- Checkpointing
- Error Handling
- Process Resumption
Enhancing Long Agent Runs with Steward
Steward ensures long-running agent processes maintain their progress and can recover from failures.
Via Bluesky · @millsdev.bsky.social ↗GitHub Copilot · Software & DevOps
6 workflows that use GitHub Copilot for software & devops work. AI pair programmer and coding agent inside GitHub.
Steward ensures long-running agent processes maintain their progress and can recover from failures.
Via Bluesky · @millsdev.bsky.social ↗An author gave the Copilot coding agent two small changes on their own site; it opened draft PRs and the spacing change was good enough to merge.
Original post ↗A developer found the agent good at context and code, but it pushed to a branch leaving main empty and spent hours checking after being told to proceed.
Original post ↗GitHub engineers used Copilot tools to have agents write most of an 800,000-line Rust rewrite of the Copilot runtime across 128 PRs, fixing a few regressions.
Original post ↗Users report the agent sometimes fails to read terminal output and may undo correct code; workarounds include switching shells.
Original post ↗The author used autopilot to iterate until done and /fleet to split work across parallel subagents, noting overhead on small tasks.
Original post ↗