{"name":"high","slug":"high","family":"setting","title":"Settings keys","noun":"settings key","description":"The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.","description_source":"entry","described_by":{"version":"2.1.219","anchor":"bundled-claude-api-skill-docs-rewritten-around-opus-5"},"presence":{"first_seen":null,"removed_in":null,"in_current_build":false,"newest_mined":"2.1.309","builds":0,"mined_builds":150,"first_cited":null},"aliases":[],"entries":[{"version":"2.1.293","anchor":"effort-levels-list-exported-alongside-tier-names","heading":"Effort levels are now defined in one shared list","line":"Claude Code now keeps one shared list of effort levels: low, medium, high, xhigh and max","released_at":"2026-10-07 17:18:04","reason":"found in this entry's text"},{"version":"2.1.290","anchor":"medium-and-high-effort-now-map-to-a-different-measured-profi","heading":"\/code-review medium now runs the high-effort recipe on most models","line":"On every model without its own `\/code-review` row, Opus 5.5 included, `medium` now runs the eight-angle high recipe instead of a single pass. `high`, `xhigh` and Opus 5 are unchanged.","released_at":"2026-10-05 18:12:44","reason":"found in this entry's text"},{"version":"2.1.281","anchor":"bundled-model-preset-config-chat-preset-thinking-effort-for","heading":"Bundled model-preset config: chat preset thinking effort for claude-opus-5-5 set to medium","line":"A bundled model config now lists claude-opus-5-5 at medium thinking effort for the chat preset, alongside claude-opus-5 at high","released_at":"2026-09-23 17:01:17","reason":"found in this entry's text"},{"version":"2.1.263","anchor":"effort-medium-nudge-generalized-to-multiple-models-and-effor","heading":"Effort-medium nudge generalized to multiple models and effort levels","line":"The effort-downgrade nudge now works per model instead of just one, but each model needs its own flag turned on.","released_at":"2026-09-06 02:07:58","reason":"found in this entry's text"},{"version":"2.1.248","anchor":"reasoning-effort-levels-and-their-aliases","heading":"Reasoning effort levels and their aliases","line":"Reasoning effort accepts low through max, with med and ultracode as aliases.","released_at":"2026-08-27 20:35:36","reason":"named in this entry, found in this entry's text"},{"version":"2.1.239","anchor":"new-modelsettings-config-key-holds-per-model-effort","heading":"New modelSettings config key holds per-model effort","line":"A new modelSettings config key stores an effort level per model, from low to xhigh.","released_at":"2026-08-21 17:18:54","reason":"found in this entry's text"},{"version":"2.1.224","anchor":"model-catalog-ships-per-effort-cost-multipliers","heading":"Model catalog ships per-effort cost multipliers","line":"Bundled models carry per-effort cost multipliers, though nothing in this build reads them.","released_at":"2026-08-07 01:36:32","reason":"found in this entry's text"},{"version":"2.1.223","anchor":"remote-notifications-from-the-session-stream-are-routed-into","heading":"Remote notifications from the session stream are routed into the local notification queue","line":"Notifications sent from a remote session now actually reach you instead of being silently discarded.","released_at":"2026-08-05 22:51:13","reason":"found in this entry's text"},{"version":"2.1.219","anchor":"bundled-claude-api-skill-docs-rewritten-around-opus-5","heading":"Bundled Claude API skill docs rewritten around Opus 5","line":"The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.","released_at":"2026-07-24 16:11:49","reason":"found in this entry's text"},{"version":"2.1.219","anchor":"new-migrating-to-opus-name-migration-guide-with-two-breaking","heading":"New \"Migrating to {{OPUS_NAME}}\" migration guide with two breaking changes","line":"A migration guide now spells out the two thinking-related changes that break existing API request code.","released_at":"2026-07-24 16:11:49","reason":"found in this entry's text"}],"entries_total":19,"docs":[{"source":"api","path":"about-claude\/api-credits-for-subscribers","title":"api-credits-for-subscribers","documented":false},{"source":"api","path":"about-claude\/glossary","title":"glossary","documented":false},{"source":"api","path":"about-claude\/model-deprecations","title":"model-deprecations","documented":false},{"source":"api","path":"about-claude\/models\/choosing-a-model","title":"choosing-a-model","documented":false},{"source":"api","path":"about-claude\/models\/migration-guide","title":"Or, for the model with the same capabilities and no access approval requirement:","documented":false},{"source":"api","path":"about-claude\/models\/optimizing-for-cost-and-intelligence","title":"optimizing-for-cost-and-intelligence","documented":false},{"source":"api","path":"about-claude\/pricing","title":"pricing","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/content-moderation","title":"content-moderation","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/customer-support-chat","title":"customer-support-chat","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/legal-summarization","title":"legal-summarization","documented":false}],"docs_total":12,"gates":[],"related":[],"url":"https:\/\/changelogs.core-directive.com\/reference\/setting\/high","family_url":"https:\/\/changelogs.core-directive.com\/reference\/setting.json"}