OpenAI request fix and stability
Highlights
- Fix OpenAI models failing every turn with invalid_request_error due to a rejected tool schema
- Recover the TUI from a vanished or unresponsive server instead of retrying forever
- Native Muse subscription login and Venice AI provider support
Improvements
- Add configurable Kagi web search backend
- Add persistent /latex rendering controls
- Show live stopwatch, context, and token stats per swarm worker
Fixes
- Honor the configured model for fresh sessions
- Report token counts for OpenAI native compaction
- Reject stale patch hunks before any file changes
- Keep swarm workers alive across reloads
- Fix OAuth credential handoff and stale daemon token recovery
- Fix Kitty images in Zellij
Full changelog: v0.99.0...v0.99.1
Platform availability
- Linux x86_64: available
- Linux aarch64: available
- macOS Apple Silicon: available
- macOS Intel: available
- Windows x86_64: available
- Windows ARM64: available
- FreeBSD x86_64: available
Windows executables are unsigned. Azure Artifact Signing is not configured and the repository's existing WINDOWS_SIGNING_REQUIRED=false override allowed unsigned publication. Windows may show publisher or SmartScreen warnings.