Skip to content

v1.1.0

Choose a tag to compare

View all tags
@dwash96 dwash96 released this 08 Aug 05:00
· 285 commits to main since this release
v1.1.0
33493d1
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's Changed

MR: #632
Full Changelog: v1.0.5...v1.1.0

Addresses:

Includes:

  • Add module and heuristics for popular provider caching and reasoning semantic auto configuration with best match resolution to be less dependent on LiteLLM keeping their global model config in sync with the world changing
  • Fix bug were model request parsing mutates underlying conversation history
  • Fix bug in parallel tool calling when LLM API does not use 0-based indexing for tool call numbers
  • Display turn level and whole session cache hit rate
Assets 2
Loading