Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.251entry #65

Claude Code v2.1.251 ·

A confined evaluation mode, set by Claude Code on itself

A confined evaluation mode exists that Claude Code only sets on its own eval subprocesses.

Under the hood Notable No documentation found Internal Changes
JSON All of v2.1.251
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
Plugin EvalArea: what it touches
Internal ChangesKind: in v2.1.251,
What probably matters to youSection of the release
What

A new environment variable, CLAUDE_CODE_EVAL_CONFINED, appears 26 times in this build and not at all in the previous one. Claude Code sets it to 1 on subprocesses it spawns for evaluation runs rather than reading it from your settings, so every branch it controls is inert in an ordinary session.

Details
  • Gates git-source teleport refusals, hard-link checks on files, forced permission denials, and network fetch confinement.
  • Added to the three lists of environment variables preserved when spawning privileged worker and background subprocesses.
  • Set alongside CLAUDE_CODE_EVAL_ARTIFACT_STUB_DIR on the same spawn.
Evidence

CLAUDE_CODE_EVAL_CONFINED, v.CLAUDE_CODE_EVAL_CONFINED = "1"

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from
Names in the bundleCLAUDE_CODE_EVAL_CONFINED
How sure we are
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this buildNew in this build: CLAUDE_CODE_EVAL_CONFINED

See this entry in the whole of v2.1.251 →

Feedback