shikumi-eval 0.2.0.1 → 0.2.0.2

raw patch · 3 files changed

+11/−4 lines, 3 filesdep ~baikaiPVP ok

version bump matches the API change (PVP)

Dependency ranges changed: baikai

API changes (from Hackage documentation)

Files

• CHANGELOG.md +7/−0
• shikumi-eval.cabal +3/−3
• test/EvalFixtures.hs +1/−1

@@ -2,6 +2,13 @@  ## Unreleased +## 0.2.0.2 — 2026-08-07++### Changed++- Upgraded the `baikai` dependency to the `0.5` series (`>=0.5 && <0.6`).+  Dependency bounds only — no changes to the exported API.+ ## 0.2.0.1 - 2026-07-20  ### Changed

@@ -1,6 +1,6 @@ cabal-version:   3.4 name:            shikumi-eval-version:         0.2.0.1+version:         0.2.0.2 synopsis:        Typed evaluation framework for shikumi LM programs (EP-8) category:        AI description:@@ -46,7 +46,7 @@    build-depends:     , aeson-    , baikai        >=0.4      && <0.5+    , baikai        >=0.5      && <0.6     , base          >=4.20     && <5     , bytestring     , containers@@ -79,7 +79,7 @@    build-depends:     , aeson-    , baikai        >=0.4      && <0.5+    , baikai        >=0.5      && <0.6     , base     , effectful     , generic-lens

@@ -129,7 +129,7 @@ -- non-zero usage as 'usageResponse'. usageTerminalEvents :: Text -> [AssistantMessageEvent] usageTerminalEvents t =-  [EventDone (doneTerminal Nothing Stop (AssistantMessage (usageResponse t ^. #message)))]+  [EventDone (doneTerminal Nothing Nothing Stop (AssistantMessage (usageResponse t ^. #message)))]  -- | An assistant 'Response' whose body decodes (via the fallback adapter) to a -- record with the given @(field, value)@ sections.