{"version":"2.1.310","anchor":"effort-unsupported-error-detection-broadened","canonical_anchor":"effort-unsupported-error-detection-broadened","heading":"Claude Code recognises more errors that mean effort is not supported","tier":"notice","area":"Elsewhere","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.310\/e\/effort-unsupported-error-detection-broadened","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.310","markdown":"### Claude Code recognises more errors that mean effort is not supported\n\nThe check for an API error saying effort is unsupported now matches one more kind of error besides the effort_unsupported message\n\n**Unclear.** What the newly matched kind of error is, and so which models or providers it covers, is not stated.\n\n**What**\n\nEffort is a setting that controls how much reasoning Claude puts into a reply. When the API (the service Claude Code sends requests to) answers that effort is not supported, Claude Code detects this from the error. Before, it only matched an error message containing `effort_unsupported`. It now also matches a second kind of error.\n\n**Why**\n\nIn practice, Claude Code may now recognise and handle an effort-unsupported error in more situations than before.\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}