{"version":"2.1.301","anchor":"managed-settings-schema-expanded-settings-read-tool-returns","canonical_anchor":"managed-settings-schema-expanded-settings-read-tool-returns","heading":"Organizations can push more settings remotely, and the output style is now reported","tier":"use","area":"Managed Settings","scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301\/e\/managed-settings-schema-expanded-settings-read-tool-returns","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301","markdown":"### Organizations can push more settings remotely, and the output style is now reported\n\nRemotely managed settings now accept keys such as `effortLevel`, `outputStyle` and `attribution`, and Claude Code's settings report includes the output style\n\n**What**\n\nManaged settings are settings an organization's administrator sets for everyone, and some of them can be pushed to Claude Code remotely. The set of settings accepted this way has grown. It now also includes:\n\n- `alwaysThinkingEnabled`\n\n- `attribution`\n\n- `effortLevel`\n\n- `includeCoAuthoredBy`\n\n- `includeGitInstructions`\n\n- `outputStyle`\n\n- `skillOverrides`\n\n- `switchModelsOnFlag`\n\nUnder `modelSettings`, each model entry can now carry `autoCompactWindow` and `effortLevel`, where before it could carry only `maxEffortLevel`.\n\nAn `attribution` value is rejected if it contains control characters, angle brackets or the text `systemreminder`.\n\nWhen Claude Code reports its current settings, the report now includes the output style: its name, its prompt, and whether it keeps the built-in coding instructions.\n\n**Why**\n\nAdministrators can now set effort, output style, commit attribution and more for their organization without asking each person to change their own settings.\n\n- Area: Managed Settings\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: org\n- Heads-up: no"}