{"version":"2.1.318","anchor":"forked-agents-accept-a-pinnedeffort-and-end-subagent-repl-se","canonical_anchor":"forked-agents-accept-a-pinnedeffort-and-end-subagent-repl-se","heading":"Forked agents can be given a fixed effort level and close their own REPL sessions","tier":"internal","area":"Agents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/forked-agents-accept-a-pinnedeffort-and-end-subagent-repl-se","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### Forked agents can be given a fixed effort level and close their own REPL sessions\n\nForked agents can now be started with a pinned effort level, and their REPL session is closed when they finish if a check allows it\n\n**Unclear.** It is unclear when the REPL clean-up runs, so whether subagents actually use their own REPL sessions in this release is not settled.\n\n**What**\n\nA forked agent is a separate copy of Claude that Claude Code starts to handle part of a task. Claude Code can now start one with a pinned effort, a fixed level of how hard the model thinks, which is passed through to the agent's requests.\n\nWhen a forked agent finishes, Claude Code can now also close the agent's REPL session (an interactive environment where code is run step by step). This happens only when an internal check allows it. Before, clean-up only stopped the agent's shell tasks. If closing the REPL session fails, Claude Code logs `REPL session end failed (continuing teardown)` and carries on cleaning up.\n\nThe separate relay-fork switch is still off unless it is switched on remotely. At its most recent reading, taken before this release, the flag server returned it on for this site's account and for the anonymous baseline.\n\n**Why**\n\nThis suggests subagents (helper copies of Claude working on part of a task) may run REPL sessions of their own, which now get closed properly when the agent ends.\n\n- Flag `tengu_wild_tome`: Off by default, switched on for this account (read for one account on one subscription tier against v2.1.318; this account: on, anonymous baseline: on, compiled default: off) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Agents\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}