Meta data for slots

The really new thing for this release is that all slots exposes meta data, inputs, outputs, and a friendly description, that can be automatically traversed, and consumed for whatever reasons you have.

Support for "upload only" file attachments

To avoid paying inference for upload invocations

Better creation of AI functions

v22.9.8

Update Version.cs

Bug fixes in some 2/3 AI functions related to code-gen

v22.9.7

Update Version.cs

Minor timeout issue for Hyperlambda gen workflow

v22.9.6

b

Workflow for "tool-gen"

v22.9.5

Update Version.cs

Cancellation tokens support

To stop "long lasting job"

Hyperlambda "immediate" mode

Plus several other prompt compression techniques to reduce costs.

Better dream prompt

v22.9.2

Update Version.cs

Context compression ++

This release focuses a lot on cost reductions, and implements "dreaming" among other things, which is rearranging context memory during memory pressure. This probably slashes down your consecutive input tokens by 95% or something, reducing memory pressure, merging rules, removing conflicts, and gets rid of irrelevant text.

It works by as the context reaches 80% of its max amount of messages a "dream prompt" is executed to clean up the context. Inspired by Anthropic's CC leak some 2 months ago.