd80ab572b123700"><code>a09932a</code></a> fix(core): prevent AbortSignal listener leak in stream() and streamEvents() (...</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/4d2e9483208e105b7c45ab1cbc8ac8d540fbb23d"><code>4d2e948</code></a> fix(langgraph-core): correct AnyValue channel update() return value (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2210">#2210</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/c8185ddb4b466accbeaf118b7a41aff8866d3ad6"><code>c8185dd</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2216">#2216</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/fe4dd5b85d285f78b6d499b1f1013927931ea634"><code>fe4dd5b</code></a> Revert &quot;chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2203">#2203</a>)&quot;</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langgraphjs/commits/@langchain/langgraph@1.2.6/libs/langgraph-core">compare view</a></li> </ul> </details> <br /> Updates `@langchain/langgraph-checkpoint` from 1.0.0 to 1.0.1 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/releases"><code>@​langchain/langgraph-checkpoint</code>'s releases</a>.</em></p> <blockquote> <h2><code>@​langchain/langgraph-checkpoint-sqlite</code><a href="https://github.com/1"><code>@​1</code></a>.0.1</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/1902">#1902</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/2378b9e951ff245a3e8a502acf42be55cce35a46"><code>2378b9e</code></a> Thanks <a href="https://github.com/warjiang"><code>@​warjiang</code></a>! - chore: upgrade better-sqlite</li> </ul> <h2><code>@​langchain/langgraph-checkpoint-postgres</code><a href="https://github.com/1"><code>@​1</code></a>.0.1</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/1979">#1979</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/d65f5a75e58e282fea831d8f126391823f241a78"><code>d65f5a7</code></a> Thanks <a href="https://github.com/Siretu"><code>@​Siretu</code></a>! - fix: quote PostgreSQL schema identifiers to support schemas with dashes</li> </ul> <h2><code>@​langchain/langgraph-checkpoint</code><a href="https://github.com/1"><code>@​1</code></a>.0.1</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2190">#2190</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/b6cfe555bfb498fe24fa85847f0fe5d1194dfa39"><code>b6cfe55</code></a> Thanks <a href="https://github.com/colifran"><code>@​colifran</code></a>! - feat(langgraph): implement uint8array support for json plus serializer</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/blob/main/libs/checkpoint/CHANGELOG.md"><code>@​langchain/langgraph-checkpoint</code>'s changelog</a>.</em></p> <blockquote> <h2>1.0.1</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2190">#2190</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/b6cfe555bfb498fe24fa85847f0fe5d1194dfa39"><code>b6cfe55</code></a> Thanks <a href="https://github.com/colifran"><code>@​colifran</code></a>! - feat(langgraph): implement uint8array support for json plus serializer</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langgraphjs/commits/@langchain/langgraph-checkpoint@1.0.1/libs/checkpoint">compare view</a></li> </ul> </details> <details> <summary>Maintainer changes</summary> <p>This version was pushed to npm by [GitHub Actions](<a href="https://www.npmjs.com/~GitHub">https://www.npmjs.com/~GitHub</a> Actions), a new releaser for <code>@​langchain/langgraph-checkpoint</code> since your current version.</p> </details> <details> <summary>Install script changes</summary> <p>This version modifies <code>prepublish</code> script that runs during installation. Review the package contents before updating.</p> </details> <br /> Updates `tsdown` from 0.21.4 to 0.21.7 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/rolldown/tsdown/releases">tsdown's releases</a>.</em></p> <blockquote> <h2>v0.21.7</h2> <h3>   🚀 Features</h3> <ul> <li>Add <code>module</code> option for attw and publint to allow passing imported modules directly  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/31e90c1"><!-- raw HTML omitted -->(31e90)<!-- raw HTML omitted --></a></li> </ul> <h3>   🐞 Bug Fixes</h3> <ul> <li><strong>deps</strong>: Add skipNodeModulesBundle dep subpath e2e tests and fix docs  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/deff72c"><!-- raw HTML omitted -->(deff7)<!-- raw HTML omitted --></a></li> </ul> <h5>    <a href="https://github.com/rolldown/tsdown/compare/v0.21.6...v0.21.7">View changes on GitHub</a></h5> <h2>v0.21.6</h2> <h3>   🚀 Features</h3> <ul> <li>Upgrade rolldown to v1.0.0-rc.12  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/512926d"><!-- raw HTML omitted -->(51292)<!-- raw HTML omitted --></a></li> <li><strong>config</strong>: <ul> <li>Pass root config to workspace config functions  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/7616960"><!-- raw HTML omitted -->(76169)<!-- raw HTML omitted --></a></li> <li>Use mergeConfig for workspace config merging and support variadic overrides  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/148aaaa"><!-- raw HTML omitted -->(148aa)<!-- raw HTML omitted --></a></li> </ul> </li> <li><strong>dts</strong>: <ul> <li>Add <code>cjsReexport</code> option to eliminate dual module type hazard  -  by <a href="https://github.com/mandarini"><code>@​mandarini</code></a> and <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/856">rolldown/tsdown#856</a> <a href="https://github.com/rolldown/tsdown/commit/875c1b3"><!-- raw HTML omitted -->(875c1)<!-- raw HTML omitted --></a></li> </ul> </li> <li><strong>exports</strong>: <ul> <li>Add <code>bin</code> option to auto-generate package.json bin field  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/869">rolldown/tsdown#869</a> <a href="https://github.com/rolldown/tsdown/commit/7ebd62d"><!-- raw HTML omitted -->(7ebd6)<!-- raw HTML omitted --></a></li> </ul> </li> </ul> <h3>   🐞 Bug Fixes</h3> <ul> <li><strong>css</strong>: <ul> <li>Compile preprocessor langs in virtual CSS modules  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/865">rolldown/tsdown#865</a> <a href="https://github.com/rolldown/tsdown/commit/7b2e0f9"><!-- raw HTML omitted -->(7b2e0)<!-- raw HTML omitted --></a></li> <li>Strip <code>.module</code> from CSS output filenames  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/866">rolldown/tsdown#866</a> <a href="https://github.com/rolldown/tsdown/commit/03ade19"><!-- raw HTML omitted -->(03ade)<!-- raw HTML omitted --></a></li> <li>Default splitting to true in unbundle mode for CSS inject  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/867">rolldown/tsdown#867</a> <a href="https://github.com/rolldown/tsdown/commit/a4da6af"><!-- raw HTML omitted -->(a4da6)<!-- raw HTML omitted --></a></li> <li>Split CSS plugin into pre/post phases for scoped CSS support  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/870">rolldown/tsdown#870</a> <a href="https://github.com/rolldown/tsdown/commit/ff0c45a"><!-- raw HTML omitted -->(ff0c4)<!-- raw HTML omitted --></a></li> </ul> </li> <li><strong>entry</strong>: <ul> <li>Correctly output relative paths in logger output  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/0005096"><!-- raw HTML omitted -->(00050)<!-- raw HTML omitted --></a></li> </ul> </li> </ul> <h5>    <a href="https://github.com/rolldown/tsdown/compare/v0.21.5...v0.21.6">View changes on GitHub</a></h5> <h2>v0.21.5</h2> <h3>   🚀 Features</h3> <ul> <li>Update rolldown to 1.0.0-rc.10  -  by <a href="https://github.com/wChenonly"><code>@​wChenonly</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/845">rolldown/tsdown#845</a> <a href="https://github.com/rolldown/tsdown/commit/414113d"><!-- raw HTML omitted -->(41411)<!-- raw HTML omitted --></a></li> <li>Support typescript v6  -  by <a href="https://github.com/ocavue"><code>@​ocavue</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/858">rolldown/tsdown#858</a> <a href="https://github.com/rolldown/tsdown/commit/bffc416"><!-- raw HTML omitted -->(bffc4)<!-- raw HTML omitted --></a></li> </ul> <h3>   🐞 Bug Fixes</h3> <ul> <li><strong>css</strong>: <ul> <li>Run final minification on merged CSS output  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/853">rolldown/tsdown#853</a> <a href="https://github.com/rolldown/tsdown/commit/475df0c"><!-- raw HTML omitted -->(475df)<!-- raw HTML omitted --></a></li> <li>Don't override internal importer  -  by <a href="https://github.com/Laupetin"><code>@​Laupetin</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/860">rolldown/tsdown#860</a> <a href="https://github.com/rolldown/tsdown/commit/af40e43"><!-- raw HTML omitted -->(af40e)<!-- raw HTML omitted --></a></li> <li>Use aliased exports for CSS module keys  -  by <a href="https://github.com/wChenonly"><code>@​wChenonly</code></a> and <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/840">rolldown/tsdown#840</a> <a href="https://github.com/rolldown/tsdown/commit/bb6decb"><!-- raw HTML omitted -->(bb6de)<!-- raw HTML omitted --></a></li> </ul> </li> <li><strong>deps</strong>: <ul> <li>External <code>optionalDependencies</code> by default  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> <a href="https://github.com/rolldown/tsdown/commit/cd24d3e"><!-- raw HTML omitted -->(cd24d)<!-- raw HTML omitted --></a></li> <li>Resolve subpath extensions for packages without exports field  -  by <a href="https://github.com/sxzz"><code>@​sxzz</code></a> in <a href="https://redirect.github.com/rolldown/tsdown/issues/863">rolldown/tsdown#863</a> <a href="https://github.com/rolldown/tsdown/commit/c51502b"><!-- raw HTML omitted -->(c5150)<!-- raw HTML omitted --></a></li> </ul> </li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/rolldown/tsdown/commit/42467bd1e223c82bb2cf9d01d028be75c908dc31"><code>42467bd</code></a> chore: release v0.21.7</li> <li><a href="https://github.com/rolldown/tsdown/commit/88d73a790f6b097d6c36938bffddfa450dc875ec"><code>88d73a7</code></a> chore: upgrade deps</li> <li><a href="https://github.com/rolldown/tsdown/commit/5b1535ef67cb9855de88c73de4789138f7984f09"><code>5b1535e</code></a> chore: remove jsr</li> <li><a href="https://github.com/rolldown/tsdown/commit/5d328185c9d6ce9aedc5d29331f02ba5b07944bc"><code>5d32818</code></a> docs: fix dead external links in docs and skills</li> <li><a href="https://github.com/rolldown/tsdown/commit/c7483a038b337284d0dd2c0c2a232606d6c66b05"><code>c7483a0</code></a> docs: update link to Rolldown plugin development guide (<a href="https://redirect.github.com/rolldown/tsdown/issues/874">#874</a>)</li> <li><a href="https://github.com/rolldown/tsdown/commit/deff72cc258515f7226cf2302612bb6da2dde658"><code>deff72c</code></a> fix(deps): add skipNodeModulesBundle dep subpath e2e tests and fix docs</li> <li><a href="https://github.com/rolldown/tsdown/commit/31e90c1f1878b9d23e7330fdbb56be2ca49c0446"><code>31e90c1</code></a> feat: add <code>module</code> option for attw and publint to allow passing imported modu...</li> <li><a href="https://github.com/rolldown/tsdown/commit/375a51ccb8f40768fac9a5432f6426bb0751bb13"><code>375a51c</code></a> chore: release v0.21.6</li> <li><a href="https://github.com/rolldown/tsdown/commit/e1403c023e6b83dea76e8cf6394d8c4a43f25141"><code>e1403c0</code></a> chore: upgrade deps</li> <li><a href="https://github.com/rolldown/tsdown/commit/000509653d41b328cc937a6d13c69cdec6c42bc3"><code>0005096</code></a> fix(entry): correctly output relative paths in logger output</li> <li>Additional commits viewable in <a href="https://github.com/rolldown/tsdown/compare/v0.21.4...v0.21.7">compare view</a></li> </ul> </details> <br /> Updates `@langchain/langgraph-sdk` from 1.8.0 to 1.8.3 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/releases"><code>@​langchain/langgraph-sdk</code>'s releases</a>.</em></p> <blockquote> <h2><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.3</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2204">#2204</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/d9d807ebb0398a43a07412fb034a65fc598c0731"><code>d9d807e</code></a> Thanks <a href="https://github.com/brydar"><code>@​brydar</code></a>! - fix(sdk): accumulate parallel interrupts in StreamManager</li> </ul> <h2><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.2</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2250">#2250</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/8eaf41069264753947e5c9633b567e589dc0e532"><code>8eaf410</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(sdk): skip post-stream getHistory for zero-arity onFinish</li> </ul> <h2><code>@​langchain/langgraph-sdk</code><a href="https://github.com/1"><code>@​1</code></a>.8.1</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2237">#2237</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/88726dfe222aed64e5cd5dfa6f77f886b5a0d205"><code>88726df</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - Extract shared <code>WithClassMessages&lt;T&gt;</code> type to <code>@langchain/langgraph-sdk/ui</code></p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2243">#2243</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/7dfcbffd4805b2b4cc41f07f30be57ed732786b4"><code>7dfcbff</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(skd): normalize interrupts between JS and Python</p> </li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langgraphjs/blob/main/libs/sdk/CHANGELOG.md"><code>@​langchain/langgraph-sdk</code>'s changelog</a>.</em></p> <blockquote> <h2>1.8.3</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2204">#2204</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/d9d807ebb0398a43a07412fb034a65fc598c0731"><code>d9d807e</code></a> Thanks <a href="https://github.com/brydar"><code>@​brydar</code></a>! - fix(sdk): accumulate parallel interrupts in StreamManager</li> </ul> <h2>1.8.2</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2250">#2250</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/8eaf41069264753947e5c9633b567e589dc0e532"><code>8eaf410</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(sdk): skip post-stream getHistory for zero-arity onFinish</li> </ul> <h2>1.8.1</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2237">#2237</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/88726dfe222aed64e5cd5dfa6f77f886b5a0d205"><code>88726df</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - Extract shared <code>WithClassMessages&lt;T&gt;</code> type to <code>@langchain/langgraph-sdk/ui</code></p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2243">#2243</a> <a href="https://github.com/langchain-ai/langgraphjs/commit/7dfcbffd4805b2b4cc41f07f30be57ed732786b4"><code>7dfcbff</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(skd): normalize interrupts between JS and Python</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/0b51ec611f9f763f73d0fd88541c57c48b146106"><code>0b51ec6</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2254">#2254</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/d9d807ebb0398a43a07412fb034a65fc598c0731"><code>d9d807e</code></a> fix(sdk): accumulate parallel interrupts in StreamManager (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2204">#2204</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/d88f29ba2558579781e60307947dba47290d58a1"><code>d88f29b</code></a> chore(repo): migrate linting and formatting from ESLint/Prettier to oxlint/ox...</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/7d88f577b82b7ef2fcebbd01fc7354901d895cec"><code>7d88f57</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2251">#2251</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/8eaf41069264753947e5c9633b567e589dc0e532"><code>8eaf410</code></a> fix(sdk): skip post-stream getHistory for zero-arity onFinish (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2250">#2250</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/9905dd102e7f68d00fc026d950e8fda033c9dded"><code>9905dd1</code></a> chore: version packages (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2238">#2238</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/7dfcbffd4805b2b4cc41f07f30be57ed732786b4"><code>7dfcbff</code></a> fix(skd): normalize interrupts between JS and Python (<a href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/sdk/issues/2243">#2243</a>)</li> <li><a href="https://github.com/langchain-ai/langgraphjs/commit/88726dfe222aed64e5cd5dfa6f77f886b5a0d205"><code>88726df</code></a> Extract shared <code>WithClassMessages\&lt;T&gt;</code> type to <code>@langchain/langgraph-sdk/ui</code> (...</li> <li>See full diff in <a href="https://github.com/langchain-ai/langgraphjs/commits/@langchain/langgraph-sdk@1.8.3/libs/sdk">compare view</a></li> </ul> </details> <br /> Updates `langchain` from 1.2.36 to 1.2.39 <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@1.2.39</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10543">#10543</a> <a href="https://github.com/langchain-ai/langchainjs/commit/7ed93b8b8a6e9eb0da3e103d74087c692fee2773"><code>7ed93b8</code></a> Thanks <a href="https://github.com/pawel-twardziak"><code>@​pawel-twardziak</code></a>! - fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10554">#10554</a> <a href="https://github.com/langchain-ai/langchainjs/commit/11a295fdadec3809f40c10492e3fd474e832c468"><code>11a295f</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(langchain): add support for dynamic structured output</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10555">#10555</a> <a href="https://github.com/langchain-ai/langchainjs/commit/f54805305787fa383c3ce1e287daafdb5464a98b"><code>f548053</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(langchain): bump langgraph dep</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10552">#10552</a> <a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@​christian-bromann</code></a>! - fix(langchain): accept cross-version runnable models in createAgent</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a>]:</p> <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.38</li> </ul> </li> </ul> <h2>langchain@1.2.38</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10527">#10527</a> <a href="https://github.com/langchain-ai/langchainjs/commit/3408008fe59eb8ee72f733349ae85afe5c23eaca"><code>3408008</code></a> Thanks <a href="https://github.com/pawel-twardziak"><code>@​pawel-twardziak</code></a>! - fix(langchain): export createAgent and prebuilt middleware from browser entry point</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10545">#10545</a> <a href="https://github.com/langchain-ai/langchainjs/commit/68e0a19238be592514b6c01243c41aefaa6a7668"><code>68e0a19</code></a> Thanks <a href="https://github.com/JadenKim-dev"><code>@​JadenKim-dev</code></a>! - fix(langchain): revert zod import in utils.ts to fix v3/v4 interop</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/6933769836fe3cec835588e5f8db9883200865f6"><code>6933769</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/50d5f32fd30cabebf058b1c13255c1daadde6107"><code>50d5f32</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/555299917c90322e25d7671bad2e20c9b104bad6"><code>5552999</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/8331833c93ba907063c9fe28e9f935ed5dfec11c"><code>8331833</code></a>]:</p> <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.37</li> </ul> </li> </ul> <h2>langchain@1.2.37</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10475">#10475</a> <a href="https://github.com/langchain-ai/langchainjs/commit/3d35eb112b46b36aea80cebe0147e315d03a1d8e"><code>3d35eb1</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix(langchain): add &quot;aws&quot; alias to MODEL_PROVIDER_CONFIG so hub/node auto-detects ChatBedrockConverse from Python-serialized prompts</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10258">#10258</a> <a href="https://github.com/langchain-ai/langchainjs/commit/ae4122f9523904423504e5a92c134c625977261d"><code>ae4122f</code></a> Thanks <a href="https://github.com/irfiacre"><code>@​irfiacre</code></a>! - Align Zod Importation For 'libs/langchain/src/agents/nodes/utils.ts'</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/bbbfea185c0777ae06df2b24a1a84f941d499c2a"><code>bbbfea1</code></a>]:</p> <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.36</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6b914bceb4acd4664b12091770a2ddcbf5d8457e"><code>6b914bc</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10553">#10553</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/7ed93b8b8a6e9eb0da3e103d74087c692fee2773"><code>7ed93b8</code></a> fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10543">#10543</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/9270c48d7a95db6e7e2570a7e681c94479a673d0"><code>9270c48</code></a> fix(openai): preserve reasoning_content in ChatOpenAICompletions (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10551">#10551</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f54805305787fa383c3ce1e287daafdb5464a98b"><code>f548053</code></a> fix(langchain): bump langgraph dep (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10555">#10555</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/11a295fdadec3809f40c10492e3fd474e832c468"><code>11a295f</code></a> fix(langchain): add support for dynamic structured output (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10554">#10554</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a> fix(langchain): accept cross-version runnable models in createAgent (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10552">#10552</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/cd86fea8de2130d0df60805baada81958d47c747"><code>cd86fea</code></a> fix: implement tool choice required on anthropic (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10519">#10519</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/b57760c55a721ed65a456bbad11172e35adee177"><code>b57760c</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10516">#10516</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6e2d29e28a8f2a84f6fbbe5755d6b4fe2d5d4fd1"><code>6e2d29e</code></a> tests(<code>@​langchain/google</code>): Lyria 3 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10522">#10522</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/68e0a19238be592514b6c01243c41aefaa6a7668"><code>68e0a19</code></a> fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10545">#10545</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/langchain@1.2.36...langchain@1.2.39">compare view</a></li> </ul> </details> <br /> Updates `@langchain/anthropic` from 1.3.23 to 1.3.26 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langchainjs/releases"><code>@​langchain/anthropic</code>'s releases</a>.</em></p> <blockquote> <h2><code>@​langchain/anthropic</code><a href="https://github.com/1"><code>@​1</code></a>.3.26</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10519">#10519</a> <a href="https://github.com/langchain-ai/langchainjs/commit/cd86fea8de2130d0df60805baada81958d47c747"><code>cd86fea</code></a> Thanks <a href="https://github.com/baptistejamin"><code>@​baptistejamin</code></a>! - fix: implement tool choice required on anthropic</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a>]:</p> <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.38</li> </ul> </li> </ul> <h2><code>@​langchain/anthropic</code><a href="https://github.com/1"><code>@​1</code></a>.3.25</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10467">#10467</a> <a href="https://github.com/langchain-ai/langchainjs/commit/da85f31688e708340a711fd43cf293b5cb69c133"><code>da85f31</code></a> Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! - fix: add default max tokens for sonnet</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/bfb7944a105470eee98fe4a0eef91e586600e1de"><code>bfb7944</code></a>]:</p> <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.34</li> </ul> </li> </ul> <h2><code>@​langchain/anthropic</code><a href="https://github.com/1"><code>@​1</code></a>.3.24</h2> <h3>Patch Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10420">#10420</a> <a href="https://github.com/langchain-ai/langchainjs/commit/08657f21b330ee05b86a8abd557aef3939f5581b"><code>08657f2</code></a> Thanks <a href="https://github.com/pawel-twardziak"><code>@​pawel-twardziak</code></a>! - Fix temperature/topK/topP handling: guard all three so undefined values are not set on the request object, and fix broken topK/topP validation when thinking is enabled.</li> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/6db417b03ecb5e2ace413389d982294e0ac88433"><code>6db417b</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/d69dfcca97503cf1c0b7e70ccf5fb7d507c60982"><code>d69dfcc</code></a>]: <ul> <li><code>@​langchain/core</code><a href="https://github.com/1"><code>@​1</code></a>.1.33</li> </ul> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6b914bceb4acd4664b12091770a2ddcbf5d8457e"><code>6b914bc</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10553">#10553</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/7ed93b8b8a6e9eb0da3e103d74087c692fee2773"><code>7ed93b8</code></a> fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10543">#10543</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/9270c48d7a95db6e7e2570a7e681c94479a673d0"><code>9270c48</code></a> fix(openai): preserve reasoning_content in ChatOpenAICompletions (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10551">#10551</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f54805305787fa383c3ce1e287daafdb5464a98b"><code>f548053</code></a> fix(langchain): bump langgraph dep (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10555">#10555</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/11a295fdadec3809f40c10492e3fd474e832c468"><code>11a295f</code></a> fix(langchain): add support for dynamic structured output (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10554">#10554</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/589ab9be391a5d6c104f34877fc1b3e2a32fa449"><code>589ab9b</code></a> fix(langchain): accept cross-version runnable models in createAgent (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10552">#10552</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/cd86fea8de2130d0df60805baada81958d47c747"><code>cd86fea</code></a> fix: implement tool choice required on anthropic (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10519">#10519</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/b57760c55a721ed65a456bbad11172e35adee177"><code>b57760c</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10516">#10516</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6e2d29e28a8f2a84f6fbbe5755d6b4fe2d5d4fd1"><code>6e2d29e</code></a> tests(<code>@​langchain/google</code>): Lyria 3 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10522">#10522</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/68e0a19238be592514b6c01243c41aefaa6a7668"><code>68e0a19</code></a> fix(langchain): revert zod import in utils.ts to fix v3/v4 interop (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10545">#10545</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/anthropic@1.3.23...@langchain/anthropic@1.3.26">compare view</a></li> </ul> </details> <br /> Updates `modal` from 0.7.1 to 0.7.3 <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/modal-labs/modal-client/blob/main/CHANGELOG_GO_JS.md">modal's changelog</a>.</em></p> <blockquote> <h2>js/v0.7.3, go/v0.7.3</h2> <ul> <li>Migrated SDKs from <code>github.com/modal-labs/libmodal</code> to <code>github.com/modal-labs/modal-client</code>.</li> </ul> <h2>modal-js/v0.7.2, modal-go/v0.7.2</h2> <ul> <li>Updated <code>Sandbox</code> methods to wait for newly created sandboxes to be ready and not error immediately when it's not avaliable yet.</li> <li>Fixed a bug in <code>modal-js</code> so that canceling <code>sandbox.stdout</code> or <code>sandbox.stderr</code> cleans up background resources.</li> <li>Updated <code>Sandbox</code> (JS) to raise a better error when the sandbox was terminated.</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/modal-labs/modal-client/commits/go/v0.7.3">compare view</a></li> </ul> </details> <details> <summary>Attestation changes</summary> <p>This version has no provenance attestation, while the previous version (0.7.1) was attested. Review the <a href="https://www.npmjs.com/package/modal?activeTab=versions">package versions</a> before updating.</p> </details> <br /> Updates `langsmith` from 0.5.7 to 0.5.16 <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> <details> <summary>Install script changes</summary> <p>This version modifies <code>prepublish</code> script that runs during installation. Review the package contents before updating.</p> </details> <br /> 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 <dependency name> major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself) - `@dependabot ignore <dependency name> minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself) - `@dependabot ignore <dependency name>` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself) - `@dependabot unignore <dependency name>` will remove all of the ignore conditions of the specified dependency - `@dependabot unignore <dependency name> <ignore condition>` will remove the ignore condition of the specified dependency and ignore conditions </details> --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 17:23:06 -04:00
yindo closed this issue 2026-06-05 17:23:06 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/deepagentsjs#442