mirror of
https://github.com/langchain-ai/langgraphjs.git
synced 2026-07-21 16:45:24 -04:00
@langchain/react@1.0.25
8 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Christian Bromann
|
5d279df5d5 |
chore(deps): bump langchain (#2564)
Bump langchainjs to latest release. --------- Signed-off-by: Christian Bromann <git@bromann.dev> Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
b1e856d987 |
feat(sdk): apply state update and goto alongside interrupt resume (#2557)
## Summary
- Add `update` and `goto` options to `respond()` across the SDK so
resolving an interrupt can apply a state update and/or directed jump in
the **same superstep** — mapped to LangGraph's `Command(resume, update,
goto)`. The canonical use case is a HITL flow that pushes the interrupt
card into state at the moment it answers, committed in one checkpoint
with no flicker.
- `@langchain/langgraph-sdk`: new `update`/`goto` fields on
`StreamRespondAllOptions`, forwarded by
`StreamController.respond`/`respondAll`; `@langchain/core` `BaseMessage`
instances under the `messagesKey` are serialized to dicts before
transport, exactly like `submit()`.
- `@langchain/langgraph-api`: forward `update`/`goto` from
`input.respond` into the run `Command` in both the protocol service and
the embedded server.
- `@langchain/react`, `@langchain/vue`, `@langchain/svelte`,
`@langchain/angular`: document the new `respond({ update, goto })`
capability (incl. `BaseMessage` examples).
- Fix: the protocol-v2 state normalizer stripped `response_metadata`,
which HITL cards ride on (`AIMessage.response_metadata`); non-empty
`response_metadata` is now preserved.
- Add React browser tests (`interrupt_card_graph` fixture via
`createAgent`) covering the approve and reject paths: the FE-pushed card
lands in committed state exactly once and persists through a slow tool
execution.
|
||
|
dependabot[bot]
|
a4919b667e |
chore(deps): bump the langchain group across 1 directory with 8 updates (#2476)
Bumps the langchain group with 8 updates in the / directory: | Package | From | To | | --- | --- | --- | | [@langchain/anthropic](https://github.com/langchain-ai/langchainjs) | `1.3.28` | `1.4.0` | | [@langchain/core](https://github.com/langchain-ai/langchainjs) | `1.1.44` | `1.1.48` | | [langchain](https://github.com/langchain-ai/langchainjs) | `1.4.0-dev-1777615538778` | `1.4.4` | | [@langchain/openai](https://github.com/langchain-ai/langchainjs) | `1.4.5` | `1.4.7` | | [@langchain/groq](https://github.com/langchain-ai/langchainjs) | `1.2.0` | `1.2.1` | | [@langchain/mistralai](https://github.com/langchain-ai/langchainjs) | `1.0.8` | `1.1.0` | | [@langchain/classic](https://github.com/langchain-ai/langchainjs) | `1.0.32` | `1.0.34` | | [langsmith](https://github.com/langchain-ai/langsmith-sdk) | `0.6.0` | `0.7.4` | Updates `@langchain/anthropic` from 1.3.28 to 1.4.0 <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>.4.0</h2> <h3>Minor Changes</h3> <ul> <li><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10777">#10777</a> <a href="https://github.com/langchain-ai/langchainjs/commit/0cfcfc66897d8fafeb7e7ed90b7299eace9a7c37"><code>0cfcfc6</code></a> Thanks <a href="https://github.com/jonaslalin"><code>@jonaslalin</code></a>! - feat(anthropic): support strict tool calling for custom tools</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits/@langchain/anthropic@1.4.0">compare view</a></li> </ul> </details> <br /> Updates `@langchain/core` from 1.1.44 to 1.1.48 <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>.1.48</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10832">#10832</a> <a href="https://github.com/langchain-ai/langchainjs/commit/1b24369a970ad6f56f1f428027f48601f87e62eb"><code>1b24369</code></a> Thanks <a href="https://github.com/info-arnav"><code>@info-arnav</code></a>! - fix(core, openrouter): make CJS default re-exports callable</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10666">#10666</a> <a href="https://github.com/langchain-ai/langchainjs/commit/2bb55b053f49f89e81e3252a7af08e86d71ddd95"><code>2bb55b0</code></a> Thanks <a href="https://github.com/hnustwjj"><code>@hnustwjj</code></a>! - feat(openrouter): surface reasoning content as v1 standard content blocks</p> <p><code>convertOpenRouterResponseToBaseMessage</code> and <code>convertOpenRouterDeltaToBaseMessageChunk</code> now copy OpenRouter's <code>reasoning</code> (flat string) and <code>reasoning_details</code> (structured array) fields onto <code>additional_kwargs.reasoning_content</code> / <code>additional_kwargs.reasoning_details</code>. A new <code>ChatOpenRouterTranslator</code> is registered in <code>@langchain/core</code> under the <code>"openrouter"</code> provider key so <code>AIMessage.contentBlocks</code> emits standard <code>{type: "reasoning"}</code> blocks alongside text and tool calls.</p> <p>Previously, reasoning text returned by reasoning-capable models routed through OpenRouter (DeepSeek R1, Minimax M2, Claude extended thinking, o-series, etc.) was silently dropped: only the <code>reasoning_tokens</code> count was preserved via <code>usage_metadata</code>. Consumers using standard content blocks (including the frontend agent UI patterns shown in the docs) could not display the model's chain of thought.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10918">#10918</a> <a href="https://github.com/langchain-ai/langchainjs/commit/3999fab55870c6eea22d6d90c08aa472f9b2fac3"><code>3999fab</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(openai): stream custom tool calls through Responses API chunks</p> </li> </ul> <h2><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.47</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10906">#10906</a> <a href="https://github.com/langchain-ai/langchainjs/commit/f61b3450f275831e47e69c08899b4a2b67b4bdb3"><code>f61b345</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - feat(core): add uuid v6 utility support</p> <p>Add <code>v6</code> UUID generation support to <code>@langchain/core/utils/uuid</code> by vendoring the upstream uuidjs <code>v6</code> implementation and its <code>v1ToV6</code> helper, exporting <code>v6</code> from the UUID utils index, and adding tests for deterministic generation, buffer/offset behavior, validation/versioning, and ordering.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10872">#10872</a> <a href="https://github.com/langchain-ai/langchainjs/commit/a64007997a4940f51bba3c1c83dae89d1ccfb692"><code>a640079</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - chore(deps): remove redundant <code>@types/uuid</code> declarations</p> <p>Remove <code>@types/uuid</code> from package manifests that rely on <code>@langchain/core/utils/uuid</code> or do not require uuid type stubs directly, and refresh the lockfile entries accordingly.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10792">#10792</a> <a href="https://github.com/langchain-ai/langchainjs/commit/3682268cd1844b2573b01f07bee367e21cb7bdc7"><code>3682268</code></a> Thanks <a href="https://github.com/Genmin"><code>@Genmin</code></a>! - fix(core): apply v1 message casting after implicit streaming aggregation</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10901">#10901</a> <a href="https://github.com/langchain-ai/langchainjs/commit/f26fc4a6f461d6d0f86d59bd00197ad510432c4a"><code>f26fc4a</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(testing): share fakeModel invocation state across bindTools instances</p> </li> </ul> <h2><code>@langchain/core</code><a href="https://github.com/1"><code>@1</code></a>.1.46</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10847">#10847</a> <a href="https://github.com/langchain-ai/langchainjs/commit/1659e7d36e31e315c890fa98f43db887f7a2d52b"><code>1659e7d</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - chore(core): reduce transitive dependency exposure and tighten release hygiene</p> <p>Remove direct runtime dependencies on <code>ansi-styles</code>, <code>camelcase</code>, and <code>decamelize</code> by inlining equivalent logic in core internals, and enable npm provenance in the release workflow.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10790">#10790</a> <a href="https://github.com/langchain-ai/langchainjs/commit/ef78bc6a21f9a8808ba95c98db2023f0a6b51bcc"><code>ef78bc6</code></a> Thanks <a href="https://github.com/Genmin"><code>@Genmin</code></a>! - fix(core): keep different content block types separate when merging chunks</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits/@langchain/core@1.1.48">compare view</a></li> </ul> </details> <br /> Updates `langchain` from 1.4.0-dev-1777615538778 to 1.4.4 <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@1.4.2</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10900">#10900</a> <a href="https://github.com/langchain-ai/langchainjs/commit/6bbddca1f8f7f280583fd839bb40c00bf19a0d51"><code>6bbddca</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(langchain): unwrap tool message outputs in agent streams</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10706">#10706</a> <a href="https://github.com/langchain-ai/langchainjs/commit/4ecb6606feae3156a07de67e39e2027f857c476e"><code>4ecb660</code></a> Thanks <a href="https://github.com/JadenKim-dev"><code>@JadenKim-dev</code></a>! - fix(langchain): set name on todoListMiddleware ToolMessages</p> </li> </ul> <h2>langchain@1.4.1</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10879">#10879</a> <a href="https://github.com/langchain-ai/langchainjs/commit/eb480cb6df8e0fa792826155bfa00a6db4536444"><code>eb480cb</code></a> Thanks <a href="https://github.com/vignesh-gep"><code>@vignesh-gep</code></a>! - fix(langchain/createAgent): throw on terminal <code>providerStrategy</code> parse failure instead of silently resolving with <code>structuredResponse: undefined</code></p> <p>When <code>createAgent</code> was configured with <code>responseFormat</code> resolving to a <code>providerStrategy</code> (either passed explicitly or auto-promoted from a bare Zod / JSON schema for models whose profile reports <code>structuredOutput: true</code>), and the model produced a terminal response (no <code>tool_calls</code>) whose text could not be JSON-parsed or did not satisfy the schema, the agent silently exited with no <code>structuredResponse</code>, surfacing later as <code>TypeError: Cannot read properties of undefined</code>. The agent now throws a <code>StructuredOutputParsingError</code> in that case while still allowing the agent loop to continue when tool calls are present. Closes <a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10878">#10878</a>.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10872">#10872</a> <a href="https://github.com/langchain-ai/langchainjs/commit/a64007997a4940f51bba3c1c83dae89d1ccfb692"><code>a640079</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - chore(deps): remove redundant <code>@types/uuid</code> declarations</p> <p>Remove <code>@types/uuid</code> from package manifests that rely on <code>@langchain/core/utils/uuid</code> or do not require uuid type stubs directly, and refresh the lockfile entries accordingly.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10160">#10160</a> <a href="https://github.com/langchain-ai/langchainjs/commit/bba900c7c8781c7efec856d5d3e539a93f14e797"><code>bba900c</code></a> Thanks <a href="https://github.com/JadenKim-dev"><code>@JadenKim-dev</code></a>! - fix(langchain): prevent llmToolSelectorMiddleware from leaking into message stream</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits/@langchain/openai@1.4.4">compare view</a></li> </ul> </details> <br /> Updates `@langchain/openai` from 1.4.5 to 1.4.7 <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>.4.7</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10918">#10918</a> <a href="https://github.com/langchain-ai/langchainjs/commit/3999fab55870c6eea22d6d90c08aa472f9b2fac3"><code>3999fab</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(openai): stream custom tool calls through Responses API chunks</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10791">#10791</a> <a href="https://github.com/langchain-ai/langchainjs/commit/fce9ab418901323618fdfaaa9fc350fa1c0d50e0"><code>fce9ab4</code></a> Thanks <a href="https://github.com/Genmin"><code>@Genmin</code></a>! - fix(openai): preserve top-level Responses API ids on AI messages</p> </li> </ul> <h2><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.6</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10902">#10902</a> <a href="https://github.com/langchain-ai/langchainjs/commit/229a7ad67b9a7ebd8df3ca451e0b8195bea0190e"><code>229a7ad</code></a> Thanks <a href="https://github.com/christian-bromann"><code>@christian-bromann</code></a>! - fix(openai): preserve v1 assistant tool calls</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10895">#10895</a> <a href="https://github.com/langchain-ai/langchainjs/commit/36fb0ef1dc76c096dcfa0c777e10c9f9365a5240"><code>36fb0ef</code></a> Thanks <a href="https://github.com/BertBR"><code>@BertBR</code></a>! - fix(openai): guard bare <code>JSON.parse</code> in Responses API converter against trailing non-whitespace characters</p> <p><code>convertResponsesDeltaToChatGenerationChunk</code> previously called <code>JSON.parse(msg.text)</code> directly when <code>response.text.format.type === "json_schema"</code>. Some models (observed with <code>gpt-5-mini</code> on <code>service_tier: "auto"</code>) intermittently emit trailing non-whitespace characters (extra tokens, control characters) after a valid JSON object, causing a <code>SyntaxError</code> that propagates as an unhandled exception and kills the entire streaming response mid-flight. The parse is now wrapped in a <code>try</code>/<code>catch</code>: on failure, <code>additional_kwargs.parsed</code> is left undefined, the stream completes normally, and the existing <code>withStructuredOutput</code> pipeline handles the typed failure — <code>includeRaw: true</code> returns <code>{ raw, parsed: null }</code> via its <code>withFallbacks</code> wrapper, <code>includeRaw: false</code> throws a typed <code>OutputParserException</code> that the caller can catch and retry. Closes <a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10894">#10894</a>.</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/langchain-ai/langchainjs/commits/@langchain/openai@1.4.7">compare view</a></li> </ul> </details> <br /> Updates `@langchain/groq` from 1.2.0 to 1.2.1 <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>.2.1</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10872">#10872</a> <a href="https://github.com/langchain-ai/langchainjs/commit/a64007997a4940f51bba3c1c83dae89d1ccfb692"><code>a640079</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - chore(deps): remove redundant <code>@types/uuid</code> declarations</p> <p>Remove <code>@types/uuid</code> from package manifests that rely on <code>@langchain/core/utils/uuid</code> or do not require uuid type stubs directly, and refresh the lockfile entries accordingly.</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/1b19e4f84d747b481879363b4884c20eb1c0f1a4"><code>1b19e4f</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10899">#10899</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/426e3aba21016d9ee070c3d130f74ae0047c9ce5"><code>426e3ab</code></a> chore: fix uuid changeset (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10916">#10916</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/245c98216ce4a6c4340954711a7ad60203283424"><code>245c982</code></a> chore(deps): bump fast-xml-builder from 1.1.5 to 1.2.0 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10914">#10914</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/126dac5a7a2fac5978448185893038ac8ea6d994"><code>126dac5</code></a> chore(deps): bump brace-expansion from 5.0.5 to 5.0.6 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10912">#10912</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/1abe24becdddce94c5bd2acfaf920b60a683f22b"><code>1abe24b</code></a> chore(deps): bump fast-uri from 3.1.0 to 3.1.2 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10913">#10913</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/229a7ad67b9a7ebd8df3ca451e0b8195bea0190e"><code>229a7ad</code></a> fix(openai): preserve v1 assistant tool calls (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10902">#10902</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f26fc4a6f461d6d0f86d59bd00197ad510432c4a"><code>f26fc4a</code></a> fix(core): share fakeModel invocation state across bindTools instances (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10901">#10901</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/a0cd7477e59677c8d15e0e70b374afa0a2410582"><code>a0cd747</code></a> chore(deps): bump fast-xml-builder from 1.1.5 to 1.1.9 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10910">#10910</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/b208e625865fc7487876b652f479dbf854263e68"><code>b208e62</code></a> chore(deps): bump ip-address from 10.1.0 to 10.2.0 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10909">#10909</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f7e50fb8b98bd9969c0f5cf0967a06df15453453"><code>f7e50fb</code></a> feat(google): Service tier and custom headers (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10704">#10704</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/groq@1.2.0...@langchain/groq@1.2.1">compare view</a></li> </ul> </details> <br /> Updates `@langchain/mistralai` from 1.0.8 to 1.1.0 <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/mistralai</code><a href="https://github.com/1"><code>@1</code></a>.1.0</h2> <h3>Minor Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10873">#10873</a> <a href="https://github.com/langchain-ai/langchainjs/commit/a74d574f7f086bea2f5c7a852e869f7d24be2f55"><code>a74d574</code></a> Thanks <a href="https://github.com/baptistejamin"><code>@baptistejamin</code></a>! - chore(mistralai): upgrade to <code>@mistralai/mistralai</code> v2</p> <p>Also populates <code>response_metadata.model</code> on chat completions (was missing before).</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/caad0914f068477293009dbf27a220fa96bdc4b8"><code>caad091</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10919">#10919</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/f4a6149e3e754203f5886dd8c2bccaa7a6fd4f81"><code>f4a6149</code></a> chore(deps): bump fast-uri from 3.1.0 to 3.1.2 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10926">#10926</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/7b12f6dfa537932073f96b561d7c851b30d69132"><code>7b12f6d</code></a> chore(deps): bump protobufjs from 7.5.6 to 7.6.0 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10930">#10930</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/5c6c5fef0cb392e782675ca5926e291a4295a653"><code>5c6c5fe</code></a> chore(deps): bump ws from 5.2.4 to 8.20.0 (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10915">#10915</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/a8652ceeb5e36434565c96fc1a6bd9a4a36304cc"><code>a8652ce</code></a> docs: fix typos, add Ollama setup, update outdated references (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10922">#10922</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/2bb55b053f49f89e81e3252a7af08e86d71ddd95"><code>2bb55b0</code></a> feat(openrouter): surface reasoning as v1 standard content blocks (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10666">#10666</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/4ecb6606feae3156a07de67e39e2027f857c476e"><code>4ecb660</code></a> fix(langchain): set name on todoListMiddleware ToolMessages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10706">#10706</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/20f27dff08a4bd5a1a16c1c71a88405c9df82914"><code>20f27df</code></a> fix(ibm): handle API errors in streaming responses (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10721">#10721</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/45668734c3205e631cdd33ac071bbf733f4558c7"><code>4566873</code></a> feat(ibm): add integration test to IBM implementation (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10732">#10732</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/6e4337fec1a7707c1a1c709a7b6aa0c5efb7b11d"><code>6e4337f</code></a> fix(aws): add claude-haiku-4 to supportedToolChoiceValuesForModel (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/10743">#10743</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langchainjs/compare/@langchain/classic@1.0.8...@langchain/mistralai@1.1.0">compare view</a></li> </ul> </details> <br /> Updates `@langchain/classic` from 1.0.32 to 1.0.34 <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>.0.34</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/3999fab55870c6eea22d6d90c08aa472f9b2fac3"><code>3999fab</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/fce9ab418901323618fdfaaa9fc350fa1c0d50e0"><code>fce9ab4</code></a>]: <ul> <li><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.7</li> </ul> </li> </ul> <h2><code>@langchain/classic</code><a href="https://github.com/1"><code>@1</code></a>.0.33</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/10872">#10872</a> <a href="https://github.com/langchain-ai/langchainjs/commit/a64007997a4940f51bba3c1c83dae89d1ccfb692"><code>a640079</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - chore(deps): remove redundant <code>@types/uuid</code> declarations</p> <p>Remove <code>@types/uuid</code> from package manifests that rely on <code>@langchain/core/utils/uuid</code> or do not require uuid type stubs directly, and refresh the lockfile entries accordingly.</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/langchain-ai/langchainjs/commit/229a7ad67b9a7ebd8df3ca451e0b8195bea0190e"><code>229a7ad</code></a>, <a href="https://github.com/langchain-ai/langchainjs/commit/36fb0ef1dc76c096dcfa0c777e10c9f9365a5240"><code>36fb0ef</code></a>]:</p> <ul> <li><code>@langchain/openai</code><a href="https://github.com/1"><code>@1</code></a>.4.6</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/@langchain/classic@1.0.34">compare view</a></li> </ul> </details> <br /> Updates `langsmith` from 0.6.0 to 0.7.4 <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>v0.7.4</h2> <h2>What's Changed</h2> <ul> <li>fix(google-adk): add wrapt dependency by <a href="https://github.com/QuentinBrosse"><code>@QuentinBrosse</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2436">langchain-ai/langsmith-sdk#2436</a></li> <li>chore: lock dependencies by <a href="https://github.com/QuentinBrosse"><code>@QuentinBrosse</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2439">langchain-ai/langsmith-sdk#2439</a></li> <li>release(py): 0.7.4 by <a href="https://github.com/QuentinBrosse"><code>@QuentinBrosse</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2441">langchain-ai/langsmith-sdk#2441</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.3...v0.7.4">https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.3...v0.7.4</a></p> <h2>v0.7.3</h2> <h2>What's Changed</h2> <ul> <li>fix: propagate tracingEnabled to nested traceables by <a href="https://github.com/hntrl"><code>@hntrl</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2427">langchain-ai/langsmith-sdk#2427</a></li> <li>chore(python): openai agents: delay span start for spans without inputs on start event 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/2424">langchain-ai/langsmith-sdk#2424</a></li> <li>release(py): 0.7.3 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/2428">langchain-ai/langsmith-sdk#2428</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.2...v0.7.3">https://github.com/langchain-ai/langsmith-sdk/compare/v0.7.2...v0.7.3</a></p> <h2>v0.7.2</h2> <h2>What's Changed</h2> <ul> <li>release(js): 0.5.1 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2389">langchain-ai/langsmith-sdk#2389</a></li> <li>fix(js): Remove <a href="https://github.com/internal"><code>@internal</code></a> by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2391">langchain-ai/langsmith-sdk#2391</a></li> <li>release(js): 0.5.2 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2392">langchain-ai/langsmith-sdk#2392</a></li> <li>chore(deps-dev): bump openai from 5.8.2 to 6.18.0 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2378">langchain-ai/langsmith-sdk#2378</a></li> <li>chore(deps-dev): bump cross-env from 7.0.3 to 10.1.0 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2379">langchain-ai/langsmith-sdk#2379</a></li> <li>chore(deps-dev): bump the js-minor-and-patch group in /js with 4 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2376">langchain-ai/langsmith-sdk#2376</a></li> <li>chore(deps-dev): bump node-fetch from 2.7.0 to 3.3.2 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2380">langchain-ai/langsmith-sdk#2380</a></li> <li>Google ADK LangSmith tracing enhancements by <a href="https://github.com/j-broekhuizen"><code>@j-broekhuizen</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2394">langchain-ai/langsmith-sdk#2394</a></li> <li>chore: update dependabot.yml to comply with posture checks by <a href="https://github.com/jkennedyvz"><code>@jkennedyvz</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2393">langchain-ai/langsmith-sdk#2393</a></li> <li>chore(deps): bump cryptography from 46.0.3 to 46.0.5 in /python in the uv group across 1 directory by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2397">langchain-ai/langsmith-sdk#2397</a></li> <li>chore(deps-dev): bump the js-minor-and-patch group in /js with 6 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2398">langchain-ai/langsmith-sdk#2398</a></li> <li>chore(deps-dev): bump eslint-config-prettier from 8.10.0 to 10.1.8 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2399">langchain-ai/langsmith-sdk#2399</a></li> <li>chore(deps): bump packaging from 25.0 to 26.0 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2403">langchain-ai/langsmith-sdk#2403</a></li> <li>chore(deps-dev): bump pytest from 8.4.2 to 9.0.2 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2405">langchain-ai/langsmith-sdk#2405</a></li> <li>chore(deps): bump the py-minor-and-patch group across 1 directory with 20 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2406">langchain-ai/langsmith-sdk#2406</a></li> <li>fix(js): Log Vitest/Jest outputs even if test throws an error by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2408">langchain-ai/langsmith-sdk#2408</a></li> <li>fix(js): Remove async by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2409">langchain-ai/langsmith-sdk#2409</a></li> <li>release(js): 0.5.3 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2410">langchain-ai/langsmith-sdk#2410</a></li> <li>fix: ignoring p-queue dep by <a href="https://github.com/jkennedyvz"><code>@jkennedyvz</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2414">langchain-ai/langsmith-sdk#2414</a></li> <li>feat(js): add feedback config CRUD and annotation queue rubric items (closes LSPE-67) by <a href="https://github.com/bentanny"><code>@bentanny</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2420">langchain-ai/langsmith-sdk#2420</a></li> <li>fix(js): Add on_start handler for traceable, use in evaluate by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2421">langchain-ai/langsmith-sdk#2421</a></li> <li>release(js): 0.5.4 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2422">langchain-ai/langsmith-sdk#2422</a></li> <li>feat(python): add feedback config CRUD and annotation queue rubric items (closes LSPE-67) by <a href="https://github.com/bentanny"><code>@bentanny</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2419">langchain-ai/langsmith-sdk#2419</a></li> <li>feat(python): add exceptions_to_handle to <a href="https://github.com/traceable"><code>@traceable</code></a> by <a href="https://github.com/QuentinBrosse"><code>@QuentinBrosse</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2423">langchain-ai/langsmith-sdk#2423</a></li> <li>release(py): 0.7.2 by <a href="https://github.com/jacoblee93"><code>@jacoblee93</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2426">langchain-ai/langsmith-sdk#2426</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/j-broekhuizen"><code>@j-broekhuizen</code></a> made their first contribution in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2394">langchain-ai/langsmith-sdk#2394</a></li> <li><a href="https://github.com/bentanny"><code>@bentanny</code></a> made their first contribution in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2420">langchain-ai/langsmith-sdk#2420</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/1132e6ce6391d08158a93acb5c96b90521ac3230"><code>1132e6c</code></a> release(py): 0.7.4 (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2441">#2441</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/8c7cc783806e4a6d71300982d58ecb3c9bc658cd"><code>8c7cc78</code></a> chore: lock dependencies (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2439">#2439</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/62c256ea56fdee0bc539275c749a427e510ded8f"><code>62c256e</code></a> fix(google-adk): add wrapt dependency (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2436">#2436</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/e32d4c18a681553f47c93350f03dc0a0f0cc4890"><code>e32d4c1</code></a> release(py): 0.7.3 (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2428">#2428</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/1c51bf881dafaeb01432db629de7cafaabca79dc"><code>1c51bf8</code></a> chore(python): openai agents: delay span start for spans without inputs on st...</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/a41bf22dadaea489a156dc06a9d0fbf1a977ff6d"><code>a41bf22</code></a> fix: propagate tracingEnabled to nested traceables (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2427">#2427</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/3a6e9dac4bf3a940f7ee47e420cc1422f9f4a4b4"><code>3a6e9da</code></a> release(py): 0.7.2 (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2426">#2426</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/f665e865e7ab7a0ba1de447f2a1cf14c719af00a"><code>f665e86</code></a> feat(python): add exceptions_to_handle to <a href="https://github.com/traceable"><code>@traceable</code></a> (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2423">#2423</a>)</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/565c4a2c5769e698ecffbf7f43131ff9cc467f8d"><code>565c4a2</code></a> feat(python): add feedback config CRUD and annotation queue rubric items (clo...</li> <li><a href="https://github.com/langchain-ai/langsmith-sdk/commit/e1b1fe13c382371ebe4cffa1b95eba3bf74e2f37"><code>e1b1fe1</code></a> release(js): 0.5.4 (<a href="https://redirect.github.com/langchain-ai/langsmith-sdk/issues/2422">#2422</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.6.0...v0.7.4">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> Co-authored-by: John Kennedy <jkennedyvz@users.noreply.github.com> |
||
|
Christian Bromann
|
2c14b12a80 |
fix(sdk): add back respondAll and respond config/metadata (#2448)
## Summary
- Add `respondAll(responsesById, options)` to the stream controller and
the React/Angular/Svelte/Vue wrappers, resuming multiple interrupts
pending at the same checkpoint in a single `Command({ resume })`. This
is required for runs that pause on several interrupts at once (e.g.
parallel tool-authorization prompts), which sequential `respond()` calls
cannot service.
- Change `respond()` to take an options object (`{ interruptId?,
namespace?, config?, metadata? }`), folding run-level
`config`/`metadata` onto the resumed run so it applies the same
configurable values and metadata a fresh `submit()` would.
- Extend `ThreadStream.respondInput()` to accept a `responses` batch
(mutually exclusive with the single `interrupt_id`/`response`) and clear
all responded interrupts from local state.
- Update the protocol-v2 reference servers (`embed/protocol.mts`,
`protocol/service.mts`) to read the `responses` batch plus
`config`/`metadata` leniently and fold them onto the run servicing
`input.respond`.
- Update docs (interrupts/use-stream) across all framework packages and
add controller tests for batched resume.
|
||
|
Christian Bromann
|
29d2bde235 |
fix(sdk): cancel runs on stop by default and add disconnect() (#2438)
## Summary
- `stream.stop()` now cancels the active run server-side by default
(`client.runs.cancel`) before disconnecting the client transport.
- Added `stream.disconnect()` as an alias for `stop({ cancel: false })`
for join/rejoin UIs.
- Introduced `StreamStopOptions` (`{ cancel?: boolean }`) on
`StreamController` and all v1 framework bindings (React, Vue, Svelte,
Angular).
- Updated `use-stream.md` and added controller unit tests for
cancel-on-stop and no-cancel-on-disconnect.
|
||
|
Christian Bromann
|
3529e3831a |
fix(sdk): align AssembledToolCall typing with pre-v1 expectations (#2421)
## Summary - Split tool-call handles by consumer: - **Client SDK** (`ThreadStream.toolCalls`, subgraph/subagent projections): `ClientAssembledToolCall` with a promise-only `output` (resolves on success, rejects on error). Still exported as `AssembledToolCall` from `@langchain/langgraph-sdk/client` for script usage. - **Framework SDKs** (`stream.toolCalls`, `useToolCalls`, `injectToolCalls`): `AssembledToolCall` with plain reactive fields — `output: T | null`, `status`, and `error` — updated in place as events arrive so React/Vue/Svelte/Angular can render from snapshots without `await`, effects, or Suspense around promises. - Add generic `AssembledToolCall<TName, TInput, TOutput>` plus `id`/`args` aliases; point `InferToolCalls` at assembled streaming handles and add `AssembledToolCallFromTool` (exported as `ToolCallFromTool` from `@langchain/react`, `@langchain/vue`, `@langchain/svelte`, and `@langchain/angular`). - Rework `ToolCallAssembler` around a mutable internal handle and `toClientAssembledToolCall()` for client projections; framework stores the reactive handle directly. - Remove redundant `InferAssembledToolCalls` and deprecated `StateOf`; wire typed `toolCalls` / selector generics across all four framework packages. - Expand and align `createAgent`, `createDeepAgent`, and `langgraph` type tests across React, Vue, Svelte, and Angular; update examples, protocol-v2 integration tests, and Vue migration docs. |
||
|
Christian Bromann
|
2bb66bf816 |
fix(sdk): update endpoints (#2366)
Aligning with latest Python changes updating endpoints to be:
POST /threads/{thread_id}/stream/events — SSE event stream
POST /threads/{thread_id}/commands — JSON command
WS /threads/{thread_id}/stream/events
for new streaming features.
|
||
|
Christian Bromann
|
085a07f569 |
feat(core): event based streaming (#2314)
All stream v2 changes consolidated. --------- Co-authored-by: Hunter Lovell <hunter@hntrl.io> |