{"version":"2.1.319","anchor":"auto-mode-refuses-repl-originated-agent-and-message-sends","canonical_anchor":"auto-mode-refuses-repl-originated-agent-and-message-sends","heading":"Auto mode now blocks code that sends tasks or messages to other agents","tier":"notice","area":"Auto Mode","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/auto-mode-refuses-repl-originated-agent-and-message-sends","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Auto mode now blocks code that sends tasks or messages to other agents\n\nIn auto mode, code run through the REPL can no longer send tasks or messages to other agents, because auto mode cannot check that text\n\n**What**\n\nAuto mode is a permission mode in which Claude Code checks each action itself instead of asking you to approve it. The REPL is a place where Claude can write and run code as one step. That code can try to start a sub-agent (a helper agent that takes on part of a task) or send a message to another agent. Auto mode cannot read the task or message text the code passes along, so it now refuses these sends.\n\nWhen this happens, the model is told one of two things:\n\n- Do the work itself, running the pieces side by side with `Promise.all`\n\n- Leave auto mode with Shift+Tab\n\nThe check that catches secrets quoted in shell commands now also tests the command after it has been split into its separate parts.\n\n**Why**\n\nThe model now gets a clear reason when one of these calls is blocked, plus two ways forward. If Claude stops to suggest leaving auto mode, this is the cause.\n\n- Area: Auto Mode\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: yes"}