@ai-sdk/workflow
@ai-sdk/workflow is a sub-module in the Vercel AI SDK ecosystem for workflow orchestration. It enables developers to chain multiple AI invocation steps in a structured manner, supporting state management, conditional branching, and multi-step reasoning, with native integration into the Vercel edge runtime and streaming response system.
Core Facts
The sole change in @ai-sdk/workflow 2.0.68 is upgrading the core dependency ai to 7.0.136.
The main changes in @ai-sdk/togetherai@3.0.51 are focused on dependency upgrades and contain no breaking changes.
A patch version update (1.0.104 → 1.0.105) signifies backward-compatible bug fixes or dependency updates, without introducing breaking changes.
Timeline (last 90 days)
@ai-sdk/workflow patch versions appear frequently, and most of them are not fixing its own business defects but rather aligning dependencies with the release cadence of the core package.
The workflow package itself has no code changes; the version number bump is to align the dependency tree.
After the core package is upgraded, if the workflow package does not follow suit, a runtime error due to protocol mismatch may occur.
Version 3.0.40 contains documentation maintenance commit e729d58, which updates README.md to unify formatting and avoid duplicate content.
For developers using @ai-sdk/workflow in production, before upgrading they should confirm whether the changes in the ai package 7.0.152 touch APIs in use, and run the critical paths of the workflow once in a test environment.
The publish timestamp is 23 Oct 19:40.
@ai-sdk/workflow released version 2.0.84, which is a patch-level update.
@ai-sdk/workflow has entered the 2.0.x series, indicating that this workflow abstraction is relatively stable.
For production environments, pure dependency patches can usually be upgraded directly, but it is recommended to run the existing test cases after upgrading, especially integration tests involving tool calls and multi-step orchestration.
This version introduces no new APIs or features; the core work is synchronously updating three dependencies.
40 more timeline events
All Facts (20)
The sole change in @ai-sdk/workflow 2.0.68 is upgrading the core dependency ai to 7.0.136.
90%VerifiedThe main changes in @ai-sdk/togetherai@3.0.51 are focused on dependency upgrades and contain no breaking changes.
90%VerifiedA patch version update (1.0.104 → 1.0.105) signifies backward-compatible bug fixes or dependency updates, without introducing breaking changes.
90%VerifiedThis release record was completed by a GitHub Actions automated workflow and carries an official GitHub verified signature (Verified).
90%VerifiedPatch version updates theoretically contain no breaking changes, making the upgrade risk low.
90%VerifiedThe core content of @ai-sdk/workflow-harness@1.0.101 is a dependency update, synchronously upgrading the underlying dependency @ai-sdk/harness@1.0.101.
90%VerifiedThe upgrade method is to run npm install @ai-sdk/openai@4.0.60.
90%VerifiedIn AI SDK, workflow-harness serves as the runtime scaffold responsible for orchestrating and executing AI workflows, linking multiple AI calls, tool calls, state management, and other steps into a controllable workflow.
90%VerifiedThe Vercel AI SDK adopts a Monorepo single-repository management model, with the core package ai and various framework adapter packages (such as @ai-sdk/vue, @ai-sdk/react, and @ai-sdk/svelte) released in coordination.
90%Verified@ai-sdk/workflow is a sub-package within the Vercel AI SDK ecosystem focused on workflow orchestration
90%Verified@ai-sdk/harness and @ai-sdk/workflow-harness are responsible for providing standardized runtime and validation environments for AI workflows.
85%VerifiedIf a project has both ai and @ai-sdk/workflow pinned, both should be updated together to avoid type or runtime errors caused by version mismatches.
80%Verified@ai-sdk/workflow provides a declarative API for describing directed task graphs, managing asynchronous call ordering, intermediate state passing, and error retry logic
80%VerifiedThe release of @ai-sdk/workflow@2.0.77 was completed automatically by the github-actions bot, contains 3 commits, was merged into the main branch, and has commit hash be27bec.
75%VerifiedIn the AI SDK's layered design, the core package ai provides framework-agnostic capabilities (model invocation, streaming response parsing, tool call orchestration, message state management, etc.).
75%VerifiedWhen upgrading @ai-sdk/vue, you should also check the changelog of the ai package, because the release notes of framework adapter layers usually only say "Updated dependencies", while the actual behavior changes are recorded in the core package.
75%VerifiedThe commit is signed with GPG key ID B5690EEEBB952194 and has been verified.
75%VerifiedEven a patch version upgrade can indirectly pull in new versions of deep dependencies, so it is recommended to run tests in a lock-file environment.
75%VerifiedWhen a foundational package such as @ai-sdk/provider-utils that is depended upon by multiple packages is updated, Changeset automatically marks the packages that depend on it for a patch version bump, which is why @ai-sdk/valibot publishes a new version even though its own code has not changed.
75%VerifiedThe commit hashes involved in this update include 3f6852a, 6317504, 3cb2dcd, and ccf98e7.
75%