{"version":"2.1.318","anchor":"subagent-lazy-fetch-reports-why-a-transcript-read-went-over","canonical_anchor":"subagent-lazy-fetch-reports-why-a-transcript-read-went-over","heading":"More detail in usage data when cloud subagent transcripts fail to load","tier":"internal","area":"Telemetry","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/subagent-lazy-fetch-reports-why-a-transcript-read-went-over","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### More detail in usage data when cloud subagent transcripts fail to load\n\nUsage data about loading cloud subagent transcripts now records their size, the event count, and which limit was exceeded\n\n**What**\n\nA subagent is a helper that Claude starts to handle part of a task, and its transcript is the record of what it did. When Claude Code loads a subagent transcript from the cloud, the usage data it sends now records two more things:\n\n- Successful loads: the size and the number of events.\n\n- Loads that hit a limit: which limit was passed, whether size, event count or time.\n\nThis changes only what is reported, not how loading works.\n\n**Why**\n\nIt helps the people running the cloud service find out why transcripts fail to load.\n\n- Area: Telemetry\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}