Agents
Anthropic adds an 'auto' permission policy that lets the server adjudicate every Managed Agents tool call, plus a terminal attach command
The Claude Platform release notes for 2026-09-10 add `auto` to Managed Agents permission policies: the server evaluates each agent or MCP tool call and runs it, denies it, or pauses for approval, and reports the decision in an `evaluation` field on agent.tool_use and agent.mcp_tool_use events alongside evaluated_permission. The same entry adds `ant beta:sessions connect`, which attaches a terminal to a live Managed Agents session to follow it, send messages, and approve or deny pending tool calls, with `--web` serving the Console session viewer locally. For builders this moves approval routing from client-side plumbing into the API surface.
↳ Follow the thread