Grok Build 1.0.38 is out! New release from @SpaceXAI with a bunch of useful improvements:

• Long agent replies in prompt-suggestion transcripts no longer get cut off mid-sentence • read_file permissions for skill/instruction files can now be configured per deployment • Pasted images now survive yank/undo/history recall, with a warning if one can't be sent • Fixed subagent overlays getting stuck on "Cancelling" • Long quoted arguments in permission prompts now wrap instead of clipping • Fixed tool-calling errors involving the inline-only use_tool schema

Small release, but lots of nice quality-of-life fixes.