Follow Discord
Sweep 30 Oct 2026 · 01:02Z Build v2.1.314 532 read Stable v2.1.308 Latest v2.1.314 Next v2.1.314 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.314 ·

Workflow agents' results are now always reviewed when a run ends

When a workflow agent finishes, Claude Code now reviews its report of the tools it used, even if it never used the handback tool

Under the hood Internal Changes
JSON All of v2.1.314
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
WorkflowsArea: what it touches
Internal ChangesKind: in v2.1.314,
Internal ChangesSection of the release

Unclear It is not clear what switches this handback behaviour on for an agent.

What

A workflow agent is a helper agent that Claude Code runs as one step of a larger task. Some hand their result back through a special handback tool. Claude Code now gives that tool only to agents it confirms are meant to hand results back, and it keeps track of each structured result they return. When the run ends, Claude Code reviews the agent's report of the tools it used, even if the agent never used the handback tool. Before, that review came only from the handback tool itself.

Why

This changes how the results of workflow helper agents get checked.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not clear what switches this handback behaviour on for an agent.

See this entry in the whole of v2.1.314 →

Feedback