---
title: "Unlimited tool rounds and workflow syntax improvements"
date: "2026-03-23"
---

## Unlimited agent tool rounds

Agent stages no longer have an artificial cap on tool rounds per input or subagent turns. Previously, the default limits could cause agents to stop mid-task on complex operations. Both `max_tool_rounds_per_input` and subagent `max_turns` now default to unlimited, so agents run until they complete their work or hit the context window.

## More

<Accordion title="Workflows">
- Condition expressions now support quoted strings: `edge [label="status == \"ready\""]`
- `"end"` and `"End"` are now recognized as exit node identifiers alongside `"END"`
- Edge selection now falls back to the default edge when no condition matches, instead of erroring
- `default_max_retries` attribute renamed to `max_retries` on graph-level stylesheets
- Removed `error_policy` and `k_of_n`/`quorum` attributes from parallel nodes — parallel stages now always wait for all branches
</Accordion>

<Accordion title="Improvements">
- Subagents are now automatically cleaned up when a session closes, preventing orphaned background processes
- All 5xx HTTP status codes from LLM providers are now classified as retryable server errors
- Request timeouts from LLM providers are now treated as non-retryable by default to avoid redundant retries on slow requests
</Accordion>

<Accordion title="Fixes">
- Fixed workflow slug lookup failing for split and resumed runs
- Fixed split run metadata being lost across engine restarts
- Fixed split run lifecycle lookup returning stale state
</Accordion>