Prerequisites

• I will write this issue in English (see our Language Policy)
• I have searched existing issues to avoid duplicates
• I am using the latest version of oh-my-opencode
• I have read the documentation or asked an AI coding agent with this project's GitHub URL loaded and couldn't find the answer

Bug Description

I am currently downgraded to v3.11.2 this one works perfect.

Problem is with big code base, many subagents doing agentic work/debugging/refactoring all p0 till the noise findings the problem is it doesn't spawn more then 50 subagents. Once total of 50 subagents are spawned it simply stops, and 'reusing'/'respawning' same sessions doesn't work properly.

Steps to Reproduce

On big code base let it audit everything and tell to find all p0 all thorough noise. Let it summen 15 sub agents per provider and then 5 for fixing then when 6 is needed you get the messages/problems. Also quite some will get canceled

Expected Behavior

Like v3.11.2

Actual Behavior

See previous message

Doctor Output

-

Error Logs

Configuration

Additional Context

No response

Operating System

Linux mint (ubuntu based)

OpenCode Version

Latest version