← News
Release

qm v0.1.10

QM 0.1.10 is a broad release: admin-managed models, grown-up sandboxes, and a web app polish pass. Admins can now manage models directly: add a model and its metadata gets looked up for you, each one…

Originally published on github.com →

QM 0.1.10 is a broad release: admin-managed models, grown-up sandboxes, and a web app polish pass.

  • Admins can now manage models directly: add a model and its metadata gets looked up for you, each one is verified before it can be enabled, and tasks resume on whichever native runtime you pick.
  • Sandboxes grew up. They're independent resources now, with sensible defaults, one set of tools, and native provider recovery. We qualify them by actually running code on each provider.
  • Big files just work: uploads go straight to object storage and can resume if interrupted, and attachments stick around in completed chat history.
  • Safer screening in Auto posture. We decide what counts as external from the egress proxy instead of trusting command text, only external tool results get screened, and anything we can't account for fails closed.
  • The web app got a real polish pass across chat, inbox, settings, and the sidebar. Chat search is much faster, live thinking stays in the transcript, and long pinned prompts collapse.
  • More control over sessions: choose isolated or open sharing, sign in by email on remembered browsers you can revoke, and portal sessions now default to 7 days rolling with a 30 day cap.
  • For operators: the services consolidate into three workloads, PostgreSQL transaction pooling is supported, admin logs get a paginated Errors view, and Linear webhooks are verified.

What's Changed

New Contributors

Full Changelog: https://github.com/yc-software/qm/compare/v0.1.9...v0.1.10