@ai-sdk/sandbox-vercel

v0.40.5 was automatically released by GitHub Actions with a GPG-verified signature.

In an AI workflow execution framework, the harness layer is responsible for orchestrating task flows, scheduling model calls and tool execution, while the sandbox layer is responsible for providing an isolated and secure environment for code execution.

This patch-level update maintains backward compatibility, allowing existing projects to upgrade without modifying their code.

For projects using loose dependency pinning such as ^1.0.0, performing a regular package manager update is enough to obtain version 1.0.151.

The core change in this update is the sandbox-vercel package synchronously upgrading its dependency @ai-sdk/harness to version 1.0.119.

sandbox-vercel provides code sandbox capabilities specifically for the Vercel platform, allowing code generated by AI models to be executed in an isolated container environment.

@ai-sdk/sandbox-vercel is the sandbox implementation component of the Vercel AI SDK, designed to deeply integrate with the Vercel cloud platform runtime environment and provide code execution isolation capabilities for AI applications deployed on Vercel.

The only patch change in version 1.0.167 comes from commit 177291a, which bumps the template version to invalidate stale templates.

@ai-sdk/sandbox-vercel depends at runtime on preset sandbox templates, which have version state.

@ai-sdk/harness, as a supporting layer, is linked with sandbox-vercel's template mechanism.

The release of @ai-sdk/sandbox-vercel 1.0.162 is only two commits away from the main branch.

The core changes in version 1.0.158 point to the same-version @ai-sdk/harness package.

When upgrading similar patch dependencies, it is advisable to confirm the dependency resolution result in the lockfile and to watch the changelog of @ai-sdk/openai-compatible 2.0.86.

In SDK projects with a monorepo architecture, when the underlying harness module changes, the upper-layer sandbox integration package needs to synchronize dependency versions to ensure consistency of runtime behavior.

If a project uses both @ai-sdk/sandbox-vercel and @ai-sdk/harness, it is recommended to upgrade both to 1.0.151 to avoid sandbox execution anomalies caused by version mismatch.

@ai-sdk/sandbox-vercel is a component in the Vercel AI SDK ecosystem, typically related to code sandboxes and isolated execution environments.

@ai-sdk/harness-pi is a sub-package under the Vercel AI SDK project that is tightly coupled with the core @ai-sdk/harness.

Version 1.0.119 is a patch-level update that involves no breaking changes and introduces no new features.

The two packages sandbox-vercel and harness maintain strict version alignment (both at 1.0.101), reflecting a monorepo lockstep versioning strategy.

The Vercel platform makes extensive use of V8 Isolate technology at its core, enabling @ai-sdk/sandbox-vercel to achieve strong isolation with extremely low cold-start latency.