set_max_thinking_tokens gains a new thinking_display option and stricter validation

What

• The thinking_display parameter of the set_max_thinking_tokens tool now accepts a new mode, in addition to summarized and omitted, that shows one short title per stretch of thinking instead of a full prose summary. This mode only works for Claude Code sessions that Anthropic itself hosts; on any other client, the request still succeeds but silently falls back to omitted once the API rejects the value.
• A tightened validation schema now requires max_thinking_tokens to be an integer or null, and thinking_display to be one of a fixed set of values or null, with a matching error message when the input doesn't fit.

Why

The new display mode gives a more scannable view of Claude's thinking on supported sessions, while the stricter validation makes sure invalid values for these settings produce a clear error instead of being silently accepted.