{"version":"2.1.281","anchor":"per-tool-call-memory-measurement-helper","canonical_anchor":"per-tool-call-memory-measurement-helper","heading":"Per-tool-call memory measurement helper","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/per-tool-call-memory-measurement-helper","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Per-tool-call memory measurement helper\n\nA new helper measures how much memory Claude Code's process gains or loses during each tool call\n\n**Unclear.** The finding does not say whether the helper is used yet or where its measurements go.\n\n**What**\n\nA new helper measures memory use around a tool call (one action Claude takes, such as running a command). It records the change in:\n\n- total memory held by the process\n\n- memory used for data\n\n- memory used outside that data area\n\nIf a reading fails, it logs a note and skips that measurement.\n\n**Why**\n\nIt can show which tool calls use a lot of memory, and a failed reading does not interrupt anything."}