{"version":"2.1.296","anchor":"relative-subagent-effort-lowerhigher-built-but-gated","canonical_anchor":"relative-subagent-effort-lowerhigher-built-but-gated","heading":"Subagents can be given a relative effort of lower or higher","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296\/e\/relative-subagent-effort-lowerhigher-built-but-gated","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296","markdown":"### Subagents can be given a relative effort of lower or higher\n\nThe Agent tool can take effort \"lower\" or \"higher\" to step a subagent's reasoning effort one level, behind a helper check and tengu_snappy_pelican\n\n**Unclear.** It is not settled whether `CLAUDE_CODE_SNAPPY_PELICAN` is read as true or false or whether any value at all, including 0, switches it on.\n\n**What**\n\nThe Agent tool, which Claude uses to start a subagent (a helper agent that works on part of a task), can now take an `effort` of `lower` or `higher` instead of a fixed effort level. Effort is how much reasoning the model puts in. A relative value moves the subagent one step down or up from the current effort, and the result is passed into the agent's definition.\n\n- The relative value is ignored for forks, remote agents and teammates.\n\n- It is honoured only when a helper check passes. That check needs the subagent model setting to be `inherit`, needs `CLAUDE_CODE_SUBAGENT_MODEL_FORCE` to be unset, and needs no other model override to apply. It then follows the environment variable `CLAUDE_CODE_SNAPPY_PELICAN` if set, and otherwise the `tengu_snappy_pelican` flag.\n\n- When the check fails, the relative effort is quietly removed from the request rather than rejected.\n\n- When the check passes, the Agent tool description adds a hint: give each independent lookup `effort: \"lower\"`, and use `higher` for pieces that need more reasoning.\n\n- Separately, permission-prompt handling for teammate and agent spawns (`canShowPermissionPrompts`) moved to the resume path.\n\nFor `tengu_snappy_pelican`, the flag server returned off for this site's account and for an anonymous baseline, but no reading has been taken under this release. The stock Agent tool description captured under this release is 7,081 characters, unchanged from the previous release.\n\n**Why**\n\nWhen it applies, this lets Claude spend less reasoning on simple parallel lookups and more on hard parts. Without the check passing, a `lower` or `higher` effort is dropped without any warning.\n\n- Flag `tengu_snappy_pelican`: Off in both readings (read for one account on one subscription tier against v2.1.296; this account: off, anonymous baseline: off, 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: Subagents\n- Tier: You'll notice\n- Useful: 5\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no\n- Present in the build but not switched on"}