chore(deps): bump the examples-npm group across 1 directory with 5 updates (#2412)

Bumps the examples-npm group with 5 updates in the /examples directory:

| Package | From | To |
| --- | --- | --- |
|
[@ai-sdk/openai](https://github.com/vercel/ai/tree/HEAD/packages/openai)
| `4.0.65` | `4.0.66` |
| [@langchain/core](https://github.com/langchain-ai/langchainjs) |
`1.2.10` | `1.2.11` |
|
[@langchain/langgraph](https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core)
| `1.4.14` | `1.4.15` |
| [@langchain/openai](https://github.com/langchain-ai/langchainjs) |
`1.5.12` | `1.5.13` |
| [ai](https://github.com/vercel/ai/tree/HEAD/packages/ai) | `7.0.97` |
`7.0.99` |


Updates `@ai-sdk/openai` from 4.0.65 to 4.0.66
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/vercel/ai/blob/main/packages/openai/CHANGELOG.md">@​ai-sdk/openai's
changelog</a>.</em></p>
<blockquote>
<h2>4.0.66</h2>
<h3>Patch Changes</h3>
<ul>
<li>5ec21a6: fix: reject unsupported batch request types</li>
<li>7469a3b: feat: support image generation requests in batches</li>
<li>0de8886: fix(openai): allow providers to disable web search source
includes</li>
<li>d5e3024: fix(openai): remove propertyNames from JSON Schema</li>
<li>Updated dependencies [5ec21a6]</li>
<li>Updated dependencies [7469a3b]</li>
<li>Updated dependencies [813bb36]</li>
<li>Updated dependencies [c43e4b7]
<ul>
<li><code>@​ai-sdk/provider</code><a
href="https://github.com/4"><code>@​4</code></a>.0.14</li>
<li><code>@​ai-sdk/provider-utils</code><a
href="https://github.com/5"><code>@​5</code></a>.0.40</li>
</ul>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/vercel/ai/commit/9ed46d2da5df1394079c66d422bc553fd0c34376"><code>9ed46d2</code></a>
Version Packages (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20569">#20569</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/d5e30246540adcc334aab700e9262c038c4cce13"><code>d5e3024</code></a>
fix(openai): remove propertyNames from JSON Schema (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20621">#20621</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/7469a3bc5daf0fd8c535c903f883d730a39de191"><code>7469a3b</code></a>
feat: support image generation requests in batches (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20594">#20594</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/0de88864f70b6f02cf89d1625aeb3fece0648a7f"><code>0de8886</code></a>
fix(openai): allow providers to disable web search source includes (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20599">#20599</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/74bbd933714d5a549927bad0e85117c7a34fd3cd"><code>74bbd93</code></a>
test(openai): avoid network in file path encoding test (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20592">#20592</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/5ec21a6946e13159d3c353c3fcd170ca8564d378"><code>5ec21a6</code></a>
fix: reject unsupported batch request types (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/openai/issues/20562">#20562</a>)</li>
<li>See full diff in <a
href="https://github.com/vercel/ai/commits/@ai-sdk/openai@4.0.66/packages/openai">compare
view</a></li>
</ul>
</details>
<br />

Updates `@langchain/core` from 1.2.10 to 1.2.11
<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>.2.11</h2>
<h3>Patch Changes</h3>
<ul>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langchainjs/pull/11603">#11603</a>
<a
href="https://github.com/langchain-ai/langchainjs/commit/fec9cd87b01976014dd549bd2cf7849aee89a566"><code>fec9cd8</code></a>
Thanks <a
href="https://github.com/thushanth-bengre-langchain"><code>@​thushanth-bengre-langchain</code></a>!
- fix(core): build streaming <code>llmOutput.tokenUsage</code> from the
fully-accumulated chunk instead of whichever individual chunk's
<code>usage_metadata</code> arrived last</p>
<p>Affects both core streaming paths —
<code>.stream()</code>/<code>.streamEvents()</code>
(<code>_streamIterator</code>) and
<code>.invoke()</code>/<code>.generate()</code> when a
streaming-preferring callback is attached
(<code>_generateWithCache</code>'s <code>hasStreamingHandler</code>
branch). Previously, <code>llmOutput.tokenUsage</code> was overwritten
by each chunk in turn, so only the last chunk carrying
<code>usage_metadata</code> won — correct for providers that emit one
cumulative total on a final chunk, but wrong for providers (e.g.
<code>@langchain/google</code>, <code>@langchain/anthropic</code>) that
emit <code>usage_metadata</code> as a per-chunk delta across multiple
chunks, where the values must be summed.</p>
<p>Note for provider authors: this assumes each streamed chunk's
<code>usage_metadata</code> is either a per-chunk delta or appears only
on a single final chunk. A provider that instead repeats a cumulative
total on every chunk will now see it summed (and inflated) in
<code>llmOutput.tokenUsage</code>, matching the existing behavior of the
correctly-working <code>message.usage_metadata</code> field.</p>
<p>Also fixes <code>@langchain/google</code>'s <code>invoke({streaming:
true})</code> path (no streaming-preferring callback attached), where
<code>llmOutput</code> was never populated at all.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langchainjs/pull/11590">#11590</a>
<a
href="https://github.com/langchain-ai/langchainjs/commit/ffebdc2f00f3290d19f85e5afd6a297920ae584c"><code>ffebdc2</code></a>
Thanks <a
href="https://github.com/thushanth-bengre-langchain"><code>@​thushanth-bengre-langchain</code></a>!
- Fix OpenAI Responses API replay under Zero Data Retention when a
response contains more than one reasoning item, for both v0 and v1. In
v0, the default replay path now reuses
<code>response_metadata.output</code> directly, preserving every
reasoning item's <code>id</code>/<code>encrypted_content</code> in
original order. In v1, <code>AIMessage.contentBlocks</code>
(<code>outputVersion: &quot;v1&quot;</code>) is fixed the same way.
<code>additional_kwargs.reasoning</code> is unchanged.</p>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/778566e60d9dde923a9074e6ebbe2129dcb9d580"><code>778566e</code></a>
chore: version packages (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11607">#11607</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/18b71af7f841f3a932050265cf5622721e7571c2"><code>18b71af</code></a>
feat(google-genai): add outputDimensionality parameter to
GoogleGenerativeAIE...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/35368db8b942a353c71a3f4c64b04defeb481000"><code>35368db</code></a>
fix(google): surface groundingMetadata/citationMetadata on streaming
path (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/1">#1</a>...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/78b29235cb1adf341fce97884f9ff558cd38b079"><code>78b2923</code></a>
fix(google): preserve tool call id and thoughtSignature in native
streaming (...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/ffebdc2f00f3290d19f85e5afd6a297920ae584c"><code>ffebdc2</code></a>
fix(openai): correctly handle multiple reasoning items in v1 content
blocks (...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/c9ae84784f14d735108feefac991723fbefbde11"><code>c9ae847</code></a>
fix(google): set <code>includeServerSideToolInvocations</code> when
mixing tools (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11611">#11611</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/bc88b750499ece71315ff3aa31309280bc0423f6"><code>bc88b75</code></a>
fix(google): route Vertex multi-region endpoints (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11433">#11433</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/fec9cd87b01976014dd549bd2cf7849aee89a566"><code>fec9cd8</code></a>
fix(core): build streaming llmOutput.tokenUsage from accumulated usage
(<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11603">#11603</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/194a06348b8f7ef0ecf76c0c72096ef453d1166a"><code>194a063</code></a>
fix(google): allowlist JSON Schema keywords for Gemini schemas (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11606">#11606</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/b0a0d3f73608674818e4ad6c12adde622c90afa5"><code>b0a0d3f</code></a>
fix(deps): upgrade Vitest to address GHSA-82fw-gwwq-j7x9 (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11599">#11599</a>)</li>
<li>See full diff in <a
href="https://github.com/langchain-ai/langchainjs/compare/@langchain/core@1.2.10...@langchain/core@1.2.11">compare
view</a></li>
</ul>
</details>
<br />

Updates `@langchain/langgraph` from 1.4.14 to 1.4.15
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/langchain-ai/langgraphjs/releases">@​langchain/langgraph's
releases</a>.</em></p>
<blockquote>
<h2><code>@​langchain/langgraph</code><a
href="https://github.com/1"><code>@​1</code></a>.4.15</h2>
<h3>Patch Changes</h3>
<ul>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2794">#2794</a>
<a
href="https://github.com/langchain-ai/langgraphjs/commit/83a4b62be99488f17f3d7370a064f635e7c05a2e"><code>83a4b62</code></a>
Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! -
feat(langgraph): add per-node <code>tracePolicy</code> input/output
processors and <code>omitPayload</code></p>
<p>Transform the payloads recorded on a node's own trace run while
retaining its span and timing. Processors receive raw values and fall
back to the original payload if they throw. Graph state, root runs, and
child runs remain unchanged when processors do not mutate their
arguments.</p>
<p>Matches Python's callback-level behavior: transforms also affect
chain events and message streaming, so omitting outputs can suppress
messages returned directly by nodes and omitting inputs can affect
message deduplication.</p>
</li>
<li>
<p>Updated dependencies [<a
href="https://github.com/langchain-ai/langgraphjs/commit/3234c69530416e2709bf54c53472e640864e7de4"><code>3234c69</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/3234c69530416e2709bf54c53472e640864e7de4"><code>3234c69</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/11a4535762b04f8f28cc98eb7b1e4b682b69e91a"><code>11a4535</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/2fab6fda74714cd792fed24e5416cec66fdbc105"><code>2fab6fd</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/4fc118fcde8fd6d977c03c8a0a7071912df1873a"><code>4fc118f</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/db4bdad61ddfc6c1113269b131ac2efde3eecf69"><code>db4bdad</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/55fa26be9290fbd89a6e0acb232f04cbc6dedb22"><code>55fa26b</code></a>]:</p>
<ul>
<li><code>@​langchain/langgraph-sdk</code><a
href="https://github.com/1"><code>@​1</code></a>.11.0</li>
</ul>
</li>
</ul>
<h2><code>@​langchain/langgraph</code><a
href="https://github.com/1"><code>@​1</code></a>.4.15-rc.0</h2>
<h3>Patch Changes</h3>
<ul>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2794">#2794</a>
<a
href="https://github.com/langchain-ai/langgraphjs/commit/83a4b62be99488f17f3d7370a064f635e7c05a2e"><code>83a4b62</code></a>
Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! -
feat(langgraph): add per-node <code>tracePolicy</code> input/output
processors and <code>omitPayload</code></p>
<p>Transform the payloads recorded on a node's own trace run while
retaining its span and timing. Processors receive raw values and fall
back to the original payload if they throw. Graph state, root runs, and
child runs remain unchanged when processors do not mutate their
arguments.</p>
</li>
<li>
<p>Updated dependencies [<a
href="https://github.com/langchain-ai/langgraphjs/commit/2fab6fda74714cd792fed24e5416cec66fdbc105"><code>2fab6fd</code></a>]:</p>
<ul>
<li><code>@​langchain/langgraph-sdk</code><a
href="https://github.com/1"><code>@​1</code></a>.10.3-rc.0</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">@​langchain/langgraph's
changelog</a>.</em></p>
<blockquote>
<h2>1.4.15</h2>
<h3>Patch Changes</h3>
<ul>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2794">#2794</a>
<a
href="https://github.com/langchain-ai/langgraphjs/commit/83a4b62be99488f17f3d7370a064f635e7c05a2e"><code>83a4b62</code></a>
Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! -
feat(langgraph): add per-node <code>tracePolicy</code> input/output
processors and <code>omitPayload</code></p>
<p>Transform the payloads recorded on a node's own trace run while
retaining its span and timing. Processors receive raw values and fall
back to the original payload if they throw. Graph state, root runs, and
child runs remain unchanged when processors do not mutate their
arguments.</p>
<p>Matches Python's callback-level behavior: transforms also affect
chain events and message streaming, so omitting outputs can suppress
messages returned directly by nodes and omitting inputs can affect
message deduplication.</p>
</li>
<li>
<p>Updated dependencies [<a
href="https://github.com/langchain-ai/langgraphjs/commit/3234c69530416e2709bf54c53472e640864e7de4"><code>3234c69</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/3234c69530416e2709bf54c53472e640864e7de4"><code>3234c69</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/11a4535762b04f8f28cc98eb7b1e4b682b69e91a"><code>11a4535</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/2fab6fda74714cd792fed24e5416cec66fdbc105"><code>2fab6fd</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/4fc118fcde8fd6d977c03c8a0a7071912df1873a"><code>4fc118f</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/db4bdad61ddfc6c1113269b131ac2efde3eecf69"><code>db4bdad</code></a>,
<a
href="https://github.com/langchain-ai/langgraphjs/commit/55fa26be9290fbd89a6e0acb232f04cbc6dedb22"><code>55fa26b</code></a>]:</p>
<ul>
<li><code>@​langchain/langgraph-sdk</code><a
href="https://github.com/1"><code>@​1</code></a>.11.0</li>
</ul>
</li>
</ul>
<h2>1.4.15-rc.0</h2>
<h3>Patch Changes</h3>
<ul>
<li>
<p><a
href="https://redirect.github.com/langchain-ai/langgraphjs/pull/2794">#2794</a>
<a
href="https://github.com/langchain-ai/langgraphjs/commit/83a4b62be99488f17f3d7370a064f635e7c05a2e"><code>83a4b62</code></a>
Thanks <a href="https://github.com/hntrl"><code>@​hntrl</code></a>! -
feat(langgraph): add per-node <code>tracePolicy</code> input/output
processors and <code>omitPayload</code></p>
<p>Transform the payloads recorded on a node's own trace run while
retaining its span and timing. Processors receive raw values and fall
back to the original payload if they throw. Graph state, root runs, and
child runs remain unchanged when processors do not mutate their
arguments.</p>
</li>
<li>
<p>Updated dependencies [<a
href="https://github.com/langchain-ai/langgraphjs/commit/2fab6fda74714cd792fed24e5416cec66fdbc105"><code>2fab6fd</code></a>]:</p>
<ul>
<li><code>@​langchain/langgraph-sdk</code><a
href="https://github.com/1"><code>@​1</code></a>.10.3-rc.0</li>
</ul>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/592fd0cab0fd9287fab1b7c7fcfd4abc44675700"><code>592fd0c</code></a>
chore: version packages (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2832">#2832</a>)</li>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/a3172e045b36b00244512260b041e472b915c39b"><code>a3172e0</code></a>
revert(langgraph): <code>tracePolicy</code> (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2834">#2834</a>)</li>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/a97e6f4eaf8683cd67002bc42cf8dddf5255e29d"><code>a97e6f4</code></a>
chore(deps): patch vulnerable browser and example dependencies (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2822">#2822</a>)</li>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/6fb9a3fe43d0e4d600fbf413392343d7242ccb63"><code>6fb9a3f</code></a>
chore(deps): bump vitest from 4.1.10 to 4.1.11 (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2818">#2818</a>)</li>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/bbbdb5aa8a50f7115bdfbb6e3cf020ee239e1842"><code>bbbdb5a</code></a>
chore: version packages (rc) (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2798">#2798</a>)</li>
<li><a
href="https://github.com/langchain-ai/langgraphjs/commit/83a4b62be99488f17f3d7370a064f635e7c05a2e"><code>83a4b62</code></a>
feat(langgraph): <code>tracePolicy</code> (<a
href="https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core/issues/2794">#2794</a>)</li>
<li>See full diff in <a
href="https://github.com/langchain-ai/langgraphjs/commits/@langchain/langgraph@1.4.15/libs/langgraph-core">compare
view</a></li>
</ul>
</details>
<br />

Updates `@langchain/openai` from 1.5.12 to 1.5.13
<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>.5.13</h2>
<h3>Patch Changes</h3>
<ul>
<li><a
href="https://redirect.github.com/langchain-ai/langchainjs/pull/11590">#11590</a>
<a
href="https://github.com/langchain-ai/langchainjs/commit/ffebdc2f00f3290d19f85e5afd6a297920ae584c"><code>ffebdc2</code></a>
Thanks <a
href="https://github.com/thushanth-bengre-langchain"><code>@​thushanth-bengre-langchain</code></a>!
- Fix OpenAI Responses API replay under Zero Data Retention when a
response contains more than one reasoning item, for both v0 and v1. In
v0, the default replay path now reuses
<code>response_metadata.output</code> directly, preserving every
reasoning item's <code>id</code>/<code>encrypted_content</code> in
original order. In v1, <code>AIMessage.contentBlocks</code>
(<code>outputVersion: &quot;v1&quot;</code>) is fixed the same way.
<code>additional_kwargs.reasoning</code> is unchanged.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/778566e60d9dde923a9074e6ebbe2129dcb9d580"><code>778566e</code></a>
chore: version packages (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11607">#11607</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/18b71af7f841f3a932050265cf5622721e7571c2"><code>18b71af</code></a>
feat(google-genai): add outputDimensionality parameter to
GoogleGenerativeAIE...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/35368db8b942a353c71a3f4c64b04defeb481000"><code>35368db</code></a>
fix(google): surface groundingMetadata/citationMetadata on streaming
path (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/1">#1</a>...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/78b29235cb1adf341fce97884f9ff558cd38b079"><code>78b2923</code></a>
fix(google): preserve tool call id and thoughtSignature in native
streaming (...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/ffebdc2f00f3290d19f85e5afd6a297920ae584c"><code>ffebdc2</code></a>
fix(openai): correctly handle multiple reasoning items in v1 content
blocks (...</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/c9ae84784f14d735108feefac991723fbefbde11"><code>c9ae847</code></a>
fix(google): set <code>includeServerSideToolInvocations</code> when
mixing tools (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11611">#11611</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/bc88b750499ece71315ff3aa31309280bc0423f6"><code>bc88b75</code></a>
fix(google): route Vertex multi-region endpoints (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11433">#11433</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/fec9cd87b01976014dd549bd2cf7849aee89a566"><code>fec9cd8</code></a>
fix(core): build streaming llmOutput.tokenUsage from accumulated usage
(<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11603">#11603</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/194a06348b8f7ef0ecf76c0c72096ef453d1166a"><code>194a063</code></a>
fix(google): allowlist JSON Schema keywords for Gemini schemas (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11606">#11606</a>)</li>
<li><a
href="https://github.com/langchain-ai/langchainjs/commit/b0a0d3f73608674818e4ad6c12adde622c90afa5"><code>b0a0d3f</code></a>
fix(deps): upgrade Vitest to address GHSA-82fw-gwwq-j7x9 (<a
href="https://redirect.github.com/langchain-ai/langchainjs/issues/11599">#11599</a>)</li>
<li>See full diff in <a
href="https://github.com/langchain-ai/langchainjs/compare/@langchain/openai@1.5.12...@langchain/openai@1.5.13">compare
view</a></li>
</ul>
</details>
<br />

Updates `ai` from 7.0.97 to 7.0.99
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a href="https://github.com/vercel/ai/releases">ai's
releases</a>.</em></p>
<blockquote>
<h2>ai@7.0.99</h2>
<h3>Patch Changes</h3>
<ul>
<li>615ac89: feat(ai): use InvalidArgumentError for utility input
validation</li>
<li>Updated dependencies [7f76d83]
<ul>
<li><code>@​ai-sdk/gateway</code><a
href="https://github.com/4"><code>@​4</code></a>.0.80</li>
</ul>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/vercel/ai/blob/main/packages/ai/CHANGELOG.md">ai's
changelog</a>.</em></p>
<blockquote>
<h2>7.0.99</h2>
<h3>Patch Changes</h3>
<ul>
<li>615ac89: feat(ai): use InvalidArgumentError for utility input
validation</li>
<li>Updated dependencies [7f76d83]
<ul>
<li><code>@​ai-sdk/gateway</code><a
href="https://github.com/4"><code>@​4</code></a>.0.80</li>
</ul>
</li>
</ul>
<h2>7.0.98</h2>
<h3>Patch Changes</h3>
<ul>
<li>5ec21a6: fix: reject unsupported batch request types</li>
<li>db59d78: feat(ai): add runtime context attribution to embed,
embedMany and rerank</li>
<li>7469a3b: feat: support image generation requests in batches</li>
<li>f87bf07: fix(ai): reject invalid reranking provider indices</li>
<li>bc5cb7a: fix(ai): accept inferred tools in
<code>validateUIMessages</code></li>
<li>a5f449a: feat(ai): add a stable UI message type and type guard for
tool output errors</li>
<li>Updated dependencies [5ec21a6]</li>
<li>Updated dependencies [7469a3b]</li>
<li>Updated dependencies [dbd83a3]</li>
<li>Updated dependencies [813bb36]</li>
<li>Updated dependencies [c43e4b7]</li>
<li>Updated dependencies [03f4e59]
<ul>
<li><code>@​ai-sdk/gateway</code><a
href="https://github.com/4"><code>@​4</code></a>.0.79</li>
<li><code>@​ai-sdk/provider</code><a
href="https://github.com/4"><code>@​4</code></a>.0.14</li>
<li><code>@​ai-sdk/provider-utils</code><a
href="https://github.com/5"><code>@​5</code></a>.0.40</li>
</ul>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/vercel/ai/commit/6c6c2210b9532a4c369615c044a16d595f3db117"><code>6c6c221</code></a>
Version Packages (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20670">#20670</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/615ac892b4b1bd0fb0b769fbf906588b27437a97"><code>615ac89</code></a>
feat: use InvalidArgumentError for utility input validation (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20304">#20304</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/9ed46d2da5df1394079c66d422bc553fd0c34376"><code>9ed46d2</code></a>
Version Packages (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20569">#20569</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/a5f449ad2d94713240d68bc33cd0f8a0b45b2aa4"><code>a5f449a</code></a>
feat: add a stable UI message type and type guard for tool output errors
(<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20">#20</a>...</li>
<li><a
href="https://github.com/vercel/ai/commit/bc5cb7ac5f966a721d86edd1099f8482f7ffb168"><code>bc5cb7a</code></a>
fix(ai): accept inferred tools in <code>validateUIMessages</code> (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20660">#20660</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/db59d78f8134ff9d231bbe34a91ca882013e1740"><code>db59d78</code></a>
feat(ai): add runtime context attribution to embed, embedMany and rerank
(<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20">#20</a>...</li>
<li><a
href="https://github.com/vercel/ai/commit/7469a3bc5daf0fd8c535c903f883d730a39de191"><code>7469a3b</code></a>
feat: support image generation requests in batches (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20594">#20594</a>)</li>
<li><a
href="https://github.com/vercel/ai/commit/f87bf07ebe466217464770ee37abe32bda3f2697"><code>f87bf07</code></a>
fix: rerank() returns undefined documents for invalid provider ranking
indice...</li>
<li><a
href="https://github.com/vercel/ai/commit/5ec21a6946e13159d3c353c3fcd170ca8564d378"><code>5ec21a6</code></a>
fix: reject unsupported batch request types (<a
href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/20562">#20562</a>)</li>
<li>See full diff in <a
href="https://github.com/vercel/ai/commits/ai@7.0.99/packages/ai">compare
view</a></li>
</ul>
</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>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Author: dependabot[bot]

examples/package.json

@@ -9,11 +9,11 @@
     "@everruns/bashkit": "latest"
   },
   "devDependencies": {
-    "@ai-sdk/openai": "^4.0.65",
-    "@langchain/core": "^1.2.10",
-    "@langchain/langgraph": "^1.4.14",
-    "@langchain/openai": "^1.5.12",
-    "ai": "^7.0.97",
+    "@ai-sdk/openai": "^4.0.66",
+    "@langchain/core": "^1.2.11",
+    "@langchain/langgraph": "^1.4.15",
+    "@langchain/openai": "^1.5.13",
+    "ai": "^7.0.99",
     "openai": "^7.15.0",
     "zod": "^4.6.2"
   },