{"version":"2.1.280","anchor":"artifact-bootprobe-reuse-within-a-single-tool-use","canonical_anchor":"artifact-bootprobe-reuse-within-a-single-tool-use","heading":"Artifact boot\/probe reuse within a single tool use","tier":"internal","area":"Artifacts","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/artifact-bootprobe-reuse-within-a-single-tool-use","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Artifact boot\/probe reuse within a single tool use\n\nClaude Code reuses a recent share-status check instead of re-fetching an artifact within the same tool call\n\n**What**\n\nWhen Claude Code reads an artifact (a file-like object it can boot up and inspect), the internal boot function now accepts a `probeToolUseId`. For plain status-probe reads, it checks a cache of recent probe results keyed by the artifact's slug (short identifier); if the same tool call already probed that artifact recently and the cached version isn't stale, it reuses that result instead of fetching again.\n\n**Why**\n\nThis avoids redundant network fetches when the same artifact is checked more than once within a single tool call, making artifact reads faster and less wasteful.\n\n- Area: Artifacts\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}