{"version":"2.1.268","anchor":"sandbox-system-prompt-text-rewritten-to-describe-allowed-dom","canonical_anchor":"sandbox-system-prompt-text-rewritten-to-describe-allowed-dom","heading":"Sandbox system-prompt text rewritten to describe allowed_domains \/ auto-mode network review","tier":"soon","area":"Sandbox Network","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268\/e\/sandbox-system-prompt-text-rewritten-to-describe-allowed-dom","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268","markdown":"### Sandbox system-prompt text rewritten to describe allowed_domains \/ auto-mode network review\n\nSandbox instructions shown to the model were rewritten to explain listing needed hosts and reacting to blocked-host violations\n\n**Unclear.** Whether this rewritten guidance is actually shown to any given user depends on the same unread tengu_flickering_rain setting.\n\n**What**\n\nThe sandbox instructions built into the system prompt (under a '`command sandbox`' heading) were substantially rewritten for when the new network-list capability is active. The model is now told to list every host a command needs, that the sandbox is applied per command at the operating-system level, and to check a `<sandbox_violations>` block for any denied hosts. If a host was denied, the instructions say to re-run the command with that host added to `allowed_domains` when in auto mode. Separately, the wording used when sandboxing is fully disabled by policy was softened from a blanket prohibition to language that tells the model to ask the user instead.\n\n**Why**\n\nThis gives the model concrete steps to follow when a sandboxed command is blocked from reaching a network host, instead of leaving it to guess how to retry.\n\n- Area: Sandbox Network\n- Names: `allowed_domains`\n- Tier: Nothing to try yet\n- Useful: 3\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}