Error messages from model provider during a subagent don't make way to primary agent

[bcardarella]

Description

I hit my weekly Claude limit and the primary agent just continued to spin over and over until I finally checked the subagent and saw the rate limit exceeded error from Anthropic.

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

[github-actions[bot]]

This issue might be a duplicate of existing issues. Please check:

• #777: No errors when usage limit is reached (Claude Pro) - similar issue where usage/rate limit errors don't show proper feedback
• #4089: TUI should show when it is retrying - related issue about displaying inference engine errors in the TUI
• #2512: Opencode stuck in "generating" - related issue where the app appears frozen without error feedback

Feel free to ignore if none of these address your specific case.