{"version":"2.1.280","anchor":"automodeagent-safety-evaluation-cache-is-cleared-when-the-v","canonical_anchor":"automodeagent-safety-evaluation-cache-is-cleared-when-the-v","heading":"Automode\/agent safety-evaluation cache is cleared when the verdict isn't 'continue', gated to first-party API usage","tier":"internal","area":"Auto Mode","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/automodeagent-safety-evaluation-cache-is-cleared-when-the-v","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Automode\/agent safety-evaluation cache is cleared when the verdict isn't 'continue', gated to first-party API usage\n\nSafety-monitor cache for automated agents is cleared whenever the verdict isn't 'continue'\n\n**What**\n\nClaude Code can run agents in an automated mode where a safety monitor checks each action an agent takes. That monitor keeps a cached state (called `mintedOnContinue`) tracking that an agent was cleared to keep going. Now, whenever the monitor's decision on an action is anything other than \"continue,\" that cached state for the agent is explicitly cleared. This applies when using Anthropic's first-party API (behind a gate referred to internally as `Ey`).\n\n**Why**\n\nThis stops a stale \"cleared to continue\" state from lingering after the safety monitor has actually flagged or stopped an action, so a later check can't mistakenly rely on outdated permission.\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}