{"version":"2.1.293","anchor":"background-agent-task-status-can-now-say-whether-an-agent-ca","canonical_anchor":"background-agent-task-status-can-now-say-whether-an-agent-ca","heading":"Background agent status now says whether the agent can be continued","tier":"internal","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293\/e\/background-agent-task-status-can-now-say-whether-an-agent-ca","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293","markdown":"### Background agent status now says whether the agent can be continued\n\nStatus updates about background agents now tell Claude whether that agent can be continued, based on the tools available\n\n**What**\n\nWhen Claude starts a subagent (a helper that works on part of a task) in the background, Claude Code sends Claude status updates about it. Those updates now include whether the agent can be continued, worked out from the set of tools available.\n\nReading a background task's output file is now also allowed for two more kinds of task: one standing in for an agent during startup, and one running in a pool. Before, reading was allowed based only on the tool check.\n\n**Why**\n\nClaude is now told whether a finished subagent can be picked up again, which may let it carry on that agent's work instead of starting a new one.\n\n- Area: Subagents\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}