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

Claude Code v2.1.234 ·

Plugin eval runs are isolated from project settings and take prompts over stdin

Plugin eval prompts now go over stdin and runs ignore project settings, so long prompts survive intact.

You'll notice Improvements
JSON All of v2.1.234
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Plugin EvalsArea: what it touches
ImprovementsKind: in v2.1.234,
ImprovementsSection of the release
What

Each eval case's prompt is now written to the child process's standard input instead of being passed as a command-line argument, so long or shell-awkward prompts survive intact. The runner also passes --setting-sources user, so project and local settings cannot perturb a run.

Details
  • The child is spawned with stdio: ["pipe", "pipe", "pipe"]; errors writing to stdin are ignored.
  • Model, allowed tools and appended system prompt are now passed in = form.
  • The --ablation help text was rewritten: the default is the with-without comparison whenever a plugin resolves by name or from the target path, and under that mode graders marked with-only signal that the plugin fired rather than counting toward the score.
Evidence

stdio: ["pipe", "pipe", "pipe"], Run a no-plugin baseline arm and report the score delta

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

Read from
Names in the bundle--setting-sources user

See this entry in the whole of v2.1.234 →

Feedback