{"version":"2.1.280","anchor":"new-telemetry-spilled-bytes-on-tool-output-events","canonical_anchor":"new-telemetry-spilled-bytes-on-tool-output-events","heading":"New telemetry: spilled_bytes on tool output events","tier":"internal","area":"Telemetry","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/new-telemetry-spilled-bytes-on-tool-output-events","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### New telemetry: spilled_bytes on tool output events\n\nTool output telemetry now reports spilled_bytes, the size of the truncated portion\n\n**What**\n\nWhen a tool's result is too large and gets \"spilled\" (truncated, with the rest only retrievable by re-running the tool), the telemetry for that event now records `spilled_bytes`: the size of the part that was cut off. This is reported alongside the existing flags that mark output as truncated.\n\n**Why**\n\nThis gives better visibility into how much output is being dropped from large tool results, which is useful for diagnosing when important information may have been truncated away.\n\n- Area: Telemetry\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}