Group of 3 Use it now Notable
Administrators can now cap the maximum reasoning-effort level, overall or per model, and Claude Code enforces it against any effort request
What
- A new managed-settings key,
maxEffortLevel, lets an administrator restrict the maximum reasoning-effort level allowed. - The effective cap is computed by combining a top-level
maxEffortLevelwith any per-modelmodelSettings.<model>.maxEffortLeveloverrides across all loaded settings files, taking the lowest applicable value. - Any explicit effort request, from
/effort,/model, the--effortflag, theCLAUDE_CODE_EFFORT_LEVELenvironment variable, or a model's default, is clamped to this cap. - Effort-level resolution (whether
effort,max_effort, orxhigh_effortapply for a given model) now checks this new setting first, before falling back to the older logic based on the model's id.
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.
Names in the bundlemaxEffortLevel
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Confirmed since
Anthropic's documentation has since written up maxEffortLevel, on What's new.
Also this week: pop any **Claude Code Desktop pane** out into its own window and dock it back later; the **`maxEffortLevel`** setting caps the effort level on every provider; and a page that **WebFetch** hasn't finished downloading within …whats-new/index see the edit
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
What secDefault itself configures is not stated in the finding.
Anthropic's documentation agrees
Anthropic's documentation has since written up maxEffortLevel, on What's new.
Anthropic's release notes agree
Added maxEffortLevel setting (top-level or per model under modelSettings): caps the effort level on every provider, including Bedrock…
The name it cites is new in this build
New in this build: maxEffortLevel