{"version":"2.1.193","anchor":"trust-dialog-enforcement-for-settings-permissions","canonical_anchor":"trust-dialog-enforcement-for-settings-permissions","heading":"Trust Dialog Enforcement for Settings Permissions","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.193\/e\/trust-dialog-enforcement-for-settings-permissions","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.193","markdown":"### Trust Dialog Enforcement for Settings Permissions\n\n**What**\n\nPermission allow-rules and additional directory grants from `.claude\/settings.json` and `.claude\/settings.local.json` are now silently ignored when the workspace has not yet been trusted via the interactive trust dialog.\n\n**Details**\n\n- Logs to stderr: \"Ignoring N permissions.allow entries from .claude\/settings.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set `projects[\\\"...\\\"].hasTrustDialogAccepted: true` in `~\/.claude\/settings.json`.\"\n- Only applies before the trust dialog has been accepted for this workspace; once trusted, all settings are applied normally.\n- Managed (policy-level) settings are still honored regardless of trust state.\n\n**Evidence**\n\nNew enforcement logic (search for `\"this workspace has not been trusted. Run Claude Code interactively here once\"`)"}