Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
chore(deps): bump the npm-production group with 24 updates (#5087)
Bumps the npm-production group with 24 updates: | Package | From | To | | --- | --- | --- | | [@anthropic-ai/claude-agent-sdk](https://github.com/anthropics/claude-agent-sdk-typescript) | `0.3.296` | `0.3.304` | | [@mastra/mcp](https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp) | `1.17.2` | `1.18.0` | | [ai](https://github.com/vercel/ai/tree/HEAD/packages/ai) | `6.0.303` | `6.0.311` | | [@anthropic-ai/sdk](https://github.com/anthropics/anthropic-sdk-typescript) | `0.133.0` | `0.135.0` | | [@google/genai](https://github.com/googleapis/js-genai) | `2.28.0` | `2.30.0` | | [@langchain/core](https://github.com/langchain-ai/langchainjs) | `1.2.17` | `1.2.18` | | [@langchain/langgraph](https://github.com/langchain-ai/langgraphjs/tree/HEAD/libs/langgraph-core) | `1.4.21` | `1.5.1` | | [langchain](https://github.com/langchain-ai/langchainjs) | `1.5.16` | `1.5.18` | | [@ai-sdk/openai](https://github.com/vercel/ai/tree/HEAD/packages/openai) | `3.0.125` | `3.0.130` | | [@typesafe-ai/sdk](https://github.com/typesafe-ai/typesafe-sdk-js) | `0.6.0` | `0.7.0` | | [undici](https://github.com/nodejs/undici) | `7.30.0` | `7.30.1` | | [typebox](https://github.com/sinclairzx81/typebox) | `1.3.36` | `1.4.2` | | [re2js](https://github.com/le0pard/re2js) | `2.8.6` | `2.8.8` | | [@mastra/schema-compat](https://github.com/mastra-ai/mastra/tree/HEAD/packages/schema-compat) | `1.3.13` | `1.3.15` | | [@ai-sdk/mcp](https://github.com/vercel/ai/tree/HEAD/packages/mcp) | `2.0.73` | `2.0.80` | | [@cloudflare/workers-types](https://github.com/cloudflare/workerd) | `5.20261012.1` | `5.20261019.1` | | [@effect/language-service](https://github.com/Effect-TS/language-service) | `0.87.4` | `0.87.5` | | [@effect/platform-bun](https://github.com/Effect-TS/effect/tree/HEAD/packages/platform/bun) | `4.0.3` | `4.0.5` | | [@effect/vitest](https://github.com/Effect-TS/effect/tree/HEAD/packages/vitest) | `4.0.3` | `4.0.5` | | [@vitest/ui](https://github.com/vitest-dev/vitest/tree/HEAD/packages/ui) | `5.0.4` | `5.0.5` | | [dotenv](https://github.com/motdotla/dotenv) | `18.0.7` | `18.0.8` | | [effect](https://github.com/Effect-TS/effect/tree/HEAD/packages/effect) | `4.0.3` | `4.0.5` | | [openai](https://github.com/openai/openai-node) | `7.32.0` | `7.39.0` | | [wrangler](https://github.com/cloudflare/workers-sdk/tree/HEAD/packages/wrangler) | `4.149.0` | `4.151.2` | Updates `@anthropic-ai/claude-agent-sdk` from 0.3.296 to 0.3.304 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/anthropics/claude-agent-sdk-typescript/releases">@anthropic-ai/claude-agent-sdk's releases</a>.</em></p> <blockquote> <h2>v0.3.304</h2> <h2>What's changed</h2> <ul> <li>Added <code>suspendSseStream(query)</code> and <code>resumeSseStream(query)</code> to the browser SDK: close a query's event stream and reopen it later without ending the query</li> <li>Added stable row ids to <code>getContextUsage()</code>, and, when the CLI answers on its own stdio, plugin ids, agent and skill file paths, and per-server MCP instruction token shares</li> <li>Fixed <code>startup()</code> timing out while a SessionStart or Setup command hook was running when no <code>initializeTimeoutMs</code> is passed: up to 10 minutes of that time no longer counts toward the 60-second limit, and the timeout error now says what the process reported</li> <li>Fixed <code>startup()</code> keeping every <code>hook_progress</code> message of a running SessionStart or Setup hook in memory until it resolved; it now keeps only the newest one for each hook</li> <li>Updated to parity with Claude Code v2.1.304</li> </ul> <h2>Update</h2> <pre lang="sh"><code>npm install @anthropic-ai/claude-agent-sdk@0.3.304 # or yarn add @anthropic-ai/claude-agent-sdk@0.3.304 # or pnpm add @anthropic-ai/claude-agent-sdk@0.3.304 # or bun add @anthropic-ai/claude-agent-sdk@0.3.304 </code></pre> <h2>v0.3.303</h2> <h2>What's changed</h2> <ul> <li>Updated to parity with Claude Code v2.1.303</li> </ul> <h2>Update</h2> <pre lang="sh"><code>npm install @anthropic-ai/claude-agent-sdk@0.3.303 # or yarn add @anthropic-ai/claude-agent-sdk@0.3.303 # or pnpm add @anthropic-ai/claude-agent-sdk@0.3.303 # or bun add @anthropic-ai/claude-agent-sdk@0.3.303 </code></pre> <h2>v0.3.302</h2> <h2>What's changed</h2> <ul> <li>Fixed structured output results delivering a response's output as <code>structured_output</code> when the API refused that response; the result is now an error with no payload</li> <li>Changed an omitted <code>permissionMode</code> to start in <code>default</code> mode on third-party providers, with telemetry off or on a fresh install; pass <code>permissionMode: 'auto'</code> to keep auto mode</li> <li>Changed fork subagents (<code>subagent_type: "fork"</code>) to be on by default in SDK sessions, as in the terminal; <code>run_in_background</code> is still offered, and <code>CLAUDE_CODE_FORK_SUBAGENT=0</code> turns them off</li> <li>Updated to parity with Claude Code v2.1.302</li> </ul> <h2>Update</h2> <pre lang="sh"><code>npm install @anthropic-ai/claude-agent-sdk@0.3.302 </tr></table> </code></pre> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/anthropics/claude-agent-sdk-typescript/blob/main/CHANGELOG.md">@anthropic-ai/claude-agent-sdk's changelog</a>.</em></p> <blockquote> <h2>0.3.304</h2> <ul> <li>Added <code>suspendSseStream(query)</code> and <code>resumeSseStream(query)</code> to the browser SDK: close a query's event stream and reopen it later without ending the query</li> <li>Added stable row ids to <code>getContextUsage()</code>, and, when the CLI answers on its own stdio, plugin ids, agent and skill file paths, and per-server MCP instruction token shares</li> <li>Fixed <code>startup()</code> timing out while a SessionStart or Setup command hook was running when no <code>initializeTimeoutMs</code> is passed: up to 10 minutes of that time no longer counts toward the 60-second limit, and the timeout error now says what the process reported</li> <li>Fixed <code>startup()</code> keeping every <code>hook_progress</code> message of a running SessionStart or Setup hook in memory until it resolved; it now keeps only the newest one for each hook</li> <li>Updated to parity with Claude Code v2.1.304</li> </ul> <h2>0.3.303</h2> <ul> <li>Updated to parity with Claude Code v2.1.303</li> </ul> <h2>0.3.302</h2> <ul> <li>Fixed structured output results delivering a response's output as <code>structured_output</code> when the API refused that response; the result is now an error with no payload</li> <li>Changed an omitted <code>permissionMode</code> to start in <code>default</code> mode on third-party providers, with telemetry off or on a fresh install; pass <code>permissionMode: 'auto'</code> to keep auto mode</li> <li>Changed fork subagents (<code>subagent_type: "fork"</code>) to be on by default in SDK sessions, as in the terminal; <code>run_in_background</code> is still offered, and <code>CLAUDE_CODE_FORK_SUBAGENT=0</code> turns them off</li> <li>Updated to parity with Claude Code v2.1.302</li> </ul> <h2>0.3.301</h2> <ul> <li>Added per-tool permission policies to sdk-type MCP server configs: <code>tools</code> entries with <code>permission_policy</code> <code>always_ask</code> or <code>always_deny</code>, applied on <code>initialize</code> and <code>setMcpServers()</code></li> <li>Added <code>BUILTIN_TOOL_NAMES</code> and <code>LEGACY_TOOL_NAME_ALIASES</code> exports: the public built-in tool names and their earlier names, for checking permission rules and tool settings</li> <li>Added <code>addPlugins</code> to <code>Query.reloadPlugins()</code> so a host can load more plugin folders into a running session</li> <li>Fixed <code>setModel()</code> with a model ID failing while the account is at its five-hour or weekly usage limit; the model now applies and the next message reports the limit</li> <li>Changed the error when a full disk keeps the login from being refreshed: <code>error</code> is now <code>invalid_request</code>, not <code>authentication_failed</code>, and <code>api_error_status</code> is <code>null</code>, not 401</li> <li>Changed <code>mcpServerStatus()</code> to still report a tool's <code>_meta.ui.visibility</code> when the rest of its <code>_meta.ui</code> fails validation</li> <li>Updated to parity with Claude Code v2.1.301</li> </ul> <h2>0.3.300</h2> <ul> <li>Fixed <code>importSessionToStore</code> skipping transcript rows that contain a Unicode line or paragraph separator (U+2028, U+2029) on Node 24 and Bun</li> <li>Fixed a background subagent's final report in auto mode being joined into one turn with another message from the same subagent; the report now always runs as its own turn</li> <li>Fixed <code>rewind_conversation</code> with <code>interrupt_if_running</code> stopping the running turn before refusing with "unseen later turn"</li> <li>Reverted <code>canUseTool</code> options carrying <code>suppressAlwaysAllowRule: true</code> for connector tools that an organization set to require approval (added in 0.3.292)</li> <li>Improved the browser SDK bundle (<code>@anthropic-ai/claude-agent-sdk/browser</code>): 40% smaller to download, by no longer bundling a Node <code>crypto</code> polyfill</li> <li>Changed <code>thinking: { type: 'disabled' }</code> and <code>maxThinkingTokens: 0</code> to run as adaptive thinking on models that can't turn thinking off</li> <li>Changed <code>updatedInput</code> from PreToolUse and PermissionRequest hook callbacks: it is now validated like Claude's own input and unknown keys are dropped; <code>canUseTool</code> is unchanged</li> <li>Updated to parity with Claude Code v2.1.300</li> </ul> <h2>0.3.299</h2> <ul> <li>Added an optional <code>nextFireAt</code> (epoch ms of the next run) to the CronCreate and CronList tool outputs</li> <li>Added <code>property_order</code> to the <code>elicitation</code> control request: a form's field names in the order the MCP server listed them, for hosts whose transport keeps no JSON object key order</li> <li>Fixed <code>rewind_conversation</code> answering "target not found" for a message stopped during its prompt hooks or plugins: until a reply or input follows, it answers <code>rewound: true</code> with a null <code>prefillText</code></li> <li>Fixed in-process SDK MCP servers named <code>constructor</code> or <code>toString</code> being silently dropped when a <code>prewarm()</code> process is claimed with <code>SpareProcess.claim()</code></li> <li>Fixed queued user messages with content-block arrays running together without a line break when merged into one turn</li> <li>Fixed <code>origin.body</code> on a user message that merges several queued peer messages (from other sessions or agents) carrying only the first message's text; it is now omitted</li> <li>Changed <code>initialize</code>, <code>mcp_set_servers</code> and <code>claim_session</code> to refuse the reserved MCP server names <code>__proto__</code>, <code>__defineGetter__</code>, <code>__defineSetter__</code>, <code>__lookupGetter__</code>, <code>__lookupSetter__</code></li> <li>Updated to parity with Claude Code v2.1.299</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/b8060fa5ac705b8f69ea32aafd21d32a9851000e"><code>b8060fa</code></a> chore: Update CHANGELOG.md</li> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/53464f259015a7f42a04b3d0be04063dfabebd9a"><code>53464f2</code></a> chore: Update CHANGELOG.md</li> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/9cf9f23b757f881c82fc2bfee459429ea26187df"><code>9cf9f23</code></a> chore: Update CHANGELOG.md</li> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/b0fc766997199a49f90c37f5ec056936c80c9491"><code>b0fc766</code></a> chore: Update CHANGELOG.md</li> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/fbc529490ca0fb07b486c6f9c8e553d3fb7c690d"><code>fbc5294</code></a> chore: Update CHANGELOG.md</li> <li><a href="https://github.com/anthropics/claude-agent-sdk-typescript/commit/273b4c87f832a82300e1f9e5db57acd835b862a5"><code>273b4c8</code></a> chore: Update CHANGELOG.md</li> <li>See full diff in <a href="https://github.com/anthropics/claude-agent-sdk-typescript/compare/v0.3.296...v0.3.304">compare view</a></li> </ul> </details> <br /> Updates `@mastra/mcp` from 1.17.2 to 1.18.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/mastra-ai/mastra/releases">@mastra/mcp's releases</a>.</em></p> <blockquote> <h2>December 9, 2025</h2> <h1>Changelog</h1> <h2>Summary</h2> <ul> <li><strong>Total packages with changes</strong>: 12</li> <li><strong>Packages with major changes</strong>: 0</li> <li><strong>Packages with minor changes</strong>: 0</li> <li><strong>Packages with patch changes</strong>: 4</li> </ul> <hr /> <h2><code>@mastra/agent-builder</code><a href="https://github.com/0"><code>@0</code></a>.2.6-alpha.1</h2> <h3>Patch Changes</h3> <ul> <li>Fix install step validation error by making targetPath optional in InstallInputSchema. This resolves the "expected string, received undefined" error when running the agent builder template workflow without explicitly providing a targetPath parameter. (<a href="https://redirect.github.com/mastra-ai/mastra/pull/10923">#10923</a>)</li> </ul> <h3>Dependency Updates</h3> <ul> <li><code>@mastra/core</code><a href="https://github.com/0"><code>@0</code></a>.24.7-alpha.3</li> </ul> <hr /> <h2><code>@mastra/ai-sdk</code><a href="https://github.com/0"><code>@0</code></a>.3.3-alpha.0</h2> <h3>Patch Changes</h3> <ul> <li> <p>Return NetworkDataPart on each agent-execution-event and workflow-execution-event in network streams (<a href="https://redirect.github.com/mastra-ai/mastra/pull/10979">#10979</a>)</p> </li> <li> <p>Fixed tool-call-suspended chunks being dropped in workflow-step-output when using AI SDK. Previously, when an agent inside a workflow step called a tool that got suspended, the tool-call-suspended chunk was not received on the frontend even though tool-input-available chunks were correctly received. (<a href="https://redirect.github.com/mastra-ai/mastra/pull/10988">#10988</a>)</p> <p>The issue occurred because tool-call-suspended was not included in the isMastraTextStreamChunk list, causing it to be filtered out in transformWorkflow. Now tool-call-suspended, tool-call-approval, object, and tripwire chunks are properly included in the text stream chunk list and will be transformed and passed through correctly.</p> <p>Fixes <a href="https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp/issues/10978">#10978</a></p> </li> </ul> <h3>Dependency Updates</h3> <ul> <li><code>@mastra/core</code><a href="https://github.com/0"><code>@0</code></a>.24.7-alpha.3</li> </ul> <hr /> <h2><code>@mastra/client-js</code><a href="https://github.com/0"><code>@0</code></a>.17.0-alpha.3</h2> <h3>Dependency Updates</h3> <ul> <li><code>@mastra/core</code><a href="https://github.com/0"><code>@0</code></a>.24.7-alpha.3</li> </ul> <hr /> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/mastra-ai/mastra/blob/main/packages/mcp/CHANGELOG.md">@mastra/mcp's changelog</a>.</em></p> <blockquote> <h2>1.18.0</h2> <h3>Patch Changes</h3> <ul> <li> <p>Improved MCP client and server declarations with concise setup examples and directions to bundled documentation. (<a href="https://redirect.github.com/mastra-ai/mastra/pull/23489">#23489</a>)</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/mastra-ai/mastra/commit/d9ef54303b7f050f4e364701c3821fc61e7002f2"><code>d9ef543</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/b96744daad8c6e181f03fdf38c732206ded428a2"><code>b96744d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ad5ac69bcd037bfb85c3399d8b39d9364931ad1b"><code>ad5ac69</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e86be034c017fca7deae7d1ebb34d36413928cb8"><code>e86be03</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/492c0aedcee3fde9555111a660b6c975c160a0db"><code>492c0ae</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/0f4d9cf79b49b6dc6a484a0b2d1cf381eb2343a6"><code>0f4d9cf</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/50e2658cdcdc55a14abde08610a8e2b12fdf67a4"><code>50e2658</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a0aa698427db9730e39f0c9956d21b97307ab313"><code>a0aa698</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/8510a6d38b9d211af7d94b7860ab182ce55c39d1"><code>8510a6d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ddbd3527654a058ed413ae164a1246003dcc9030"><code>ddbd352</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/5eba9420330b3f116810891ae14888f7f256cd4f"><code>5eba942</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/4112ecdec76827384d3a7ab4e8db3ccf90ae7ed1"><code>4112ecd</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/37065ad6cd3f74afd16417e8d4e0839c13beca40"><code>37065ad</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/648dd4f4c4cd330013c0a98f50ffac77fe2ad632"><code>648dd4f</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/2990bccd1c648c8f8614da97fbb459819871f5bc"><code>2990bcc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/617c1b30e7e794bbb77feaced1848fde291fc240"><code>617c1b3</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/1ce03b9c04c633e815bc21cb78c29f7f19851fb2"><code>1ce03b9</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/c3d00db279a95c7dcba0f767704a2bb6544b7b29"><code>c3d00db</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/df14b5d12374137db86f92061f8714b28473672e"><code>df14b5d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/fff33614a3376676797cb9b5a5c5b090b026fa0e"><code>fff3361</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/422e798ab1a4b14302c5b49fed2f6c818a82706e"><code>422e798</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/3fc8c2d35f724c3648150b29e50cf61a9360b274"><code>3fc8c2d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ddb3639e3de41f3fe33f68f81c2e5850ff1280b6"><code>ddb3639</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/4b3f587ceabb3f3697c4c1ad4fb154d58002ef7c"><code>4b3f587</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/47868b2dde360b038d829c9f88e15061acf3efb5"><code>47868b2</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/44c20c9a40ba5ef153e1d5d0c413b825e1de42d7"><code>44c20c9</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/502ca8904848e77d44622669f2728171d36ad6ca"><code>502ca89</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/953be88befd9cdb789b4cfc16680121c663a631b"><code>953be88</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/b95aabba261a39b73430d95f3ed051634117d517"><code>b95aabb</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/055057ca2102e35008fe30871f7c8f422ae25ec2"><code>055057c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/7290151bdb3bfe518653b0a66a19d6790925e4a0"><code>7290151</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/2990bccd1c648c8f8614da97fbb459819871f5bc"><code>2990bcc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/9bc789591ad683f304c63bd01e554fbba2df9cf6"><code>9bc7895</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ffe16f17447449b7155f1f15992e3c9e5f6511ac"><code>ffe16f1</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/f4667539a0c41ae4aa08a4ed380f374687db2592"><code>f466753</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/04c11b3cd698fa37af8fad466dc2bf6fa0d5494d"><code>04c11b3</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/967ab179c9814e734af9c3395ff8ef795acbe06c"><code>967ab17</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ad5ac69bcd037bfb85c3399d8b39d9364931ad1b"><code>ad5ac69</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/6d206205f781cfa2598c2a55123a336909e039b4"><code>6d20620</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/47868b2dde360b038d829c9f88e15061acf3efb5"><code>47868b2</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/fde3ca590f7d854ff33354eff4261b907bdacde4"><code>fde3ca5</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/3a1d2537ad28754a164aedbf0dd94be224ccb0c3"><code>3a1d253</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/0775cdee12b6ad2ad6b5c97874e6248db720224c"><code>0775cde</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e3c3e5e3e354e88207aa9747f9f0cd3352cea972"><code>e3c3e5e</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/6902f940f1879955a90faa0a0ac871667b59d428"><code>6902f94</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/d55aa616b3e88015c3b74342c75bd510c7e764df"><code>d55aa61</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/7148bf55b147e3fae90b3ba0c9517adb0af5f2a4"><code>7148bf5</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e83dfade569ee5aea688de9f2bb8bf8db0a653a7"><code>e83dfad</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/44057eac6fd048100574bf71c6dc095f769a6d63"><code>44057ea</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/d581249a5bf97d32d73e0f1f30cd50ff108e2d67"><code>d581249</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/228945659b2003633e0ebb33e7e34cc2f6efbded"><code>2289456</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/6bb122c5147b612c0fe7f173f940933066c4cfcc"><code>6bb122c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/2c501bc8f661b27a06842f1312221efa6125e580"><code>2c501bc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/990b47fa7370753967ea7ce83100a522f79ab328"><code>990b47f</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/90846f2bfd890de159ab7c3d4fcf8a71c6fb7125"><code>90846f2</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/6bdb944acb3f39bccad59ee140d7614420948f6b"><code>6bdb944</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/d1b070cd77a944e6bb2e5848052b1e8275be88a2"><code>d1b070c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/7f6d101044eefc0d776a555b45dbea1c0d5224c4"><code>7f6d101</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/4573c231c108e7d796eab12b8e9b2094f8cc4d47"><code>4573c23</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a54766a10381295583144847b856d18e8f924d30"><code>a54766a</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/1bd31e7fd49e6de56e6e9a157a6b452cbbd86983"><code>1bd31e7</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a4381a2b36cdb81c4e33c435cd882921edfc146c"><code>a4381a2</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ff45065d42132075c4efb064d96169c4eadbab58"><code>ff45065</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e872dd6619f3a5a46f1158b190b02f607b74d191"><code>e872dd6</code></a>]:</p> <ul> <li><code>@mastra/core</code><a href="https://github.com/1"><code>@1</code></a>.67.0</li> </ul> </li> </ul> <h2>1.18.0-alpha.1</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/mastra-ai/mastra/commit/ad5ac69bcd037bfb85c3399d8b39d9364931ad1b"><code>ad5ac69</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/df14b5d12374137db86f92061f8714b28473672e"><code>df14b5d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/fff33614a3376676797cb9b5a5c5b090b026fa0e"><code>fff3361</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ffe16f17447449b7155f1f15992e3c9e5f6511ac"><code>ffe16f1</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/04c11b3cd698fa37af8fad466dc2bf6fa0d5494d"><code>04c11b3</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ad5ac69bcd037bfb85c3399d8b39d9364931ad1b"><code>ad5ac69</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e83dfade569ee5aea688de9f2bb8bf8db0a653a7"><code>e83dfad</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/6bb122c5147b612c0fe7f173f940933066c4cfcc"><code>6bb122c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/7f6d101044eefc0d776a555b45dbea1c0d5224c4"><code>7f6d101</code></a>]: <ul> <li><code>@mastra/core</code><a href="https://github.com/1"><code>@1</code></a>.67.0-alpha.4</li> </ul> </li> </ul> <h2>1.17.4-alpha.0</h2> <h3>Patch Changes</h3> <ul> <li> <p>Improved MCP client and server declarations with concise setup examples and directions to bundled documentation. (<a href="https://redirect.github.com/mastra-ai/mastra/pull/23489">#23489</a>)</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/mastra-ai/mastra/commit/a0aa698427db9730e39f0c9956d21b97307ab313"><code>a0aa698</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/c3d00db279a95c7dcba0f767704a2bb6544b7b29"><code>c3d00db</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/44c20c9a40ba5ef153e1d5d0c413b825e1de42d7"><code>44c20c9</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/f4667539a0c41ae4aa08a4ed380f374687db2592"><code>f466753</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e3c3e5e3e354e88207aa9747f9f0cd3352cea972"><code>e3c3e5e</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/d581249a5bf97d32d73e0f1f30cd50ff108e2d67"><code>d581249</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/990b47fa7370753967ea7ce83100a522f79ab328"><code>990b47f</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e872dd6619f3a5a46f1158b190b02f607b74d191"><code>e872dd6</code></a>]:</p> <ul> <li><code>@mastra/core</code><a href="https://github.com/1"><code>@1</code></a>.67.0-alpha.2</li> </ul> </li> </ul> <h2>1.17.3</h2> <h3>Patch Changes</h3> <ul> <li> <p>Update README to include accurate, up-to-date information (<a href="https://redirect.github.com/mastra-ai/mastra/pull/22858">#22858</a>)</p> </li> <li> <p>Fixed MCP tools not validating structured tool results against the tool's output schema. Tools rebuilt from a cached catalog with toolFromDefinition / toolsFromDefinitions (and live-discovered tools whose result bypasses the SDK check) now validate structuredContent before it reaches the model, and return the same structured validation error that createTool produces on mismatch. Valid results, in-band tool errors, and results without structuredContent are unchanged. Fixes <a href="https://redirect.github.com/mastra-ai/mastra/issues/22549">mastra-ai/mastra#22549</a> (<a href="https://redirect.github.com/mastra-ai/mastra/pull/22779">#22779</a>)</p> </li> <li> <p>Required <code>@mastra/core</code> 1.64 or newer so MCP can use the tool output validation API added in that release. (<a href="https://redirect.github.com/mastra-ai/mastra/pull/22817">#22817</a>)</p> </li> <li> <p>Remove <code>CHANGELOG.md</code> from distributed npm files resulting in reduced package size (<a href="https://redirect.github.com/mastra-ai/mastra/pull/22737">#22737</a>)</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/mastra-ai/mastra/commit/3910c77413a3058ab270c6dbc74a59bc3cdf67ea"><code>3910c77</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/decd47d0db2a891a6832e226557145b6658b0b19"><code>decd47d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/c1d3422e8052a4282e8547df914b6231e5345f01"><code>c1d3422</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/285ce1c1399341a37e76233aa94dbf9f1a41bd5d"><code>285ce1c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e983f749873189f767f509eb33d1a3596c0f1c74"><code>e983f74</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/45963483f4cd2810f0646469916f74266a3dd607"><code>4596348</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/7686114e3802f4cea414377eaf10999524d670fa"><code>7686114</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ea56b1fa6e0f99673d2f8a5b7dacc8d351507ff7"><code>ea56b1f</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/50469b2d085fc8550579ca4b741eb359d1705abc"><code>50469b2</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/5b5e3cc006950b0ff9720c5be8396d4c95e8a6ac"><code>5b5e3cc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/809e882ee9c154ac642eaed396163df706db6ae4"><code>809e882</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/cedc25d8c2dec005d8b10b6ce2d36feef1162ff0"><code>cedc25d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/125523539237c39f84d126d16476093336089c0d"><code>1255235</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/2e87ffbb454cc88bd8a8c022d1e46325e7907482"><code>2e87ffb</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a499422cd7eccca184cac7b7a684a6199784aa82"><code>a499422</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/cf58c86cb48ccc72677bdaa422e43f102683184c"><code>cf58c86</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a3606a09f3deaeef17caf04b9c6a0d7cd6b80fe6"><code>a3606a0</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/40957529233d202446ebecab1f59c76e99910230"><code>4095752</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/74b21fd9bbe88e770d9acf4e00e01c8bbb7c9e61"><code>74b21fd</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/045c3c78f2129fea5d4467bb26cff2b49788b3d0"><code>045c3c7</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/a3606a09f3deaeef17caf04b9c6a0d7cd6b80fe6"><code>a3606a0</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/449d1120cc1f9c43a71308a9fd8b178cfb11355f"><code>449d112</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/e8aca339dc92c0b60baad3d948a7c48ec9ae106f"><code>e8aca33</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/c5c9ffc3b36bdc7b17d6f911be81e28ba02acfad"><code>c5c9ffc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/9d3073c230dbff45d58c259d676b2b137afd2ff5"><code>9d3073c</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/19b71cf1de8afe6f69a3171d8a5a28086790e49b"><code>19b71cf</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/2a0ca021d95e23f1d1c0b5fe858b0b56f71fe0ba"><code>2a0ca02</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/ff539f6dc21137fbeb3f0867f07069cbce45c15f"><code>ff539f6</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/9fdb3bc0f9bfab5269b4f3045595e62323da5d3a"><code>9fdb3bc</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/d53a05614893e8d1bbfdab50b42c19435e6bd065"><code>d53a056</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/420052fcac3fc672be17fe655667dfbdbd35a2cc"><code>420052f</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/28ce924276eeca492e6a360e5482ed20c2785ef6"><code>28ce924</code></a>]:</p> <ul> <li><code>@mastra/core</code><a href="https://github.com/1"><code>@1</code></a>.64.0</li> </ul> </li> </ul> <h2>1.17.3-alpha.2</h2> <h3>Patch Changes</h3> <ul> <li> <p>Update README to include accurate, up-to-date information (<a href="https://redirect.github.com/mastra-ai/mastra/pull/22858">#22858</a>)</p> </li> <li> <p>Updated dependencies [<a href="https://github.com/mastra-ai/mastra/commit/e983f749873189f767f509eb33d1a3596c0f1c74"><code>e983f74</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/cedc25d8c2dec005d8b10b6ce2d36feef1162ff0"><code>cedc25d</code></a>, <a href="https://github.com/mastra-ai/mastra/commit/9fdb3bc0f9bfab5269b4f3045595e62323da5d3a"><code>9fdb3bc</code></a>]:</p> <ul> <li><code>@mastra/core</code><a href="https://github.com/1"><code>@1</code></a>.64.0-alpha.7</li> </ul> </li> </ul> <h2>1.17.3-alpha.1</h2> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/mastra-ai/mastra/commit/871bdaa5957c2b680cd043a728b1b7fec4101512"><code>871bdaa</code></a> chore: version - exit prerelease mode</li> <li><a href="https://github.com/mastra-ai/mastra/commit/21e22d156fa61c3619a11ae1b1ddf8447b752f8e"><code>21e22d1</code></a> fix(<code>@mastra/docker</code>): kill processes in the container PID namespace and reap z...</li> <li><a href="https://github.com/mastra-ai/mastra/commit/ba200359a93f10d711e0fc14984d549fd59b7dfa"><code>ba20035</code></a> chore: version packages</li> <li><a href="https://github.com/mastra-ai/mastra/commit/d3841b96d7e6dc4ec42d9fc8a4000deb34b7f590"><code>d3841b9</code></a> feat(mcp): expose Mastra server APIs as MCP tools (<a href="https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp/issues/23077">#23077</a>)</li> <li><a href="https://github.com/mastra-ai/mastra/commit/cfc365b486f47764435a9c3ce03065dafeef720c"><code>cfc365b</code></a> chore: version packages</li> <li><a href="https://github.com/mastra-ai/mastra/commit/c3d00db279a95c7dcba0f767704a2bb6544b7b29"><code>c3d00db</code></a> docs: add usage examples and docs breadcrumbs to central primitives (<a href="https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp/issues/23489">#23489</a>)</li> <li><a href="https://github.com/mastra-ai/mastra/commit/a0ad9351eaf8527d1515051ddf3998ee258b9acd"><code>a0ad935</code></a> fix(core): apply delegation result text to failures (<a href="https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp/issues/23000">#23000</a>)</li> <li><a href="https://github.com/mastra-ai/mastra/commit/c19a93b0956f957581931786645d0597efec41eb"><code>c19a93b</code></a> chore: version - exit prerelease mode</li> <li><a href="https://github.com/mastra-ai/mastra/commit/13b28beaa21afde50d2d780200637f5a0fe6474a"><code>13b28be</code></a> test(mcp): run filesystem-server tests from a pinned devDependency (<a href="https://github.com/mastra-ai/mastra/tree/HEAD/packages/mcp/issues/22898">#22898</a>)</li> <li><a href="https://github.com/mastra-ai/mastra/commit/e6de7740694109c5119c5f6a65ed33ce3e9bda7c"><code>e6de774</code></a> chore: version packages</li> <li>Additional commits viewable in <a href="https://github.com/mastra-ai/mastra/commits/@mastra/mcp@1.18.0/packages/mcp">compare view</a></li> </ul> </details> <br /> Updates `ai` from 6.0.303 to 6.0.311 <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/vercel/ai/blob/ai@6.0.311/packages/ai/CHANGELOG.md">ai's changelog</a>.</em></p> <blockquote> <h2>6.0.311</h2> <h3>Patch Changes</h3> <ul> <li>af9972b: fix(ai): stop emitting buffered stream parts after a <code>streamText</code> transform calls <code>stopStream</code></li> </ul> <h2>6.0.310</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [37be196] <ul> <li><code>@ai-sdk/gateway</code><a href="https://github.com/3"><code>@3</code></a>.0.218</li> </ul> </li> </ul> <h2>6.0.309</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [5aa3086]</li> <li>Updated dependencies [c42700c] <ul> <li><code>@ai-sdk/provider-utils</code><a href="https://github.com/4"><code>@4</code></a>.0.61</li> <li><code>@ai-sdk/gateway</code><a href="https://github.com/3"><code>@3</code></a>.0.217</li> </ul> </li> </ul> <h2>6.0.308</h2> <h3>Patch Changes</h3> <ul> <li>739e9f6: Restore raw OpenAI custom-tool input deltas for consumers that forward them to Responses API clients. Mark streamed input with <code>inputEncoding: 'text'</code> so UI clients can display it progressively without JSON parsing. Preserve the encoding when partial UI messages are saved and resumed. Final provider tool-call inputs remain JSON-encoded.</li> <li>Updated dependencies [739e9f6] <ul> <li><code>@ai-sdk/provider</code><a href="https://github.com/3"><code>@3</code></a>.0.19</li> <li><code>@ai-sdk/gateway</code><a href="https://github.com/3"><code>@3</code></a>.0.216</li> <li><code>@ai-sdk/provider-utils</code><a href="https://github.com/4"><code>@4</code></a>.0.60</li> </ul> </li> </ul> <h2>6.0.307</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [d5e7d82]</li> <li>Updated dependencies [0650c06] <ul> <li><code>@ai-sdk/provider-utils</code><a href="https://github.com/4"><code>@4</code></a>.0.59</li> <li><code>@ai-sdk/gateway</code><a href="https://github.com/3"><code>@3</code></a>.0.215</li> </ul> </li> </ul> <h2>6.0.306</h2> <h3>Patch Changes</h3> <ul> <li>Updated dependencies [d9244d1] <ul> <li><code>@ai-sdk/gateway</code><a href="https://github.com/3"><code>@3</code></a>.0.214</li> </ul> </li> </ul> <h2>6.0.305</h2> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/vercel/ai/commit/de615928053b34cc78e8057e0eb228016b0411a6"><code>de61592</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23569">#23569</a>)</li> <li><a href="https://github.com/vercel/ai/commit/af9972b6d4926a9c376703d55fa0f40399c2887c"><code>af9972b</code></a> [v6.0] fix(ai): stop emitting buffered stream parts after stopStream (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23567">#23567</a>)</li> <li><a href="https://github.com/vercel/ai/commit/a07566e63afae7986340119c915145a596bbcb8e"><code>a07566e</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23553">#23553</a>)</li> <li><a href="https://github.com/vercel/ai/commit/f0300b871300e9353426808800cca43f07011dd1"><code>f0300b8</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23417">#23417</a>)</li> <li><a href="https://github.com/vercel/ai/commit/68ad66ceb983078e6e3e3d8ce1442c111cb15c42"><code>68ad66c</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23409">#23409</a>)</li> <li><a href="https://github.com/vercel/ai/commit/739e9f62585d862a1b9f7275412cbe5f9600f433"><code>739e9f6</code></a> fix(openai): preserve raw custom-tool deltas with explicit UI input encoding ...</li> <li><a href="https://github.com/vercel/ai/commit/67f30382d8d0961f370a22a6d5d5fcce73c3a123"><code>67f3038</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23351">#23351</a>)</li> <li><a href="https://github.com/vercel/ai/commit/b83ef50aae69e3c58025fa48df61f35b487ae696"><code>b83ef50</code></a> Backport: chore: fix timeout issue for global declaration test (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23349">#23349</a>)</li> <li><a href="https://github.com/vercel/ai/commit/64e07d4bca19b51c30fb7827fa110a600a96c219"><code>64e07d4</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23268">#23268</a>)</li> <li><a href="https://github.com/vercel/ai/commit/886e59d27fad69ba39dc515fd811b3c9e44f14ba"><code>886e59d</code></a> Version Packages (<a href="https://github.com/vercel/ai/tree/HEAD/packages/ai/issues/23121">#23121</a>)</li> <li>Additional commits viewable in <a href="https://github.com/vercel/ai/commits/ai@6.0.311/packages/ai">compare view</a></li> </ul> </details> <br /> Updates `@anthropic-ai/sdk` from 0.133.0 to 0.135.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/anthropics/anthropic-sdk-typescript/releases">@anthropic-ai/sdk's releases</a>.</em></p> <blockquote> <h2>sdk-v0.135.0</h2> <h3>Features</h3> <ul> <li><strong>api:</strong> add between_tools to thinking types in model capabilities</li> <li><strong>api:</strong> add the speed parameter and usage.speed to Messages</li> <li><strong>api:</strong> return a Console organization's usage-tier spend cap as a read-only spend limit</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>client:</strong> close streams dropped without being read to the end</li> <li><strong>client:</strong> keep an unread JSONL response open while it is held</li> </ul> <h3>Chores</h3> <ul> <li><strong>ci:</strong> speed up breaking change detection</li> <li><strong>docs:</strong> describe headers on Managed Agents and telemetry endpoints</li> </ul> <h3>Documentation</h3> <ul> <li><strong>api:</strong> note that some models need a beta header to use speed</li> </ul> <h2>sdk-v0.134.0</h2> <h3>Features</h3> <ul> <li> <p><strong>api:</strong> add execution_identity to Managed Agents agents</p> </li> <li> <p><strong>api:</strong> add organization_type_not_supported error to spend limit lists</p> </li> <li> <p><strong>api:</strong> add telemetry destination test endpoint</p> </li> <li> <p><strong>api:</strong> add telemetry destinations to the Admin API</p> </li> <li> <p><strong>client:</strong> add native support for OpenTelemetry tracing</p> <p>If your app registers a global tracer provider, the SDK will create spans with it after upgrading, and they'll be exported with the rest of your traces. Requests will also get trace context headers from the global propagator. To disable, pass <code>openTelemetry: false</code> to the client or set <code>ANTHROPIC_OPEN_TELEMETRY=false</code>. Learn more in the <a href="https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk">documentation</a>.</p> </li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>api:</strong> rename telemetry destination test response model</li> <li><strong>client:</strong> close an unread stream that was dropped while tracing is on</li> <li><strong>client:</strong> don't follow redirects on token requests</li> <li><strong>client:</strong> treat proxy-authorization as a sensitive header</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>streaming:</strong> tolerate unknown event types in MessageStream and BetaMessageStream</li> <li><strong>streaming:</strong> stop throwing "Unexpected event order" for an event before message_start</li> <li><strong>streaming:</strong> yield events that arrive before message_start when iterating MessageStream and BetaMessageStream</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/anthropics/anthropic-sdk-typescript/blob/main/CHANGELOG.md">@anthropic-ai/sdk's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.134.0...sdk-v0.135.0">0.135.0</a> (2026-10-15)</h2> <h3>Features</h3> <ul> <li><strong>api:</strong> add between_tools to thinking types in model capabilities</li> <li><strong>api:</strong> add the speed parameter and usage.speed to Messages</li> <li><strong>api:</strong> return a Console organization's usage-tier spend cap as a read-only spend limit</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>client:</strong> close streams dropped without being read to the end</li> <li><strong>client:</strong> keep an unread JSONL response open while it is held</li> </ul> <h3>Chores</h3> <ul> <li><strong>ci:</strong> speed up breaking change detection</li> <li><strong>docs:</strong> describe headers on Managed Agents and telemetry endpoints</li> </ul> <h3>Documentation</h3> <ul> <li><strong>api:</strong> note that some models need a beta header to use speed</li> </ul> <h2><a href="https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.133.0...sdk-v0.134.0">0.134.0</a> (2026-10-14)</h2> <h3>Features</h3> <ul> <li> <p><strong>api:</strong> add execution_identity to Managed Agents agents</p> </li> <li> <p><strong>api:</strong> add organization_type_not_supported error to spend limit lists</p> </li> <li> <p><strong>api:</strong> add telemetry destination test endpoint</p> </li> <li> <p><strong>api:</strong> add telemetry destinations to the Admin API</p> </li> <li> <p><strong>client:</strong> add native support for OpenTelemetry tracing</p> <p>If your app registers a global tracer provider, the SDK will create spans with it after upgrading, and they'll be exported with the rest of your traces. Requests will also get trace context headers from the global propagator. To disable, pass <code>openTelemetry: false</code> to the client or set <code>ANTHROPIC_OPEN_TELEMETRY=false</code>. Learn more in the <a href="https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk">documentation</a>.</p> </li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>api:</strong> rename telemetry destination test response model</li> <li><strong>client:</strong> close an unread stream that was dropped while tracing is on</li> <li><strong>client:</strong> don't follow redirects on token requests</li> <li><strong>client:</strong> treat proxy-authorization as a sensitive header</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>streaming:</strong> tolerate unknown event types in MessageStream and BetaMessageStream</li> <li><strong>streaming:</strong> stop throwing "Unexpected event order" for an event before message_start</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/04a4c28c70de498d6d0e930e43edb5edb9ac545e"><code>04a4c28</code></a> release: 0.135.0</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/69dbe62f377e3a12e14ef087d139bbdad410cb64"><code>69dbe62</code></a> Merge pull request <a href="https://redirect.github.com/anthropics/anthropic-sdk-typescript/issues/935">#935</a> from anthropics/synced/published</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/b61a531fcc3de9a45e9330257655fa798b33ab53"><code>b61a531</code></a> feat(helpers): retry a rate-limited fast fallback at standard speed (<a href="https://redirect.github.com/anthropics/anthropic-sdk-typescript/issues/943">#943</a>)</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/38d0ab4b8e1c9bb763e32362f98f277de86aecb8"><code>38d0ab4</code></a> feat(api): add between_tools to thinking types in model capabilities</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/366b53b2dbf205fce164a532dd919f64e5f40186"><code>366b53b</code></a> chore(docs): describe headers on Managed Agents and telemetry endpoints</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/ca50812ed769a40510bb2f9e5e232e95cdd376f1"><code>ca50812</code></a> docs(api): note that some models need a beta header to use speed</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/03f6012e6d6d25fe5402674a4f525f7c52a27a22"><code>03f6012</code></a> fix(helpers): honor speed overrides from fallback entries when streaming (<a href="https://redirect.github.com/anthropics/anthropic-sdk-typescript/issues/942">#942</a>)</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/88bf0348f005aff54d6de535b3684c8ec7876b3b"><code>88bf034</code></a> docs(changelog): shorten the OpenTelemetry tracing note (<a href="https://redirect.github.com/anthropics/anthropic-sdk-typescript/issues/941">#941</a>)</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/7c807a0d94de53d8484dca989fdd50977a29ae2e"><code>7c807a0</code></a> fix(client): close streams dropped without being read to the end</li> <li><a href="https://github.com/anthropics/anthropic-sdk-typescript/commit/64758f63568ecf53dae4e2573d4d0af6a69a8341"><code>64758f6</code></a> feat(api): add the speed parameter and usage.speed to Messages</li> <li>Additional commits viewable in <a href="https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.133.0...sdk-v0.135.0">compare view</a></li> </ul> </details> <br /> Updates `@google/genai` from 2.28.0 to 2.30.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/googleapis/js-genai/releases">@google/genai's releases</a>.</em></p> <blockquote> <h2>v2.30.0</h2> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.29.1...v2.30.0">2.30.0</a> (2026-10-14)</h2> <h3>Features</h3> <ul> <li><strong>interactions:</strong> add gemini-4-argon to Model enum (<a href="https://github.com/googleapis/js-genai/commit/8a3c3074a6688cc12c9f30c2366089cd94622fd6">8a3c307</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li>clear continuation state and preserve prompt feedback when continuation hop returns no candidates (<a href="https://github.com/googleapis/js-genai/commit/e63d1f184811ac2ddec2a17e206e5a6c1c79ed6e">e63d1f1</a>)</li> <li>fix the grounding metadata merging for automatic continuation in generate content and generate content stream (<a href="https://github.com/googleapis/js-genai/commit/6bfba8790e9a3a663884db10290b2909b7ca4b0b">6bfba87</a>)</li> <li>make continuation streams retry dropped hops, stop on prompt_feedback, and keep real errors in generate_content (<a href="https://github.com/googleapis/js-genai/commit/6bdc0d98709df070c935e812bb126dcffaedff97">6bdc0d9</a>)</li> <li>type GeminiNextGen signatures with public, importable names (<a href="https://github.com/googleapis/js-genai/commit/ad3fb891c91b8b57fee846f3319442150d77d622">ad3fb89</a>)</li> </ul> <h2>v2.29.1</h2> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.29.0...v2.29.1">2.29.1</a> (2026-10-13)</h2> <h3>Bug Fixes</h3> <ul> <li>concatenate output_text across multi-step model responses in a turn (<a href="https://github.com/googleapis/js-genai/commit/567cc8a1731850d3d3f22c0f9cf3b0b3664cf79f">567cc8a</a>)</li> </ul> <h2>v2.29.0</h2> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.28.0...v2.29.0">2.29.0</a> (2026-10-13)</h2> <h3>Features</h3> <ul> <li>accumulate streaming continuation usage metadata and expose initialPromptTokenCount (<a href="https://github.com/googleapis/js-genai/commit/dbc961f0294e3fdc9d8fc277b9921bada8f97b90">dbc961f</a>)</li> <li>Add <code>continuation_token</code> to the Interactions <code>interaction.status_update</code> event. (<a href="https://github.com/googleapis/js-genai/commit/a93776c9479d69d280ca1d2fc9784a8cebc5417a">a93776c</a>)</li> <li>Add a CONTINUATION_REQUIRED Interaction status (<a href="https://github.com/googleapis/js-genai/commit/754f71f0f90d0355f32f100a1c338b008a1c89e1">754f71f</a>)</li> <li>add billable token counts fields (<a href="https://github.com/googleapis/js-genai/commit/839ffc25de12a47a66db10d236d53d59d97d0530">839ffc2</a>)</li> <li>Add startOffset/endOffset to Transcription and interimTranscriptTimestampEnabled to RealtimeInputConfig (<a href="https://github.com/googleapis/js-genai/commit/bdbf1560751d333c6391ca5b4a29799af2baef3c">bdbf156</a>)</li> <li>Add usage in InteractionStatusUpdate events (<a href="https://github.com/googleapis/js-genai/commit/8892aeace095b90805890e0fd5cfa027d87bbc70">8892aea</a>)</li> <li>automatically consume the continuation token (<a href="https://github.com/googleapis/js-genai/commit/98637d1f60dd5a02d978aa354d576ce160b5c65c">98637d1</a>)</li> <li><strong>cli:</strong> update Speakeasy generator to v2.948.0, bump CLI to v0.4.2, and apply CLI overlay fixes (<a href="https://github.com/googleapis/js-genai/commit/22d53ec2f7dc94416fac20bbbf68585712c527c3">22d53ec</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li>clear intermediate CONTINUATION finishReason in streaming continuation (<a href="https://github.com/googleapis/js-genai/commit/22706af4f7d770a64df2aa0557011549380d2350">22706af</a>)</li> <li>do not record incomplete continuation stream turns in curated chat history (<a href="https://github.com/googleapis/js-genai/commit/81c3c49bd2a86c300b23693327df41382f94e535">81c3c49</a>)</li> <li><strong>gemini-api-cli:</strong> remove unsupported 2.5 and 1.6 models from Interactions model options and CLI examples (<a href="https://github.com/googleapis/js-genai/commit/1002720893eef0663d020312da552c64d7c5e65e">1002720</a>)</li> <li><strong>js:</strong> do not set initial prompt token count for requests that do not use automatic consumption of continuation token (<a href="https://github.com/googleapis/js-genai/commit/0885fb917cba113fcbe4294731473de5be1fc55f">0885fb9</a>)</li> <li><strong>js:</strong> fix streaming continuation edge cases (stale token, AbortError, initialPromptTokenCount) (<a href="https://github.com/googleapis/js-genai/commit/f3d10a68f010825ebf07b13857012ac78ea92546">f3d10a6</a>)</li> <li>Raise default HTTP timeouts so long-running requests aren't killed client-side (<a href="https://github.com/googleapis/js-genai/commit/10e850c21ab87d00c7e63e7c8afa592c5d407f0e">10e850c</a>)</li> <li>resume streaming generation from the latest checkpoint continuation token on mid-stream errors or cutoffs (<a href="https://github.com/googleapis/js-genai/commit/625ac2c3a663719e57efbf51055a36b1e27a86d8">625ac2c</a>)</li> <li>Update EnvironmentConfig.env schema to map keys to EnvVar or string. (<a href="https://github.com/googleapis/js-genai/commit/8478e1222137e288fa3eaedbc5111bd090dbf400">8478e12</a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/googleapis/js-genai/blob/main/CHANGELOG.md">@google/genai's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.29.1...v2.30.0">2.30.0</a> (2026-10-14)</h2> <h3>Features</h3> <ul> <li><strong>interactions:</strong> add gemini-4-argon to Model enum (<a href="https://github.com/googleapis/js-genai/commit/8a3c3074a6688cc12c9f30c2366089cd94622fd6">8a3c307</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li>clear continuation state and preserve prompt feedback when continuation hop returns no candidates (<a href="https://github.com/googleapis/js-genai/commit/e63d1f184811ac2ddec2a17e206e5a6c1c79ed6e">e63d1f1</a>)</li> <li>fix the grounding metadata merging for automatic continuation in generate content and generate content stream (<a href="https://github.com/googleapis/js-genai/commit/6bfba8790e9a3a663884db10290b2909b7ca4b0b">6bfba87</a>)</li> <li>make continuation streams retry dropped hops, stop on prompt_feedback, and keep real errors in generate_content (<a href="https://github.com/googleapis/js-genai/commit/6bdc0d98709df070c935e812bb126dcffaedff97">6bdc0d9</a>)</li> <li>type GeminiNextGen signatures with public, importable names (<a href="https://github.com/googleapis/js-genai/commit/ad3fb891c91b8b57fee846f3319442150d77d622">ad3fb89</a>)</li> </ul> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.29.0...v2.29.1">2.29.1</a> (2026-10-13)</h2> <h3>Bug Fixes</h3> <ul> <li>concatenate output_text across multi-step model responses in a turn (<a href="https://github.com/googleapis/js-genai/commit/567cc8a1731850d3d3f22c0f9cf3b0b3664cf79f">567cc8a</a>)</li> </ul> <h2><a href="https://github.com/googleapis/js-genai/compare/v2.28.0...v2.29.0">2.29.0</a> (2026-10-13)</h2> <h3>Features</h3> <ul> <li>accumulate streaming continuation usage metadata and expose initialPromptTokenCount (<a href="https://github.com/googleapis/js-genai/commit/dbc961f0294e3fdc9d8fc277b9921bada8f97b90">dbc961f</a>)</li> <li>Add <code>continuation_token</code> to the Interactions <code>interaction.status_update</code> event. (<a href="https://github.com/googleapis/js-genai/commit/a93776c9479d69d280ca1d2fc9784a8cebc5417a">a93776c</a>)</li> <li>Add a CONTINUATION_REQUIRED Interaction status (<a href="https://github.com/googleapis/js-genai/commit/754f71f0f90d0355f32f100a1c338b008a1c89e1">754f71f</a>)</li> <li>add billable token counts fields (<a href="https://github.com/googleapis/js-genai/commit/839ffc25de12a47a66db10d236d53d59d97d0530">839ffc2</a>)</li> <li>Add startOffset/endOffset to Transcription and interimTranscriptTimestampEnabled to RealtimeInputConfig (<a href="https://github.com/googleapis/js-genai/commit/bdbf1560751d333c6391ca5b4a29799af2baef3c">bdbf156</a>)</li> <li>Add usage in InteractionStatusUpdate events (<a href="https://github.com/googleapis/js-genai/commit/8892aeace095b90805890e0fd5cfa027d87bbc70">8892aea</a>)</li> <li>automatically consume the continuation token (<a href="https://github.com/googleapis/js-genai/commit/98637d1f60dd5a02d978aa354d576ce160b5c65c">98637d1</a>)</li> <li><strong>cli:</strong> update Speakeasy generator to v2.948.0, bump CLI to v0.4.2, and apply CLI overlay fixes (<a href="https://github.com/googleapis/js-genai/commit/22d53ec2f7dc94416fac20bbbf68585712c527c3">22d53ec</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li>clear intermediate CONTINUATION finishReason in streaming continuation (<a href="https://github.com/googleapis/js-genai/commit/22706af4f7d770a64df2aa0557011549380d2350">22706af</a>)</li> <li>do not record incomplete continuation stream turns in curated chat history (<a href="https://github.com/googleapis/js-genai/commit/81c3c49bd2a86c300b23693327df41382f94e535">81c3c49</a>)</li> <li><strong>gemini-api-cli:</strong> remove unsupported 2.5 and 1.6 models from Interactions model options and CLI examples (<a href="https://github.com/googleapis/js-genai/commit/1002720893eef0663d020312da552c64d7c5e65e">1002720</a>)</li> <li><strong>js:</strong> do not set initial prompt token count for requests that do not use automatic consumption of continuation token (<a href="https://github.com/googleapis/js-genai/commit/0885fb917cba113fcbe4294731473de5be1fc55f">0885fb9</a>)</li> <li><strong>js:</strong> fix streaming continuation edge cases (stale token, AbortError, initialPromptTokenCount) (<a href="https://github.com/googleapis/js-genai/commit/f3d10a68f010825ebf07b13857012ac78ea92546">f3d10a6</a>)</li> <li>Raise default HTTP timeouts so long-running requests aren't killed client-side (<a href="https://github.com/googleapis/js-genai/commit/10e850c21ab87d00c7e63e7c8afa592c5d407f0e">10e850c</a>)</li> <li>resume streaming generation from the latest checkpoint continuation token on mid-stream errors or cutoffs (<a href="https://github.com/googleapis/js-genai/commit/625ac2c3a663719e57efbf51055a36b1e27a86d8">625ac2c</a>)</li> <li>Update EnvironmentConfig.env schema to map keys to EnvVar or string. (<a href="https://github.com/googleapis/js-genai/commit/8478e1222137e288fa3eaedbc5111bd090dbf400">8478e12</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/googleapis/js-genai/commit/1de87f896cfdb6a091d65ab81c7d68c3f2d54382"><code>1de87f8</code></a> chore(main): release 2.30.0 (<a href="https://redirect.github.com/googleapis/js-genai/issues/2058">#2058</a>)</li> <li><a href="https://github.com/googleapis/js-genai/commit/14086e639acb309b87857ef118e0fac25b68386c"><code>14086e6</code></a> chore(cli): update Speakeasy OpenAPI generator to v2.948.9</li> <li><a href="https://github.com/googleapis/js-genai/commit/433a33ad16992efeae215901ac345c67a0735ab4"><code>433a33a</code></a> chore: internal change</li> <li><a href="https://github.com/googleapis/js-genai/commit/6bdc0d98709df070c935e812bb126dcffaedff97"><code>6bdc0d9</code></a> fix: make continuation streams retry dropped hops, stop on prompt_feedback, a...</li> <li><a href="https://github.com/googleapis/js-genai/commit/6bfba8790e9a3a663884db10290b2909b7ca4b0b"><code>6bfba87</code></a> fix: fix the grounding metadata merging for automatic continuation in generat...</li> <li><a href="https://github.com/googleapis/js-genai/commit/ad3fb891c91b8b57fee846f3319442150d77d622"><code>ad3fb89</code></a> fix: type GeminiNextGen signatures with public, importable names</li> <li><a href="https://github.com/googleapis/js-genai/commit/8a3c3074a6688cc12c9f30c2366089cd94622fd6"><code>8a3c307</code></a> feat(interactions): add gemini-4-argon to Model enum</li> <li><a href="https://github.com/googleapis/js-genai/commit/f2ad2c1107d9ed0b09aa0a8116f2c093a7628a45"><code>f2ad2c1</code></a> chore: Skip the code coverage workflow on push/PR (manual trigger only).</li> <li><a href="https://github.com/googleapis/js-genai/commit/e63d1f184811ac2ddec2a17e206e5a6c1c79ed6e"><code>e63d1f1</code></a> fix: clear continuation state and preserve prompt feedback when continuation ...</li> <li><a href="https://github.com/googleapis/js-genai/commit/2e083a76600f37755dab8c4947dd45881f05f33a"><code>2e083a7</code></a> chore(main): release 2.29.1 (<a href="https://redirect.github.com/googleapis/js-genai/issues/2052">#2052</a>)</li> <li>Additional commits viewable in <a href="https://github.com/googleapis/js-genai/compare/v2.28.0...v2.30.0">compare view</a></li> </ul> </details> <br /> Updates `@langchain/core` from 1.2.17 to 1.2.18 <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>.2.18</h2> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/11956">#11956</a> <a href="https://github.com/langchain-ai/langchainjs/commit/93d62b008e13e10f28724a5ab09ab6eda584f1cb"><code>93d62b0</code></a> Thanks <a href="https://github.com/hntrl"><code>@hntrl</code></a>! - Require langsmith >=0.11.0 to include the restored NullableHeaders type declarations.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/11822">#11822</a> <a href="https://github.com/langchain-ai/langchainjs/commit/d3e6fe66a5f902fa615f076ca71d9541f1291166"><code>d3e6fe6</code></a> Thanks <a href="https://github.com/dqbd"><code>@dqbd</code></a>! - Add explicit agent address support to <code>LangChainTracer</code>, inherit project and address destinations together, and delegate default destination resolution to the LangSmith SDK.</p> </li> <li> <p><a href="https://redirect.github.com/langchain-ai/langchainjs/pull/11150">#11150</a> <a href="https://github.com/langchain-ai/langchainjs/commit/cea15cf9ef5216125b24f23bb5ad06b7c1a91b33"><code>cea15cf</code></a> Thanks <a href="https://github.com/mdnanocom"><code>@mdnanocom</code></a>! - fix(core): defer tool call chunk collapsing in AIMessageChunk to fix O(n²) streaming aggregation</p> <p><code>AIMessageChunk</code> eagerly re-ran <code>collapseToolCallChunks</code> in its constructor on every streamed delta <code>concat</code>, re-parsing all accumulated tool args each time — O(n²) over a stream, which can block the event loop for seconds on long tool-call streams. Collapsing now runs lazily, once, on first read of <code>tool_calls</code> / <code>invalid_tool_calls</code>.</p> </li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain-ai/langchainjs/commit/ba363b15a90eb9c8f1d3d718b3bcc4fbf7b61bac"><code>ba363b1</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11937">#11937</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/93d62b008e13e10f28724a5ab09ab6eda584f1cb"><code>93d62b0</code></a> fix: require langsmith with restored header declarations (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11956">#11956</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/57d0e02b2256da85dec6e5062d3e1bde2271c5de"><code>57d0e02</code></a> fix(google): support Argon thinking and preserve streaming usage (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11940">#11940</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/73a739c871fb8191976848482052c1a8b30c68ba"><code>73a739c</code></a> feat(aws): map Bedrock thinking tokens to output_token_details.reasoning (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11">#11</a>...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/227f01c818996bf107dbcedc3e0ffa1620b7719e"><code>227f01c</code></a> feat(langchain): support HITL respond decisions (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11498">#11498</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/d3e6fe66a5f902fa615f076ca71d9541f1291166"><code>d3e6fe6</code></a> feat(core): add explicit address support to LangChainTracer (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11822">#11822</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/cea15cf9ef5216125b24f23bb5ad06b7c1a91b33"><code>cea15cf</code></a> fix(core): defer tool call chunk collapsing in AIMessageChunk to fix O(n²) st...</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/20c38bf7f3bda43f6aa2376e5783b3b1197a787d"><code>20c38bf</code></a> fix: bump vulnerable transitive dependencies (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11920">#11920</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/b2c113459e362121564e7c5924e1e530f87a92c5"><code>b2c1134</code></a> chore: version packages (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11881">#11881</a>)</li> <li><a href="https://github.com/langchain-ai/langchainjs/commit/aa1b519f91b2f466e7bbce21d5b67361224bc6a9"><code>aa1b519</code></a> docs: fix typo in README (<a href="https://redirect.github.com/langchain-ai/langchainjs/issues/11443">#11... _Description has been truncated_ --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: jkomyno <alberto@composio.dev>