Skip to content

v0.38.5

Choose a tag to compare

View all tags
@michaelneale michaelneale released this 23 Mar 02:02
· 1956 commits to main since this release
v0.38.5
4164e0f
  • Fix chat 400 errors on long conversations: bump small-host context from 8K to 16K
  • Router: stop preferring small models for chat — higher tier always preferred
  • Tighten random model spread window (50→15 points) so weak models are fallbacks, not equal contenders
  • Add Qwen3.5-9B router profile (tier 2)
  • TODO: context-aware routing, retry-on-400 noted as future work
Assets 3
Loading