diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,104 @@ ## [Unreleased] +## [baikai 0.7.1.0] - 2026-09-23 + +### Added + +- Curated GPT-6 Sol and Luna on OpenAI Responses and Claude Opus 5.5 on + Anthropic Messages (`openai_gpt_6_sol`, `openai_gpt_6_luna`, + `anthropic_claude_opus_5_5`), with endpoint compatibility and standard, + long-context, cache-duration, and fast-mode prices where applicable. All + three passed live acceptance on 2026-09-23. Sol and Luna dispatch to + `OpenAIResponses`, so calling them requires the + `Baikai.Provider.OpenAI.Responses.register` call that `baikai-openai 0.7.0.0` + introduced. + +## [baikai-kit 0.3.0.0] - 2026-09-23 + +Closes four improvement requests from the tools that ship `baikai-kit` as their +`kit` command: project scope resolves from a configurable root (IR-8), +`kit status` reports local edits separately from upstream drift (IR-7), +`kit install` without a name asks a tool-supplied chooser (IR-6), and `list`, +`status` and `update` print versioned JSON (IR-9). A consumer raising its bound +builds `KitConfig` with `kitConfig`, passes it to `kitCommandParser`, and +matches on `StatusRow.conditions`; each break is at a call site the compiler +names. + +### Added + +- `baikai-kit`: `KitConfig.projectRoot :: IO FilePath` says where project scope + lives. Install, status, update, uninstall and `agentDirsForSession` all derive + project-scope paths from it, so they agree whichever subdirectory a command + runs from. `kitConfig` builds a configuration with every optional field at its + default (project scope is the current directory, as before); + `projectRootByMarkers [".git", ".mytool"]` is a ready-made resolver that walks + up to the nearest marker and falls back to the current directory, and + `findProjectRoot` is the underlying walk. Resolves IR-8. + +- `baikai-kit`: `kit status` reports local edits. It runs the same + installed-file check `kit update` uses to skip an item, and shows + `modified` for an edited copy and `edits-unknown` for one whose sidecar + predates the installed-file hash. The check is exported as + `checkLocalEdits`, returning `LocalEdits` (`Unedited`, `Edited`, + `EditsUnknown`). Resolves IR-7. + +- `baikai-kit`: `kit install` with no name asks a chooser the tool supplies in + the new `KitConfig.chooseItem :: Maybe (KitManifest -> IO (Maybe Text))` + field. The engine refreshes the kit, passes the whole manifest, and installs + what the chooser returns; a cancelled choice prints + `No item chosen; nothing installed.` and exits 0. With no chooser (the + `kitConfig` default) the command fails with the new `KitItemNameRequired` + error, which tells the user to pass `NAME`. The engine ships no picker. + `KitCommand` derives `Eq`, and `kit install --help` names the tool's + `./agents` directory. Resolves IR-6. + +- `baikai-kit`: `kit list`, `kit status` and `kit update` accept `--json` and + print exactly one versioned JSON document on stdout + (`{"formatVersion": 1, "document": "kit-list" | "kit-status" | "kit-update", …}`); + warnings and the first-clone notice go to stderr, and a failed command writes + nothing to stdout. The shapes are written by explicit encoders — + `Baikai.Kit.Json.listDocument`, `statusDocument`, `updateDocument`, and + `kitJsonFormatVersion` — so library callers get the same values, and they are + pinned by golden tests. `Baikai.Kit.Command.OutputFormat` selects the mode, + and `Baikai.Kit.Status.InstalledCopy` / `installedCopies` report where each + item is installed. Resolves IR-9. + +### Changed + +- `baikai-kit`: `KitConfig` gains the strict field `projectRoot`, so a record + literal must set it; build the configuration with + `kitConfig toolName repoUrl providers` instead and override fields with record + update syntax. `KitConfig`'s `Show` instance is now hand-written and prints + `` for the resolver. __Breaking__. + +- `baikai-kit`: `kit status` conditions compose, and `dirty` is renamed + `changed-upstream` (it meant the upstream sources changed without a version + bump, not local edits); `dirty+outdated` now reads + `outdated+changed-upstream`. `StatusRow.state :: KitState` is replaced by + `StatusRow.conditions :: [KitCondition]` (sorted; empty means up to date), + `renderState` by `conditionLabel` and `renderConditions`, and `classify` + returns `[KitCondition]`. `KitUpToDate`, `KitDirty` and `KitDirtyOutdated` + are gone; match on the list instead. __Breaking__. + +- `baikai-kit`: `KitInstall` takes `Maybe Text` (`Nothing` asks the chooser), + `kitCommandParser` takes the `KitConfig` (migration: `kitCommandParser` + becomes `kitCommandParser myKitConfig`), `KitConfig` gains the `chooseItem` + field (set by `kitConfig`), and `KitError` gains `KitItemNameRequired`. + __Breaking__. + +- `baikai-kit`: `KitList`, `KitStatus` and `KitUpdate` gain a trailing + `OutputFormat` field (`HumanOutput` for the previous behaviour). + __Breaking__. + +## [baikai-effectful 0.4.0.2] - 2026-09-15 + +### Changed (dependencies) + +- Requires `effectful-core ^>=2.7` (was `^>=2.6`). No API change: none of the + 2.7 breaking APIs (`LocalEnv`'s second type parameter, `SharedSuffix`, + `KnownEffects`, the ticked strict modules) are used. + ## [baikai 0.7.0.0] - 2026-09-08 ### Added diff --git a/baikai.cabal b/baikai.cabal --- a/baikai.cabal +++ b/baikai.cabal @@ -1,7 +1,7 @@ -cabal-version: 3.4 -name: baikai -version: 0.7.0.0 -synopsis: Unified Haskell interface for multiple AI providers +cabal-version: 3.4 +name: baikai +version: 0.7.1.0 +synopsis: Unified Haskell interface for multiple AI providers description: baikai provides a unified, provider-agnostic Haskell interface for working with multiple AI providers. It abstracts chat and streaming completions, tool @@ -9,21 +9,27 @@ concrete provider implementations supplied by companion packages such as @baikai-claude@ and @baikai-openai@. -category: AI -license: BSD-3-Clause -license-file: LICENSE -author: Nadeem Bitar -maintainer: nadeem@gmail.com -copyright: (c) 2026 Nadeem Bitar -build-type: Simple -tested-with: GHC ==9.12.4 +category: AI +license: BSD-3-Clause +license-file: LICENSE +author: Nadeem Bitar +maintainer: nadeem@gmail.com +copyright: (c) 2026 Nadeem Bitar +build-type: Simple +tested-with: ghc ==9.12.4 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 -- Exhaustiveness is an error, not a warning. A non-exhaustive match @@ -38,10 +44,11 @@ -- fail the build on warnings that are stylistic or that a future GHC -- invents, and would push people toward blanket suppression. ghc-options: - -Werror=incomplete-patterns -Werror=incomplete-uni-patterns + -Werror=incomplete-patterns + -Werror=incomplete-uni-patterns -Werror=incomplete-record-updates - default-language: GHC2024 + default-language: GHC2024 default-extensions: DeriveAnyClass DuplicateRecordFields @@ -49,8 +56,8 @@ OverloadedStrings library - import: common-options - hs-source-dirs: src + import: common-options + hs-source-dirs: src exposed-modules: Baikai Baikai.Agent @@ -100,84 +107,90 @@ -- it so an evidence record can name the build that produced it, -- centrally rather than through a literal in each of the five -- packages that construct evidence. - other-modules: Paths_baikai + other-modules: Paths_baikai autogen-modules: Paths_baikai build-depends: - , aeson ^>=2.2 - , base >=4.20 && <5 - , base16-bytestring ^>=1.0 - , base64-bytestring ^>=1.2 - , bytestring ^>=0.12 - , case-insensitive ^>=1.2 - , containers ^>=0.7 - , cryptohash-sha256 ^>=0.11 - , directory ^>=1.3 - , filepath ^>=1.5 - , generic-lens ^>=2.3 - , http-client ^>=0.7 - , http-client-tls >=0.3 && <0.5 - , http-types ^>=0.12 - , lens ^>=5.3 - , openai ^>=2.5 - , process ^>=1.6 - , scientific ^>=0.3 - , servant-client ^>=0.20 - , stm ^>=2.5 - , streamly >=0.11 && <0.13 - , streamly-core >=0.3 && <0.5 - , text ^>=2.1 - , time ^>=1.14 - , tls >=2.2 && <2.5 - , unliftio-core ^>=0.2 - , vector ^>=0.13 + aeson ^>=2.2, + base >=4.20 && <5, + base16-bytestring ^>=1.0, + base64-bytestring ^>=1.2, + bytestring ^>=0.12, + case-insensitive ^>=1.2, + containers ^>=0.7, + cryptohash-sha256 ^>=0.11, + directory ^>=1.3, + filepath ^>=1.5, + generic-lens ^>=2.3, + http-client ^>=0.7, + http-client-tls >=0.3 && <0.5, + http-types ^>=0.12, + lens ^>=5.3, + openai ^>=2.5, + process ^>=1.6, + scientific ^>=0.3, + servant-client ^>=0.20, + stm ^>=2.5, + streamly >=0.11 && <0.13, + streamly-core >=0.3 && <0.5, + text ^>=2.1, + time ^>=1.14, + tls >=2.2 && <2.5, + unliftio-core ^>=0.2, + vector ^>=0.13, executable baikai-gen-models - import: common-options + import: common-options hs-source-dirs: gen - main-is: GenModels.hs - other-modules: GenModelsCore + main-is: GenModels.hs + other-modules: GenModelsCore build-depends: - , aeson ^>=2.2 - , baikai - , base >=4.20 && <5 - , bytestring ^>=0.12 - , containers ^>=0.7 - , directory ^>=1.3 - , filepath ^>=1.5 - , scientific ^>=0.3 - , text ^>=2.1 + aeson ^>=2.2, + baikai, + base >=4.20 && <5, + bytestring ^>=0.12, + containers ^>=0.7, + directory ^>=1.3, + filepath ^>=1.5, + scientific ^>=0.3, + text ^>=2.1, executable baikai-fetch-models - import: common-options + import: common-options hs-source-dirs: fetch - main-is: FetchModels.hs - other-modules: FetchModelsCore - + main-is: FetchModels.hs + other-modules: FetchModelsCore -- The main module is named @FetchModels@ (not @Main@) so the pure -- core can be compiled into the test suite alongside its own -- @Main.hs@ without a module-name clash. - ghc-options: -main-is FetchModels + ghc-options: + -main-is + FetchModels + build-depends: - , aeson ^>=2.2 - , baikai - , base >=4.20 && <5 - , bytestring ^>=0.12 - , containers ^>=0.7 - , directory ^>=1.3 - , filepath ^>=1.5 - , generic-lens ^>=2.3 - , http-client ^>=0.7 - , http-client-tls >=0.3 && <0.5 - , lens ^>=5.3 - , scientific ^>=0.3 - , text ^>=2.1 - , vector ^>=0.13 + aeson ^>=2.2, + baikai, + base >=4.20 && <5, + bytestring ^>=0.12, + containers ^>=0.7, + directory ^>=1.3, + filepath ^>=1.5, + generic-lens ^>=2.3, + http-client ^>=0.7, + http-client-tls >=0.3 && <0.5, + lens ^>=5.3, + scientific ^>=0.3, + text ^>=2.1, + vector ^>=0.13, test-suite baikai-test - import: common-options - type: exitcode-stdio-1.0 - hs-source-dirs: test fetch gen - main-is: Main.hs + import: common-options + type: exitcode-stdio-1.0 + hs-source-dirs: + test + fetch + gen + + main-is: Main.hs other-modules: AgentAssetsSpec AgentSpec @@ -209,29 +222,29 @@ build-tool-depends: baikai:baikai-gen-models build-depends: - , aeson - , baikai - , base - , bytestring - , case-insensitive - , containers - , directory - , filepath - , generic-lens - , http-client - , http-types - , lens - , openai - , process - , scientific - , servant-client - , stm - , streamly-core >=0.3 && <0.5 - , tasty - , tasty-hunit - , tasty-quickcheck - , temporary - , text - , time - , tls - , vector + aeson, + baikai, + base, + bytestring, + case-insensitive, + containers, + directory, + filepath, + generic-lens, + http-client, + http-types, + lens, + openai, + process, + scientific, + servant-client, + stm, + streamly-core >=0.3 && <0.5, + tasty, + tasty-hunit, + tasty-quickcheck, + temporary, + text, + time, + tls, + vector, diff --git a/fetch/FetchModelsCore.hs b/fetch/FetchModelsCore.hs --- a/fetch/FetchModelsCore.hs +++ b/fetch/FetchModelsCore.hs @@ -259,13 +259,19 @@ } deriving stock (Generic) --- | Curation include set for OpenAI: the chat-completions-compatible --- current line. Responses-API-only ids (@*-pro@, @*-codex@, --- @*-deep-research@) are deliberately absent. +-- | Curation include set for OpenAI's current Chat and Responses lines. +-- Responses-only ids outside the text and function-tool scope +-- (@*-pro@, @*-codex@, @*-deep-research@) are deliberately absent. openaiInclude :: Map Text (Maybe CatalogModelCompat) openaiInclude = - Map.insert "gpt-6-astra" (Just (CatalogResponsesCompat astraResponsesFacts)) $ - Map.fromList + Map.union + ( Map.fromList + [ ("gpt-6-astra", Just (CatalogResponsesCompat astraResponsesFacts)), + ("gpt-6-sol", Just (CatalogResponsesCompat gpt6ResponsesFacts)), + ("gpt-6-luna", Just (CatalogResponsesCompat gpt6ResponsesFacts)) + ] + ) + $ Map.fromList [ (model, Nothing) | model <- [ "gpt-5.6", @@ -293,6 +299,11 @@ ] ] where + -- 2026-09-23: Sol and Luna require Responses for function calling at + -- their default reasoning effort; Chat permits it only at effort none. + -- https://developers.openai.com/api/docs/models/gpt-6-sol + -- https://developers.openai.com/api/docs/models/gpt-6-luna + gpt6ResponsesFacts = astraResponsesFacts -- 2026-09-07: native tools require Responses; only modern 30m cache TTL. -- https://developers.openai.com/api/docs/guides/latest-model astraResponsesFacts = @@ -322,6 +333,13 @@ -- docs/plans/60-... named this id as the one the include set did not -- yet carry, and stated the facts it would have to arrive with. ("claude-opus-5", fastAdaptive), + -- 2026-09-23: always-on adaptive thinking; forced tool choice is + -- rejected. Nondefault sampling is rejected on Claude 4.7 and later; + -- fast mode is supported on the Claude API. + -- https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5 + -- https://platform.claude.com/docs/en/claude_api_primer + -- https://platform.claude.com/docs/en/build-with-claude/fast-mode + ("claude-opus-5-5", opus55Facts), -- 2026-08-27: adaptive-only, sampling parameters rejected with a -- 400 — same source. ("claude-opus-4-8", fastAdaptive), @@ -353,8 +371,9 @@ ("claude-fable-5-1", adaptiveNoSampling & #supportsForcedToolChoice .~ False) ] where - -- 2026-09-07: all curated predecessors accept forced choice (subject to - -- their separate manual-thinking constraint); only Fable 5.1 rejects it. + opus55Facts = adaptiveNoSampling & #supportsForcedToolChoice .~ False & #fastModeCost ?~ CatalogCost 8 40 0.4 10 + -- 2026-09-23: Fable 5.1 and Opus 5.5 reject forced choice; older curated + -- models accept it subject to their separate manual-thinking constraint. -- https://platform.claude.com/docs/en/api/errors -- https://platform.claude.com/docs/en/models/fable-5-1/migration-guide -- 2026-09-07: Opus 5 and 4.8 only; cache multipliers stack on fast rates. @@ -620,17 +639,23 @@ where c = m ^. #cost --- | Provider documentation verified 2026-09-07. These rules supplement base +-- | Provider documentation verified 2026-09-23. These rules supplement base -- models.dev rates, which do not describe the full request billing policy. -- https://developers.openai.com/api/docs/models/gpt-6-astra +-- https://developers.openai.com/api/docs/models/gpt-6-sol +-- https://developers.openai.com/api/docs/models/gpt-6-luna -- https://platform.claude.com/docs/en/models/fable-5-1/overview +-- https://platform.claude.com/docs/en/models/opus-5-5/overview -- https://platform.claude.com/docs/en/build-with-claude/fast-mode pricingPolicies :: Map (Text, Text) Model.PricingPolicy pricingPolicies = Map.fromList - [ (("anthropic", "claude-opus-5"), Model.PricingPolicy [] (Just 10)), + [ (("anthropic", "claude-opus-5-5"), Model.PricingPolicy [] (Just 8)), + (("anthropic", "claude-opus-5"), Model.PricingPolicy [] (Just 10)), (("anthropic", "claude-opus-4-8"), Model.PricingPolicy [] (Just 10)), (("openai", "gpt-6-astra"), Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 20 75 2 25)] Nothing), + (("openai", "gpt-6-sol"), Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 4 15 0.4 5)] Nothing), + (("openai", "gpt-6-luna"), Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 0.2 0.75 0.02 0.25)] Nothing), (("anthropic", "claude-fable-5-1"), Model.PricingPolicy [] (Just 20)) ] diff --git a/src/Baikai/Models/Generated.hs b/src/Baikai/Models/Generated.hs --- a/src/Baikai/Models/Generated.hs +++ b/src/Baikai/Models/Generated.hs @@ -361,6 +361,49 @@ } } +anthropic_claude_opus_5_5 :: Model +anthropic_claude_opus_5_5 = + emptyModel + { modelId = "claude-opus-5-5", + name = "Claude Opus 5.5", + api = AnthropicMessages, + provider = "anthropic", + baseUrl = "https://api.anthropic.com", + reasoning = True, + input = [InputText, InputImage], + cost = + ModelCost + { inputCost = 4 % 1, + outputCost = 20 % 1, + cacheReadCost = 1 % 5, + cacheWriteCost = 5 % 1 + }, + fastModeCost = + Just + ( ModelCost + { inputCost = 8 % 1, + outputCost = 40 % 1, + cacheReadCost = 2 % 5, + cacheWriteCost = 10 % 1 + } + ), + pricingPolicy = Just (PricingPolicy [] (Just (8 % 1))), + contextWindow = 1000000, + maxOutputTokens = 128000, + headers = Map.empty, + compat = + CompatAnthropicMessages + defaultAnthropicMessagesCompat + { supportsLongCacheRetention = True, + supportsCacheControlOnTools = True, + sendSessionAffinityHeaders = False, + thinkingStyle = AnthropicThinkingAdaptive, + supportsSamplingParameters = False, + supportsFastMode = True, + supportsForcedToolChoice = False + } + } + anthropic_claude_sonnet_4_5 :: Model anthropic_claude_sonnet_4_5 = emptyModel @@ -998,6 +1041,70 @@ } } +openai_gpt_6_luna :: Model +openai_gpt_6_luna = + emptyModel + { modelId = "gpt-6-luna", + name = "GPT-6 Luna", + api = OpenAIResponses, + provider = "openai", + baseUrl = "https://api.openai.com", + reasoning = True, + input = [InputText, InputImage], + cost = + ModelCost + { inputCost = 1 % 10, + outputCost = 1 % 2, + cacheReadCost = 1 % 100, + cacheWriteCost = 1 % 8 + }, + fastModeCost = Nothing, + pricingPolicy = Just (PricingPolicy [InputPriceTier 272000 (ModelCost (1 % 5) (3 % 4) (1 % 50) (1 % 4))] Nothing), + contextWindow = 1050000, + maxOutputTokens = 128000, + headers = Map.empty, + compat = + CompatOpenAIResponses + defaultOpenAIResponsesCompat + { supportedReasoningEfforts = Just [ThinkingLow, ThinkingMedium, ThinkingHigh, ThinkingXHigh, ThinkingMax], + supportsSamplingParameters = False, + supportsLongCacheRetention = False, + supportsPromptCacheOptions = True + } + } + +openai_gpt_6_sol :: Model +openai_gpt_6_sol = + emptyModel + { modelId = "gpt-6-sol", + name = "GPT-6 Sol", + api = OpenAIResponses, + provider = "openai", + baseUrl = "https://api.openai.com", + reasoning = True, + input = [InputText, InputImage], + cost = + ModelCost + { inputCost = 2 % 1, + outputCost = 10 % 1, + cacheReadCost = 1 % 5, + cacheWriteCost = 5 % 2 + }, + fastModeCost = Nothing, + pricingPolicy = Just (PricingPolicy [InputPriceTier 272000 (ModelCost (4 % 1) (15 % 1) (2 % 5) (5 % 1))] Nothing), + contextWindow = 1050000, + maxOutputTokens = 128000, + headers = Map.empty, + compat = + CompatOpenAIResponses + defaultOpenAIResponsesCompat + { supportedReasoningEfforts = Just [ThinkingLow, ThinkingMedium, ThinkingHigh, ThinkingXHigh, ThinkingMax], + supportsSamplingParameters = False, + supportsLongCacheRetention = False, + supportsPromptCacheOptions = True + } + } + openai_o1 :: Model openai_o1 = emptyModel @@ -1159,6 +1266,7 @@ anthropic_claude_opus_4_7, anthropic_claude_opus_4_8, anthropic_claude_opus_5, + anthropic_claude_opus_5_5, anthropic_claude_sonnet_4_5, anthropic_claude_sonnet_4_6, anthropic_claude_sonnet_5, @@ -1183,6 +1291,8 @@ openai_gpt_5_mini, openai_gpt_5_nano, openai_gpt_6_astra, + openai_gpt_6_luna, + openai_gpt_6_sol, openai_o1, openai_o3, openai_o3_mini, diff --git a/src/Baikai/Provider/Transport/Classify.hs b/src/Baikai/Provider/Transport/Classify.hs --- a/src/Baikai/Provider/Transport/Classify.hs +++ b/src/Baikai/Provider/Transport/Classify.hs @@ -61,6 +61,7 @@ ePIPE, eTIMEDOUT, ) + -- Qualified: its 'IOErrorType' has a constructor named @OtherError@, -- which collides with the 'ErrorCategory' constructor of that name. import GHC.IO.Exception qualified as IOE diff --git a/src/Baikai/Trace.hs b/src/Baikai/Trace.hs --- a/src/Baikai/Trace.hs +++ b/src/Baikai/Trace.hs @@ -65,6 +65,7 @@ summarizeContext, ) import Baikai.Error (BaikaiError, providerError) + -- 'Baikai.Evidence.CallStatus' has a @CallFailed@ constructor and so -- does 'Baikai.Trace.Event.TraceEvent'. They mean different things and -- both belong in this module, so the status constructors stay behind diff --git a/test/CatalogSpec.hs b/test/CatalogSpec.hs --- a/test/CatalogSpec.hs +++ b/test/CatalogSpec.hs @@ -60,6 +60,19 @@ c.supportsSamplingParameters @?= False c.supportedReasoningEfforts @?= Just [ThinkingLow, ThinkingMedium, ThinkingHigh, ThinkingXHigh, ThinkingMax] _ -> assertFailure "Astra needs explicit OpenAI endpoint facts", + testCase "Sol and Luna select Responses with explicit endpoint facts" $ + mapM_ + ( \mid -> do + [api m | m <- allModels, modelId m == mid] @?= [OpenAIResponses] + case [compat m | m <- allModels, modelId m == mid] of + [CompatOpenAIResponses c] -> do + c.supportsPromptCacheOptions @?= True + c.supportsLongCacheRetention @?= False + c.supportsSamplingParameters @?= False + c.supportedReasoningEfforts @?= Just [ThinkingLow, ThinkingMedium, ThinkingHigh, ThinkingXHigh, ThinkingMax] + _ -> assertFailure "GPT-6 Sol/Luna need explicit OpenAI Responses facts" + ) + ["gpt-6-sol", "gpt-6-luna"], testCase "regenerating from data/models produces no diff" $ withSystemTempDirectory "baikai-catalog-spec" $ \tmpDir -> do let regenPath = tmpDir <> "/Generated.hs" @@ -103,6 +116,7 @@ ("claude-opus-4-7", (AnthropicThinkingAdaptive, False, True, False)), ("claude-opus-4-8", (AnthropicThinkingAdaptive, False, True, True)), ("claude-opus-5", (AnthropicThinkingAdaptive, False, True, True)), + ("claude-opus-5-5", (AnthropicThinkingAdaptive, False, False, True)), ("claude-sonnet-4-5", (AnthropicThinkingBudget, True, True, False)), ("claude-sonnet-4-6", (AnthropicThinkingAdaptive, True, True, False)), ("claude-sonnet-5", (AnthropicThinkingAdaptive, False, True, False)) diff --git a/test/FetchModelsSpec.hs b/test/FetchModelsSpec.hs --- a/test/FetchModelsSpec.hs +++ b/test/FetchModelsSpec.hs @@ -162,12 +162,15 @@ map (^. #apiOverride) (refreshed ^. #models) @?= [Just "openai-responses"] map (^. #compat) (refreshed ^. #models) @?= [expected] assertBool "explicit compat survives rendering" ("openai-responses" `Text.isInfixOf` decodeUtf8 (renderCatalog refreshed)), - testCase "fast rates and capability survive fetch and generator on exactly two curated models" $ do + testCase "fast rates and capability survive fetch and generator on curated models" $ do upstream <- loadUpstream let sample = (upstream Map.! "openai") Map.! "gpt-5.4" forM_ (Map.keys anthropicInclude) $ \mid -> do let refreshed = normalizeProvider anthropicSpec (Map.singleton mid (sample & #modelId .~ mid)) - expected = if mid `elem` ["claude-opus-5", "claude-opus-4-8"] then Just (CatalogCost 10 50 1 12.5) else Nothing + expected + | mid == "claude-opus-5-5" = Just (CatalogCost 8 40 0.4 10) + | mid `elem` ["claude-opus-5", "claude-opus-4-8"] = Just (CatalogCost 10 50 1 12.5) + | otherwise = Nothing map (^. #fastModeCost) (refreshed ^. #models) @?= [expected] case Aeson.eitherDecode (BSL.fromStrict (renderCatalog refreshed)) of Left err -> assertFailure err @@ -175,12 +178,19 @@ testCase "curated pricing survives fetch rendering and generator parsing" $ do upstream <- loadUpstream let sample = (upstream Map.! "openai") Map.! "gpt-5.4" - forM_ [(openaiSpec, "gpt-6-astra", Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 20 75 2 25)] Nothing), (anthropicSpec, "claude-fable-5-1", Model.PricingPolicy [] (Just 20))] $ \(spec, mid, policy) -> do - let refreshed = normalizeProvider spec (Map.singleton mid (sample & #modelId .~ mid)) - map (^. #pricingPolicy) (refreshed ^. #models) @?= [Just policy] - case Aeson.eitherDecode (BSL.fromStrict (renderCatalog refreshed)) of - Left err -> assertFailure err - Right catalog -> map (Gen.pricingPolicy . snd) (Gen.flattenEntries catalog) @?= [Just policy], + forM_ + [ (openaiSpec, "gpt-6-astra", Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 20 75 2 25)] Nothing), + (openaiSpec, "gpt-6-sol", Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 4 15 0.4 5)] Nothing), + (openaiSpec, "gpt-6-luna", Model.PricingPolicy [Model.InputPriceTier 272000 (Model.ModelCost 0.2 0.75 0.02 0.25)] Nothing), + (anthropicSpec, "claude-fable-5-1", Model.PricingPolicy [] (Just 20)), + (anthropicSpec, "claude-opus-5-5", Model.PricingPolicy [] (Just 8)) + ] + $ \(spec, mid, policy) -> do + let refreshed = normalizeProvider spec (Map.singleton mid (sample & #modelId .~ mid)) + map (^. #pricingPolicy) (refreshed ^. #models) @?= [Just policy] + case Aeson.eitherDecode (BSL.fromStrict (renderCatalog refreshed)) of + Left err -> assertFailure err + Right catalog -> map (Gen.pricingPolicy . snd) (Gen.flattenEntries catalog) @?= [Just policy], testCase "OpenAI normalization filters, curates, and maps fields" $ do upstream <- loadUpstream catalogFor upstream openaiSpec @?= expectedOpenAI, diff --git a/test/PricingPolicySpec.hs b/test/PricingPolicySpec.hs --- a/test/PricingPolicySpec.hs +++ b/test/PricingPolicySpec.hs @@ -4,10 +4,11 @@ import Baikai.CacheRetention (CacheRetention (..)) import Baikai.Cost qualified as C -import Baikai.Cost.Pricing (computeCost, computeCostAtRates, computeCostForService, computeCostWith, resolveRates) +import Baikai.Cost.Pricing (computeCost, computeCostAtRates, computeCostAtSpeed, computeCostForService, computeCostWith, resolveRates) import Baikai.Evidence qualified as Ev import Baikai.Model qualified as M import Baikai.Models.Generated qualified as Models +import Baikai.Speed (Speed (..)) import Baikai.Usage qualified as U import Baikai.Usage.Normalize qualified as N import Control.Lens ((&), (.~)) @@ -22,7 +23,22 @@ tests = testGroup "Pricing policy" - [ testCase "requested tiers never substitute for observed service" $ do + [ testCase "Sol and Luna prices switch the complete request above 272K" $ + forM_ [(Models.openai_gpt_6_sol, M.ModelCost 2 10 (1 / 5) (5 / 2), M.ModelCost 4 15 (2 / 5) 5), (Models.openai_gpt_6_luna, M.ModelCost (1 / 10) (1 / 2) (1 / 100) (1 / 8), M.ModelCost (1 / 5) (3 / 4) (1 / 50) (1 / 4))] $ \(m, standard, highRates) -> do + forM_ [(272000, standard), (272001, highRates)] $ \(n, expected) -> do + let u = U.zeroUsage & #inputTokens .~ (n - 2000) & #cacheReadTokens .~ 1000 & #cacheWriteTokens .~ 1000 & #outputTokens .~ 100 + resolveRates Nothing m u @?= Right expected + (computeCost m u).usd @?= (fromIntegral (n - 2000) * expected.inputCost + 1000 * expected.cacheReadCost + 1000 * expected.cacheWriteCost + 100 * expected.outputCost) / 1000000, + testCase "Opus 5.5 prices short, long, and observed fast cache writes" $ do + let m = Models.anthropic_claude_opus_5_5 + u = U.zeroUsage & #cacheWriteTokens .~ 1000000 + observedFast = U.observeBilling [U.BillingSpeed "fast", U.BillingServiceTier "standard"] u + (computeCostWith (Just CacheRetentionShort) m u).usd @?= 5 + (computeCostWith (Just CacheRetentionLong) m u).usd @?= 8 + (computeCostAtSpeed m SpeedFast u).usd @?= 10 + (computeCostForService (Just CacheRetentionLong) Nothing m observedFast).usd @?= 16 + Set.member (C.UnsupportedSpeed "fast") (computeCostForService (Just CacheRetentionLong) Nothing m observedFast).basis.estimateReasons @?= False, + testCase "requested tiers never substitute for observed service" $ do let unknown = N.normalizeUsage N.InclusiveInput (N.ReportedUsage (Just 1000) (Just 0) (Just 0) (Just 0) Nothing) standard = U.observeBilling [U.BillingServiceTier "default"] unknown priority = U.observeBilling [U.BillingServiceTier "priority"] unknown