Choose a permission mode changedpermission-modes
Nearest release: v2.1.234, published 8 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+2added
Lines−2removed
From line
390
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits91to this page, all time
The whole hunk
from line 390, old and new numbered
/
from line 390
390390Sandbox network access requests are routed through the classifier rather than allowed by default. As of v2.1.198, the classifier reuses its verdict for a network host and port instead of re-running on every connection:
391391
392392* An allow is reused until new content enters the conversation, at which point that host is checked again
393* In the interactive CLI, a deny is dropped when the turn ends
394* In [non-interactive mode](/docs/en/headless) and Agent SDK sessions there is no turn boundary, so a deny is reused for the rest of the run
393* Claude Code v2.1.234 and later reuse a deny caused by the conversation outgrowing the classifier's context window until new content enters the conversation, or until [compaction](/docs/en/costs#reduce-token-usage) shrinks what the classifier reads. Claude Code then checks the host again
394* A deny that the classifier reached by evaluating the request lasts for the turn in the interactive CLI. In [non-interactive mode](/docs/en/headless) and Agent SDK sessions, Claude Code reuses that deny for the rest of the run, because those sessions have no turn boundary
395395* Changing your permission mode or rules drops all cached verdicts
396396
397397Run `claude auto-mode defaults` to print the full rule lists as JSON. If routine actions get blocked, an administrator can add trusted repos, buckets, and services via the `autoMode.environment` setting: see [Configure auto mode](/docs/en/auto-mode-config).
No line in this hunk matches that.