{"version":"2.1.285","anchor":"set-max-thinking-tokens-thinking-display-highlights-warnin","canonical_anchor":"set-max-thinking-tokens-thinking-display-highlights-warnin","heading":"set_max_thinking_tokens now checks thinking_display and can refuse part of a request","tier":"notice","area":"Thinking Display","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285\/e\/set-max-thinking-tokens-thinking-display-highlights-warnin","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.285","markdown":"### `set_max_thinking_tokens` now checks `thinking_display` and can refuse part of a request\n\nThe SDK `set_max_thinking_tokens` request now validates `thinking_display`, refuses bad parts, and does not apply the value \"highlights\"\n\n**Unclear.** It is unclear whether this message can be reached in normal use.\n\n**What**\n\nThe SDK (the kit for driving Claude Code from your own program) can send a `set_max_thinking_tokens` request to change the thinking budget (`max_thinking_tokens`) and how thinking is shown (`thinking_display`). The request is now checked as a whole:\n\n- Validation: `max_thinking_tokens` and `thinking_display` are checked together. If the check fails, the reply is `set_max_thinking_tokens: part of the request refused`.\n\n- \"highlights\": asking for `thinking_display` \"highlights\" produces a message that it \"was not applied\", and the display stays as it was. The accepted values are \"summarized\" and \"omitted\".\n\n**Why**\n\nIf your program changes thinking settings, part of a request can now be rejected. Check the reply rather than assuming the new display setting took effect, and use \"summarized\" or \"omitted\".\n\n- Area: Thinking Display\n- Names: `thinking_display`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 4\/5"}