v0.63.1

ruvnet/RuViewv0.63.1Jul 22, 2026by github-actions[bot]

AI Summary

This patch release focuses on improving the reliability of Composio task execution and tool-call parsing to prevent execution loops and handle garbled model output more gracefully.

Key Highlights

Composio actions avoid 'first call bounce' and execute immediately when arguments match the resolved contract
Tool-call parsing hardened to recover from Kimi-K2-family garbled output
Schema validation improvements for `integrations_agent` actions

New Features

Improved Composio task execution resilience
Enhanced tool-call parsing robustness
Fixes for text-mode per-action execution loops

Full Release Notes

# The Composio Reliability Upgrade

This patch release tightens up Composio task execution and makes tool-calls more resilient, so your agents can get to work faster and recover more gracefully when model output gets messy. 🚀

## Highlights

### Composio task execution & schema validation 🧩
Composio actions triggered via `integrations_agent` now avoid a frustrating “first call bounce” and can execute immediately when the model’s arguments already match the resolved live contract. This prevents loops like “fetch my latest email” stalling before `GMAIL_FETCH_EMAILS` ever runs, especially along the text-mode per-action path. ([#5132](https://github.com/tinyhumansai/openhuman/pull/5132)) — Thank you @M3gA-Mind!

### Tool-call parsing robustness (Kimi recovery) 🛠️
Tool-call parsing has been hardened to better recover from Kimi-K2-family garbled tool-call bodies. The normalization now strips the `<|\"|>` argument-quote sentinels and rewrites malformed `NAME{unquoted-json}` into a canonical form, improving resilience when model output is slightly corrupted. ([#5132](https://github.com/tinyhumansai/openhuman/pull/5132)) — Thank you @M3gA-Mind!

## Contributor Credits

Thanks to everyone who contributed to v0.63.1: @M3gA-Mind and @github-actions[bot].

## Full Compare

https://github.com/tinyhumansai/openhuman/compare/v0.63.0...v0.63.1