{"version":"2.1.257","anchor":"advisor-tool-advisormodel-setting","canonical_anchor":"advisor-tool-advisormodel-setting","heading":"Advisor tool \/ advisorModel setting","tier":"soon","area":"Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.257\/e\/advisor-tool-advisormodel-setting","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.257","markdown":"### Advisor tool \/ advisorModel setting\n\nAn internal advisor model concept exists, with sub-agents told never to consult it, and only runs under first-party auth plus a flag.\n\nClaude Code now supports an internal 'advisor' model concept, surfaced through the query context via `getAdvisorSetting`\/`advisorModel`. When the advisor is active and the session isn't compacting, an internal meta message, `Never consult the advisor tool.`, is injected into forked-agent prompts so sub-agents don't recursively call it. The advisor tool itself only runs when first-party auth is combined with a support flag or a remote experiment.\n\n- Flag `tengu_sage_compass2`: Not enough to say (read for one account on one subscription tier against v2.1.257; this account: no value returned, anonymous baseline: no value returned, compiled default: no gate table built for this version) 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: Models\n- Names: `advisorModel`\n- Tier: Nothing to try yet\n- Useful: 5\/5\n- Signal: 5\/5\n- Present in the build but not switched on"}