{"version":"2.1.247","anchor":"the-model-is-told-when-command-sandboxing-is-switched-off-mi","canonical_anchor":"the-model-is-told-when-command-sandboxing-is-switched-off-mi","heading":"The model is told when command sandboxing is switched off mid-session","tier":"notice","area":"Sandbox","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.247\/e\/the-model-is-told-when-command-sandboxing-is-switched-off-mi","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.247","markdown":"### The model is told when command sandboxing is switched off mid-session\n\nTurning command sandboxing off mid-session now tells the model the earlier sandbox instructions no longer apply.\n\n**What**\n\nThe sandbox description sent with each turn is re-rendered and compared with the last one in the transcript, so policy changes reach the model while the session is running. When sandboxing is turned off, the description goes empty and the model is told that the command sandbox has been disabled and the earlier instructions no longer apply.\n\n**Details**\n\n- The description is produced only when the Bash tool is available and sandboxing is enabled locally; no remote flag is involved.\n- The disabled notice is a fixed sentence built around the Bash tool name.\n- The attachment type is stripped before token-count caching, as the agent listing delta already was.\n\n**Evidence**\n\n`command sandbox has been disabled. Commands now run without sandbox restrictions; the earlier sandbox instructions no longer apply.`\n\n- Area: Sandbox\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5"}