Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.321 ·

Unreviewed subagent output now comes with a security warning

Claude Code now warns when a subagent's output was not reviewed, with wording that depends on CLAUDE_CODE_USER_DELEGATED_SESSION_DIRECT_API

You'll notice No documentation found Improvements
JSON All of v2.1.321
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
AgentsArea: what it touches
ImprovementsKind: in v2.1.321,
ImprovementsSection of the release

Unclear What else setting CLAUDE_CODE_USER_DELEGATED_SESSION_DIRECT_API changes beyond this warning is not known.

What

A subagent is a helper agent that Claude starts to carry out part of a task. Claude Code now builds a "SECURITY WARNING" saying that a subagent's output is unreviewed. Its wording depends on the environment variable CLAUDE_CODE_USER_DELEGATED_SESSION_DIRECT_API, a setting you can put in your shell before starting Claude Code:

  • With the variable set, the warning says the safety check gave no verdict on the output.
  • Without it, the warning says Claude Code no longer reviews a subagent's output itself.
Why

The warning marks subagent output that has not been checked, so it can be treated with more care. The variable is referred to in many places in this build, which suggests it switches on a distinct way of running a session.

Read from
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 doubtWhat else setting CLAUDE_CODE_USER_DELEGATED_SESSION_DIRECT_API changes beyond this warning is not known.
The name it cites is new in this buildNew in this build: CLAUDE_CODE_USER_DELEGATED_SESSION_DIRECT_API

See this entry in the whole of v2.1.321 →

Feedback