Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.287 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.287 ·

Server safety verdicts are not reused after a tool's input is rewritten

If a tool's input was rewritten, Claude Code no longer uses the server's classifier verdict for it

Under the hood Internal Changes
JSON All of v2.1.287
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Auto ModeArea: what it touches
Internal ChangesKind: in v2.1.287,
Internal ChangesSection of the release
What

Before Claude Code runs a tool (an action such as editing a file or running a command), a classifier, an automatic check, can judge whether the action is safe to allow. Some of those judgments come from the server. If the tool's input has been rewritten, Claude Code now skips the server's judgment entirely and records the reason as server_input_rewritten.

Why

A judgment made about the original input does not apply to a changed one, so this stops an old verdict from approving an action it never saw.

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 rewrites a tool's input.

See this entry in the whole of v2.1.287 →

Feedback