2 people reported
All time, since Oct 1.
Agent thread limit reached below configured concurrency
“Starting/resuming a separate coordinator was rejected with “agent thread limit reached”, although capacity remained.”
Is this your bug? What gets counted gets fixed. Pile on.
Paste this into your agent. It files your report, with your error and version.
I hit this bug: rapsheet.dev/sheets/codex/issues/14184/file Follow it to file my report. Show me the text before you send.
No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends
Completed subagents appear to retain capacity, so spawning or resuming subagents fails in long-running multi-agent workflows.
Is this your bug?
File my report- Where
- multi-agent orchestration
- Error text
collab spawn failed: agent thread limit reached- Versions
- 0.159.0 to 0.160.0
- Platforms
- Linux, Windows
- How bad
- Breaks a normal workflow.