{"version":"2.1.267","anchor":"new-policy-setting-maxeffortlevel","canonical_anchor":"new-policy-setting-maxeffortlevel","heading":"New maxEffortLevel setting caps reasoning effort","tier":"use","area":"Effort","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267\/e\/new-policy-setting-maxeffortlevel","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.267","markdown":"### New maxEffortLevel setting caps reasoning effort\n\nAdministrators can now cap the maximum reasoning-effort level, overall or per model, and Claude Code enforces it against any effort request\n\n**Unclear.** What secDefault itself configures is not stated in the finding.\n\n**What**\n\n- A new managed-settings key, `maxEffortLevel`, lets an administrator restrict the maximum reasoning-effort level allowed.\n\n- The effective cap is computed by combining a top-level `maxEffortLevel` with any per-model `modelSettings.<model>.maxEffortLevel` overrides across all loaded settings files, taking the lowest applicable value.\n\n- Any explicit effort request, from `\/effort`, `\/model`, the `--effort` flag, the `CLAUDE_CODE_EFFORT_LEVEL` environment variable, or a model's default, is clamped to this cap.\n\n- Effort-level resolution (whether `effort`, `max_effort`, or `xhigh_effort` apply for a given model) now checks this new setting first, before falling back to the older logic based on the model's id.\n\n**Why** This lets organizations enforce a ceiling on how much reasoning effort, and therefore cost and latency, Claude Code can use, regardless of what an individual user or model requests.\n\n- Area: Effort\n- Names: `maxEffortLevel`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 3\/5"}