diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,115 @@ ## [Unreleased] +## [baikai 0.10.0.0] - 2026-10-25 + +### Added + +- `ThinkingNone` (`none`) explicitly requests reasoning off; `Nothing` still + leaves provider defaults untouched. Anthropic compatibility records declare + `supportsThinkingDisabled`; legacy records conservatively default to False. +- Endpoint-specific `NativeCachePolicy` records distinguish modern, legacy and + unsupported native OpenAI cache controls. Policies survive legacy JSON and + catalog refresh; Luna Responses Long has verified 12h base and tier rates. +- Evidence schema 2.8 includes the `none` preference and content-free native + cache controls and input structure. Digest rules and the separation of + requested, translated and observed reasoning are unchanged. + +### Changed (breaking) + +- `ThinkingLevel` gains `ThinkingNone` as its least constructor. Update exhaustive + matches. Anthropic and OpenAI compatibility records gain fields; use the + default records or update explicit record construction. +- All seven dependent packages now require `baikai ^>=0.10.0` and release + independently below. The unchanged adapters take dependency-only patch bumps. + +## [baikai-claude 0.7.3.0] - 2026-10-25 + +### Added + +- Export `injectSystemCacheControl` for shared system-prefix cache markers. +- `ThinkingNone` sends catalog-gated `thinking: {"type": "disabled"}` without + effort, display or a budget. Unsupported off requests remain visible + adjustments and fail strict evidence before dispatch. A host with no thinking + controls is not assumed to be a non-reasoning model. + +### Fixed + +- Short and long `cacheRetention` mark non-empty system prompts so fresh + conversations with different first questions can reuse the tools-and-system + prefix. System, last-tool and automatic markers share the effective TTL, + including host downgrades, and use at most three breakpoints. Empty or absent + system prompts and disabled caching keep their existing shape. Regression + coverage includes tool compatibility and an isolated live shared-prefix case. + Implements issue #2 and the approach in PR #3. + +### Changed + +- Require `baikai ^>=0.10.0`. + +## [baikai-openai 0.7.3.0] - 2026-10-25 + +### Added + +- Export `applyNativeCache` for validated native cache plans. +- OpenAI-compatible Chat (including Ollama) and Responses carry `none` where + supported. Z.ai and Qwen emit `enable_thinking: false`; unsupported off + requests remain visible adjustments and fail strict evidence before dispatch. + +### Fixed + +- Native OpenAI Short caching marks shared non-empty system prefixes on + catalog-supported Responses and Chat bindings. Unsupported native requests + fail locally. Effective duration reaches terminal pricing, partial usage + and evidence. +- Funded live prefix checks pass for Luna Responses Short/Long and GPT-5.6 Chat + Short. Luna Long uses verified 12h base and tier rates; unsupported Chat Long + and unverified modern bindings remain locally refused. + +### Changed + +- Require `baikai ^>=0.10.0`. Catalog effort policies distinguish GPT-5/o-series + models that cannot disable reasoning, Sol/Luna that accept none, and + Astra/GPT-6.1 Sol that do not. + +## [baikai-typesafe 0.1.0.1] - 2026-10-25 + +### Changed + +- Require `baikai ^>=0.10.0`. Dependency-only update; no package API change. + +## [baikai-trace-otel 0.4.1.1] - 2026-10-25 + +### Changed + +- Require `baikai ^>=0.10.0`. Dependency-only update; no package API change. + +## [baikai-effectful 0.4.0.5] - 2026-10-25 + +### Changed + +- Require `baikai ^>=0.10.0`. Dependency-only update; no package API change. + +## [baikai-kit 0.4.0.3] - 2026-10-25 + +### Changed + +- Require `baikai ^>=0.10.0`. Dependency-only update; no package API change. + +## [baikai-agent 0.2.0.4] - 2026-10-25 + +### Fixed + +- Layered job configuration accepts `thinking "none"` through the shared + canonical parser, keeping explicit off distinct from an absent preference. +- The UTF-8 stdin test runs in a child process under an ASCII locale, avoiding + shared-stdin descriptor races with parallel subprocess tests in the tarball. + +### Changed + +- Require `baikai ^>=0.10.0`, `baikai-claude ^>=0.7.3` and + `baikai-openai ^>=0.7.3` for explicit-off handling in both vendor renderers. + ## [baikai 0.9.0.0] - 2026-10-25 ### Added diff --git a/baikai-agent.cabal b/baikai-agent.cabal --- a/baikai-agent.cabal +++ b/baikai-agent.cabal @@ -1,6 +1,6 @@ cabal-version: 3.4 name: baikai-agent -version: 0.2.0.3 +version: 0.2.0.4 synopsis: Unattended coding-agent runs for the Baikai abstraction description: Runs a local coding-agent command-line tool with no terminal and no @@ -66,9 +66,9 @@ build-depends: aeson ^>=2.2, - baikai ^>=0.9.0, - baikai-claude ^>=0.7.1.1, - baikai-openai ^>=0.7.1.1, + baikai ^>=0.10.0, + baikai-claude ^>=0.7.3, + baikai-openai ^>=0.7.3, base >=4.20 && <5, bytestring ^>=0.12, containers ^>=0.7, diff --git a/src/Baikai/Agent/Config.hs b/src/Baikai/Agent/Config.hs --- a/src/Baikai/Agent/Config.hs +++ b/src/Baikai/Agent/Config.hs @@ -431,7 +431,7 @@ effortDecoder :: Decoder ThinkingLevel effortDecoder = parsedDecoder - "one of: minimal, low, medium, high, xhigh, max" + "one of: none, minimal, low, medium, high, xhigh, max" (maybe (Left "unknown effort") Right . parseThinkingLevel) pathDecoder :: Decoder FilePath diff --git a/test/CliTests.hs b/test/CliTests.hs --- a/test/CliTests.hs +++ b/test/CliTests.hs @@ -38,7 +38,6 @@ import Data.Text qualified as Text import Data.Text.Encoding qualified as Text import Data.Text.IO qualified as TextIO -import GHC.IO.Handle (hDuplicate, hDuplicateTo) import Options.Applicative qualified as Options import Settei.Env (EnvSnapshot, envSnapshot) import Settei.Key (parseKey) @@ -52,10 +51,11 @@ setOwnerExecutable, setPermissions, ) -import System.Environment (setEnv) +import System.Environment (getExecutablePath, setEnv) +import System.Exit (ExitCode (..)) import System.FilePath (takeDirectory, ()) -import System.IO (IOMode (..), hClose, openFile, stdin) import System.IO.Temp (withSystemTempDirectory) +import System.Process qualified as P import Test.Tasty (TestTree, testGroup) import Test.Tasty.HUnit (assertBool, assertFailure, testCase, (@?=)) @@ -1223,21 +1223,19 @@ readsThePromptFromStandardInputTest :: TestTree readsThePromptFromStandardInputTest = - testCase "the standard-input reader decodes UTF-8 explicitly" $ - -- The fixture above uses a file, because standard input cannot be - -- piped in-process; this is the narrow test of the transport the - -- motivating script actually uses. The real handle is duplicated - -- and restored so no other test is affected. - withWorkspace $ \dir -> do - path <- writeDocument dir "prompt.txt" fixturePrompt - saved <- hDuplicate stdin - source <- openFile path ReadMode - hDuplicateTo source stdin - hClose source - outcome <- readPromptSource PromptStdin - hDuplicateTo saved stdin - hClose saved - outcome @?= Right fixturePrompt + testCase "the standard-input reader decodes UTF-8 explicitly" $ do + -- Reading stdin closes it. Replacing the suite's shared handle races + -- with parallel subprocess fixtures, which can then reuse descriptor zero + -- for a pipe. Exercise the real reader in a child instead, under an ASCII + -- locale so locale-dependent decoding cannot accidentally pass. + executable <- getExecutablePath + let spec = + (P.proc executable ["--fixture-read-prompt-stdin"]) + { P.env = Just [("LANG", "C"), ("LC_ALL", "C")] + } + (code, output, err) <- P.readCreateProcessWithExitCode spec (Text.unpack fixturePrompt) + assertBool ("stdin reader failed: " <> show (code, err)) (code == ExitSuccess) + output @?= Text.unpack fixturePrompt readsThePromptFromAFileTest :: TestTree readsThePromptFromAFileTest = diff --git a/test/ConfigTests.hs b/test/ConfigTests.hs --- a/test/ConfigTests.hs +++ b/test/ConfigTests.hs @@ -35,6 +35,7 @@ repositoryScopeViolations, resolveAgentJob, ) +import Baikai.ThinkingLevel (ThinkingLevel (ThinkingNone)) import Control.Lens ((^.)) import Data.Generics.Labels () import Data.List (isPrefixOf, isSuffixOf) @@ -70,6 +71,10 @@ commandLineBeatsBothTest, environmentLayerTest, defaultsTest, + testCase "none resolves as explicit off rather than an absent override" $ + withConfigs Nothing (Just (jobDocWith "read-only" ["effort \"none\""])) $ \paths -> do + job <- resolveJob paths noEnvironment [] "demo" + job ^. #effort @?= Just ThinkingNone, singleArgumentListTest, outputFormatTest, missingFileTest @@ -255,6 +260,7 @@ job ^. #allowedTools @?= [] job ^. #providerArgs @?= [] job ^. #envRequires @?= [] + job ^. #effort @?= Nothing job ^. #timeout @?= Nothing job ^. #executable @?= Nothing job ^. #outputFormat @?= TextFormat diff --git a/test/Main.hs b/test/Main.hs --- a/test/Main.hs +++ b/test/Main.hs @@ -12,6 +12,7 @@ agentRunRequest, capturedBytes, ) +import Baikai.Agent.Cli (PromptSource (..), readPromptSource) import Baikai.Agent.Run (runAgentCommand, timeoutMicros) import Baikai.Evidence (noThinkingRequested) import BinaryTests (binaryTests) @@ -33,7 +34,8 @@ setOwnerExecutable, setPermissions, ) -import System.Exit (ExitCode (..)) +import System.Environment (getArgs) +import System.Exit (ExitCode (..), die) import System.FilePath (()) import System.IO.Temp (withSystemTempDirectory) import System.Process qualified as P @@ -41,16 +43,26 @@ import Test.Tasty.HUnit (assertBool, assertFailure, testCase, (@?=)) main :: IO () -main = - defaultMain $ - testGroup - "baikai-agent" - [ runTests, - configTests, - cliTests, - binaryTests, - PublicSurfaceSpec.tests - ] +main = do + args <- getArgs + case args of + ["--fixture-read-prompt-stdin"] -> do + outcome <- readPromptSource PromptStdin + case outcome of + Left problem -> die (Text.unpack problem) + Right prompt -> BS.putStr (Text.encodeUtf8 prompt) + _ -> defaultMain tests + +tests :: TestTree +tests = + testGroup + "baikai-agent" + [ runTests, + configTests, + cliTests, + binaryTests, + PublicSurfaceSpec.tests + ] runTests :: TestTree runTests =