0.87.0

stepfun-ai/Step-Audio0.87.0Sep 25, 2026by takahirom

Upgrading?

AI Summary

Reduces non-AI execution time by cutting down the number of view hierarchy fetches per step to 3-4 from 11-13, and ensures elements and UI tree come from a single fetch.

Key Highlights

  • Fewer view hierarchy fetches per step
  • Single hierarchy fetch for step elements and UI tree

New Features

  • Reduced screen reading latency
  • Single hierarchy fetch per step
  • Improved connection retry logic

Full Release Notes

Each step now reads the device screen with far fewer view hierarchy fetches, which cuts non-AI time per step. On an Android emulator, reading the screen went from about 1.4s to 0.2–0.4s per step, and hierarchy fetches went from 11–13 to 3–4 per step.

## Fewer Hierarchy Fetches per Step (#452, #453)

- Reads no longer check the connection with an extra hierarchy fetch first. A read that fails reconnects and is retried. Actions keep the up-front check, so a tap or key press that failed part way is not repeated blindly.
- A step's elements, UI tree and focused element now come from one hierarchy fetch, so they always describe the same frame.

## What's Changed
* Reconnect on a failed device read instead of probing before every read by @takahirom in https://github.com/takahirom/arbigent/pull/452
* Read a step's elements, tree and focus from one hierarchy fetch by @takahirom in https://github.com/takahirom/arbigent/pull/453


**Full Changelog**: https://github.com/takahirom/arbigent/compare/0.86.0...0.87.0

Related Repositories