> The model writes less user-facing text between tool calls, especially at higher effort. Set thinking.display to "updates" (beta) to receive the progress updates it does write, and remove any prompt line that tells it to hold findings for the final response.
I love when I make a request or ask a question, and Claude Code immediately queues up a dozen tool calls to edit files instead of explaining what it wants to do or why, despite repeated constant reminding that I will not approve tool calls without context and reasoning
Ive been through this a lot myself, and thats why im building this tool called kaplira, it is an control layer for ai coding agents. it does not allow ai agents to touch files outside a determined scope, it learns as u code, learns from past mistakes, regressions, it injects cirurgical memories into the ai agents. u can download it for free at kaplira.com
