diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,10 @@ # Changelog -## Unreleased +## 0.4.1.0 — 2026-09-30 + +- Give `ReAct`'s `ProtocolAuto` its own tool-calling check instead of reusing `Shikumi.Adapter.capabilityFor`. Behavior is unchanged: only `openai` over Chat Completions or Responses and `anthropic` over Messages use provider-native tool calling. CLI models, which `shikumi` 0.4.1.0 now treats as schema-native, still use the prompt tool protocol, because Baikai's CLI providers drop tools. Raise the internal `shikumi` bound to `^>=0.4.1.0` so this check never pairs with an older `shikumi`. + +- Move the dependency on `mori://shinzui/baikai/packages/baikai` to `>=0.7.1.0 && <0.8` and widen the `effectful` bound to `>=2.6 && <2.8`, so both effectful 2.6 and 2.7 are supported (effectful 2.7 needs `baikai-effectful` 0.4.0.2, effectful 2.6 needs 0.4.0.1). Bounds only; no source changed. ## 0.4.0.0 — 2026-09-08 diff --git a/shikumi-tools.cabal b/shikumi-tools.cabal --- a/shikumi-tools.cabal +++ b/shikumi-tools.cabal @@ -1,10 +1,10 @@ -cabal-version: 3.4 -name: shikumi-tools -version: 0.4.0.0 +cabal-version: 3.4 +name: shikumi-tools +version: 0.4.1.0 synopsis: Typed tools and ReAct agents for shikumi LM programs (EP-11) -category: AI +category: AI description: Typed tools and multi-step ReAct agents for shikumi. A @Tool i o@ is an ordinary function over record types whose JSON-Schema argument shape is Generic-derived @@ -19,20 +19,26 @@ inspectable shikumi program. Every test runs against a deterministic mock LM with no network. -license: BSD-3-Clause -author: Nadeem Bitar -maintainer: nadeem@gmail.com -build-type: Simple +license: BSD-3-Clause +author: Nadeem Bitar +maintainer: nadeem@gmail.com +build-type: Simple extra-doc-files: CHANGELOG.md common common-options ghc-options: - -Wall -Wcompat -Widentities -Wincomplete-uni-patterns - -Wincomplete-record-updates -Wredundant-constraints - -fhide-source-paths -Wmissing-export-lists -Wpartial-fields + -Wall + -Wcompat + -Widentities + -Wincomplete-uni-patterns + -Wincomplete-record-updates + -Wredundant-constraints + -fhide-source-paths + -Wmissing-export-lists + -Wpartial-fields -Wmissing-deriving-strategies - default-language: GHC2024 + default-language: GHC2024 default-extensions: DeriveAnyClass DuplicateRecordFields @@ -40,8 +46,8 @@ OverloadedStrings library - import: common-options - hs-source-dirs: src + import: common-options + hs-source-dirs: src exposed-modules: Shikumi.Agent.History Shikumi.Agent.ReAct @@ -61,31 +67,34 @@ Shikumi.Tool.Web build-depends: - , aeson >=2.2 && <2.3 - , baikai >=0.7.0.0 && <0.8 - , base >=4.20 && <5 - , bytestring >=0.11 && <0.13 - , containers >=0.6 && <0.9 - , directory >=1.3 && <1.4 - , effectful >=2.5 && <2.7 - , filepath >=1.4 && <1.6 - , generic-lens >=2.2 && <2.4 - , http-client >=0.7 && <0.8 - , http-client-tls >=0.3 && <0.5 - , http-types >=0.12 && <0.13 - , lens ^>=5.3 - , process >=1.6 && <1.7 - , regex-tdfa >=1.3 && <1.4 - , shikumi ^>=0.4.0.0 - , text ^>=2.1 - , vector >=0.13 && <0.14 + aeson >=2.2 && <2.3, + baikai >=0.7.1.0 && <0.8, + base >=4.20 && <5, + bytestring >=0.11 && <0.13, + containers >=0.6 && <0.9, + directory >=1.3 && <1.4, + effectful >=2.6 && <2.8, + filepath >=1.4 && <1.6, + generic-lens >=2.2 && <2.4, + http-client >=0.7 && <0.8, + http-client-tls >=0.3 && <0.5, + http-types >=0.12 && <0.13, + lens ^>=5.3, + process >=1.6 && <1.7, + regex-tdfa >=1.3 && <1.4, + shikumi ^>=0.4.1.0, + text ^>=2.1, + vector >=0.13 && <0.14, test-suite shikumi-tools-test - import: common-options - type: exitcode-stdio-1.0 + import: common-options + type: exitcode-stdio-1.0 hs-source-dirs: test - main-is: Main.hs - ghc-options: -threaded -with-rtsopts=-N + main-is: Main.hs + ghc-options: + -threaded + -with-rtsopts=-N + other-modules: AcceptanceSpec AgentHistorySpec @@ -97,13 +106,13 @@ FsSpec ProgramOfThoughtSpec ProtocolSpec + RLMExample + RLMSpec ReActSessionExample ReActSpec ResponsesIntegrationSpec ResponsesSchemaSpec RestrictedSpec - RLMExample - RLMSpec SchemaSpec SessionSpec ShellSpec @@ -112,21 +121,21 @@ WebSpec build-depends: - , aeson - , baikai >=0.7.0.0 && <0.8 - , base - , bytestring - , containers - , directory - , effectful - , filepath - , generic-lens - , lens - , shikumi ^>=0.4.0.0 - , shikumi-cache ^>=0.2.0.0 - , shikumi-testing ^>=0.1.0.0 - , shikumi-tools ^>=0.4.0.0 - , tasty - , tasty-hunit - , text - , vector + aeson, + baikai >=0.7.1.0 && <0.8, + base, + bytestring, + containers, + directory, + effectful, + filepath, + generic-lens, + lens, + shikumi ^>=0.4.1.0, + shikumi-cache ^>=0.2.0.0, + shikumi-testing ^>=0.1.0.0, + shikumi-tools ^>=0.4.0.0, + tasty, + tasty-hunit, + text, + vector, diff --git a/src/Shikumi/Agent/ReAct.hs b/src/Shikumi/Agent/ReAct.hs --- a/src/Shikumi/Agent/ReAct.hs +++ b/src/Shikumi/Agent/ReAct.hs @@ -16,8 +16,9 @@ -- inspectable, and composes with every other shikumi program and combinator. -- -- Two tool /protocols/ are supported behind one internal interface ('ProtocolImpl'), --- selected by a 'ToolProtocol' value ('ProtocolAuto' resolves per model via --- "Shikumi.Adapter"'s 'capabilityFor'): a provider-native function-calling path +-- selected by a 'ToolProtocol' value ('ProtocolAuto' resolves per model from a +-- tool-calling table of first-party HTTP hosts, kept separate from +-- "Shikumi.Adapter"'s schema-only 'Shikumi.Adapter.capabilityFor'): a provider-native function-calling path -- (baikai @Context.tools@ + @Options.toolChoice@, parsing @AssistantToolCall@ blocks) -- and a prompt-based fallback that renders an explicit action grammar and parses the -- model's text. The loop body is protocol-agnostic. @@ -93,7 +94,7 @@ import Effectful (Eff, (:>)) import Effectful.Error.Static (Error, catchError, throwError) import GHC.Generics (Generic) -import Shikumi.Adapter (ModelCapability (..), ToPrompt (toPrompt), attachSchema, capabilityFor) +import Shikumi.Adapter (ToPrompt (toPrompt), attachSchema) import Shikumi.Agent.History (ReActSession) import Shikumi.Agent.History qualified as H import Shikumi.Compaction (CompactionConfig (..), compactTail, defaultCompactionConfig, usageExceedsWindow) @@ -361,9 +362,23 @@ resolveProtocolKind :: ToolProtocol -> Model -> ToolProtocol resolveProtocolKind ProtocolNative _ = ProtocolNative resolveProtocolKind ProtocolPrompt _ = ProtocolPrompt -resolveProtocolKind ProtocolAuto m = case capabilityFor m of - NativeSchema -> ProtocolNative - PromptFallback -> ProtocolPrompt +resolveProtocolKind ProtocolAuto m + | nativeToolCalling m = ProtocolNative + | otherwise = ProtocolPrompt + +-- | Whether a model's transport executes provider-native function calling. +-- Deliberately not "Shikumi.Adapter"'s 'Shikumi.Adapter.capabilityFor': that +-- answers /schema/ enforcement, which baikai's CLI providers (@claude@, @codex@) +-- support, while those same providers silently drop @Context.tools@. Only the +-- first-party HTTP hosts are native here; CLI, third-party and @Custom@ hosts +-- use the prompt protocol. +nativeToolCalling :: Model -> Bool +nativeToolCalling m = + (m ^. #provider, m ^. #api) + `elem` [ ("openai", B.OpenAIChatCompletions), + ("openai", B.OpenAIResponses), + ("anthropic", B.AnthropicMessages) + ] -- | Build the concrete 'ProtocolImpl' for a model, choosing the native or prompt -- renderers from 'resolveProtocolKind'. diff --git a/test/ProtocolSpec.hs b/test/ProtocolSpec.hs --- a/test/ProtocolSpec.hs +++ b/test/ProtocolSpec.hs @@ -61,6 +61,12 @@ _ -> assertFailure "both protocols should succeed", testCase "ProtocolAuto picks prompt for a CLI model" $ resolveProtocolKind ProtocolAuto (emptyModel & #api .~ AnthropicMessagesCli) @?= ProtocolPrompt, + testCase "ProtocolAuto picks prompt for a codex CLI model" $ + resolveProtocolKind ProtocolAuto (emptyModel & #provider .~ "codex-cli" & #api .~ OpenAICompletionsCli) @?= ProtocolPrompt, + testCase "ProtocolAuto picks prompt for a claude CLI model (schema-native, not tool-native)" $ + resolveProtocolKind ProtocolAuto (emptyModel & #provider .~ "claude-cli" & #api .~ AnthropicMessagesCli) @?= ProtocolPrompt, + testCase "ProtocolAuto picks prompt for a third-party Chat Completions host" $ + resolveProtocolKind ProtocolAuto (emptyModel & #provider .~ "deepseek" & #api .~ OpenAIChatCompletions) @?= ProtocolPrompt, testCase "ProtocolAuto picks native for a native-capable model" $ resolveProtocolKind ProtocolAuto (emptyModel & #provider .~ "openai" & #api .~ OpenAIChatCompletions) @?= ProtocolNative, testCase "native turn with two tool calls executes both in order" $ do