{"version":"2.1.318","anchor":"incremental-request-body-kept-per-subagent","canonical_anchor":"incremental-request-body-kept-per-subagent","heading":"Incremental request reuse now keeps content per subagent and can split near the tools list","tier":"notice","area":"Prompt Caching","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/incremental-request-body-kept-per-subagent","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### Incremental request reuse now keeps content per subagent and can split near the tools list\n\nThe off-by-default request-reuse mode now keeps a saved request for each subagent and can place a block boundary near the end of the tools list\n\n**What**\n\nThe request-reuse mode set by `CLAUDE_CODE_INCREMENTAL_REQUEST_BODY` reuses content from earlier requests to the model. It now does more.\n\n- **Per-subagent reuse.** A subagent is a helper agent Claude starts for part of a job. Before, only the main conversation's saved request was kept. Now a saved request is kept for each subagent, up to a count set remotely through `tengu_vast_frost`; a value of 0 clears them. If the server rejects a reused request because the bytes sent were wrong, that subagent's saved entry is cleared. Requests that reuse a subagent's saved content are tagged `keptForSubagent`. This applies only with `CLAUDE_CODE_INCREMENTAL_REQUEST_BODY` set to 2 and Anthropic's own API. Nothing has been read about how `tengu_vast_frost` is set.\n\n- **Split near the tools list.** When the request is broken into compressed blocks, a new `cutNearToolsEnd` option, controlled by a switch, can place a boundary near the end of the tools section. Before, boundaries were only placed at the messages and system sections. The code that finds saved content was also made more general; it used to match on the exact stored copy.\n\n- Request details sent to Anthropic now include whether the tools-end split was on and whether subagent content was reused, when set.\n\n**Why**\n\nSessions that use many subagents could avoid rebuilding and resending the same large request again and again, which may also help prompt caching. The mode stays off unless you turn it on.\n\n- Area: Prompt Caching\n- Names: `CLAUDE_CODE_INCREMENTAL_REQUEST_BODY`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}