shikumi-eval 0.2.0.2 → 0.2.0.3

raw patch · 4 files changed

+33/−16 lines, 4 filesdep ~aesondep ~baikaidep ~bytestringPVP ok

version bump matches the API change (PVP)

Dependency ranges changed: aeson, baikai, bytestring, containers, effectful, generic-lens, tasty, tasty-golden, vector

API changes (from Hackage documentation)

Files

• CHANGELOG.md +17/−0
• shikumi-eval.cabal +11/−11
• test/EvalFixtures.hs +3/−3
• test/UsageSpec.hs +2/−2

@@ -2,6 +2,23 @@  ## Unreleased +## 0.2.0.3 — 2026-08-29++### Changed++- Every library dependency now carries a PVP upper bound: `aeson`, `bytestring`,+  `containers`, `effectful`, `generic-lens`, `tasty`, `tasty-golden`, `vector`.+  `cabal check` reported these under `missing-upper-bounds`. Without one, a+  future breaking release of a dependency enters a consumer's build plan+  unchecked — which is the failure the bound exists to prevent.++  Each bound admits the version this package is built and tested against and+  stops below the next major.++  `aeson` stops at `<2.3` rather than `<2.4`: baikai-openai 0.5 constrains it to+  `^>=2.2`, so aeson 2.3 is not reachable for this cohort and a wider bound+  would assert compatibility that cannot be exercised here.+ ## 0.2.0.2 — 2026-08-07  ### Changed

@@ -1,6 +1,6 @@ cabal-version:   3.4 name:            shikumi-eval-version:         0.2.0.2+version:         0.2.0.3 synopsis:        Typed evaluation framework for shikumi LM programs (EP-8) category:        AI description:@@ -45,19 +45,19 @@     Shikumi.Eval.Usage    build-depends:-    , aeson-    , baikai        >=0.5      && <0.6+    , aeson         >=2.2      && <2.3+    , baikai        >=0.6      && <0.7     , base          >=4.20     && <5-    , bytestring-    , containers-    , effectful-    , generic-lens+    , bytestring    >=0.11     && <0.13+    , containers    >=0.6      && <0.9+    , effectful     >=2.5      && <2.7+    , generic-lens  >=2.2      && <2.4     , lens          ^>=5.3     , shikumi       ^>=0.3.0.0-    , tasty-    , tasty-golden+    , tasty         >=1.4      && <1.6+    , tasty-golden  >=2.3      && <2.4     , text          ^>=2.1-    , vector+    , vector        >=0.13     && <0.14  test-suite shikumi-eval-test   import:         common-options@@ -79,7 +79,7 @@    build-depends:     , aeson-    , baikai        >=0.5      && <0.6+    , baikai        >=0.6      && <0.7     , base     , effectful     , generic-lens

@@ -36,8 +36,8 @@     Response,     StopReason (..),     doneTerminal,-    _Response,-    _TextContent,+    emptyResponse,+    emptyTextContent,   ) import Control.Lens ((&), (.~), (^.)) import Data.Generics.Labels ()@@ -145,7 +145,7 @@ -- | An assistant 'Response' carrying @t@ as its single text block. mkResponse :: Text -> Response mkResponse t =-  _Response & #message . #content .~ V.singleton (AssistantText (_TextContent & #text .~ t))+  emptyResponse & #message . #content .~ V.singleton (AssistantText (emptyTextContent & #text .~ t))  -- --------------------------------------------------------------------------- -- Mock LLM interpreters

@@ -1,7 +1,7 @@ -- | Usage-accounting tests for both blocking and streamed LM calls. module UsageSpec (tests) where -import Baikai (_Context, _Model, _Options)+import Baikai (emptyContext, emptyModel, emptyOptions) import Effectful (runEff) import Effectful.Concurrent (runConcurrent) import Effectful.Error.Static (runErrorNoCallStack)@@ -48,7 +48,7 @@         result <-           runEff . runPrim $             runStreamLLM events $-              withUsageTotals (stream _Model _Context _Options)+              withUsageTotals (stream emptyModel emptyContext emptyOptions)         snd result @?= usageTotalsPerCall,       testCase "evaluate reports non-zero usage end-to-end" $ do         let ds =