Release 0.9.1 - #42
Merged
Merged
Conversation
'd/dx <expression> at x=<point>' in the step schema, settled by mpeqs.calculus and refused into silence where it cannot be exact. Passive until a model reaches for it -- measured at zero uses on qwen3:4b, where the calc field carries derivative questions instead -- and shipped for the model generation that does, the same shape as the convert field's early history.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
derivativefield:d/dx <expression> at x=<point>in the step schema, settled bympeqs.calculus(two independent derivative paths that must agree), refused into silence where it cannot be exact —x**x,sin(x), a missing point.Shipped with its usage honestly measured at zero on qwen3:4b, where the
calcfield carries derivative questions instead (the model applies the chain rule itself and hands the arithmetic over — 8/8 on the calculus domain). The field is passive — an empty string costs nothing — and is there for the model generation that reaches for it, the same shape as theconvertfield's early history.Also carries the bench flush fix and the sums-strip refactor (one
exactChiphelper). 461 tests.