v0.2.107
stablePublished Jul 20, 2026
NEW11FIX2PERF1
Changelog
0.2.107 — 2026-07-20
Features
- Stop hooks can now keep the agent running by feeding feedback back to the model instead of ending the turn.
- Custom models can now authenticate using rotating tokens fetched from a command, similar to credential helpers.
- Feedback now includes author details when provided, helping with follow-up.
- Sessions can now resume across hosts by mirroring transcripts to external storage like S3.
- Sessions can now be imported and resumed from mirrored state across hosts.
- Auto mode now continues after classifier blocks by telling the agent the reason, escalating only after repeated denials.
- Session storage can now flush after every frame (eager mode) instead of only at turn end.
Bug Fixes
- Ctrl+B now backgrounds running commands; Ctrl+G toggles the tasks pane.
- OAuth popups in live preview now redirect correctly after login.
- Git status shown to the model at startup now includes unstaged and untracked files.
- Tool descriptions now stay correct when parameter names are randomized.
- Minimal mode now shows full reasoning in scrollback and collapses successful lookup results to one-line headers.
- Empty commands like true or bare echo now remind the model to stop and wait for background work instead of spinning.
Performance
- Recap summaries after idle now load much faster by reusing the previous turn's cached context.