{"version":"2.1.282","anchor":"model-capability-record-gains-thinking-and-temperature-field","canonical_anchor":"model-capability-record-gains-thinking-and-temperature-field","heading":"Claude Code now records thinking and temperature support for each model","tier":"internal","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.282\/e\/model-capability-record-gains-thinking-and-temperature-field","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.282","markdown":"### Claude Code now records thinking and temperature support for each model\n\nClaude Code's per-model capability details now include whether a model supports extended thinking and whether it accepts a temperature\n\n**Unclear.** It is not clear what uses this record or whether any user sees it.\n\n**What**\n\nClaude Code keeps a record of what each model can do. That record now also notes:\n\n- whether the model supports thinking (reasoning before it answers)\n\n- whether it refuses requests that turn thinking off\n\n- whether it limits effort when thinking is turned off\n\n- whether it accepts a temperature setting, which controls how varied its answers are\n\n**Why**\n\nIn practice, this information may appear in model details or debugging output.\n\n- Area: Models\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}