fix(core): derive models.dev reasoning variants (#34726)

packages/llm/src/protocols/anthropic-messages.ts

@@ -148,9 +148,22 @@ const AnthropicToolChoice = Schema.Union([
   Schema.Struct({ type: Schema.tag("tool"), name: Schema.String }),
 ])
 
-const AnthropicThinking = Schema.Struct({
-  type: Schema.tag("enabled"),
-  budget_tokens: Schema.Number,
+const AnthropicThinking = Schema.Union([
+  Schema.Struct({
+    type: Schema.tag("enabled"),
+    budget_tokens: Schema.Number,
+  }),
+  Schema.Struct({
+    type: Schema.tag("adaptive"),
+    display: Schema.optional(Schema.Literals(["summarized", "omitted"])),
+  }),
+  Schema.Struct({
+    type: Schema.tag("disabled"),
+  }),
+])
+
+const AnthropicOutputConfig = Schema.Struct({
+  effort: Schema.optional(Schema.String),
 })
 
 const AnthropicBodyFields = {
@@ -166,6 +179,7 @@ const AnthropicBodyFields = {
   top_k: Schema.optional(Schema.Number),
   stop_sequences: optionalArray(Schema.String),
   thinking: Schema.optional(AnthropicThinking),
+  output_config: Schema.optional(AnthropicOutputConfig),
 }
 const AnthropicMessagesBody = Schema.Struct(AnthropicBodyFields)
 export type AnthropicMessagesBody = Schema.Schema.Type<typeof AnthropicMessagesBody>
@@ -492,7 +506,16 @@ const anthropicOptions = (request: LLMRequest) => request.providerOptions?.anthr
 
 const lowerThinking = Effect.fn("AnthropicMessages.lowerThinking")(function* (request: LLMRequest) {
   const thinking = anthropicOptions(request)?.thinking
-  if (!ProviderShared.isRecord(thinking) || thinking.type !== "enabled") return undefined
+  if (!ProviderShared.isRecord(thinking)) return undefined
+  if (thinking.type === "adaptive") {
+    const display = thinking.display
+    return {
+      type: "adaptive" as const,
+      ...(display === "summarized" || display === "omitted" ? { display } : {}),
+    }
+  }
+  if (thinking.type === "disabled") return { type: "disabled" as const }
+  if (thinking.type !== "enabled") return undefined
   const budget =
     typeof thinking.budgetTokens === "number"
       ? thinking.budgetTokens
@@ -503,6 +526,11 @@ const lowerThinking = Effect.fn("AnthropicMessages.lowerThinking")(function* (re
   return { type: "enabled" as const, budget_tokens: budget }
 })
 
+const outputConfig = (request: LLMRequest) => {
+  const effort = anthropicOptions(request)?.effort
+  return typeof effort === "string" ? { effort } : undefined
+}
+
 const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
   const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
   const generation = request.generation
@@ -549,6 +577,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
     top_k: generation?.topK,
     stop_sequences: generation?.stop,
     thinking: yield* lowerThinking(request),
+    output_config: outputConfig(request),
   }
 })
 

packages/llm/src/protocols/openai-chat.ts

@@ -168,8 +168,6 @@ interface ParserState {
   readonly lifecycle: Lifecycle.State
 }
 
-const invalid = ProviderShared.invalidRequest
-
 // =============================================================================
 // Request Lowering
 // =============================================================================
@@ -333,8 +331,6 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
 const lowerOptions = Effect.fn("OpenAIChat.lowerOptions")(function* (request: LLMRequest) {
   const store = OpenAIOptions.store(request)
   const reasoningEffort = OpenAIOptions.reasoningEffort(request)
-  if (reasoningEffort && !OpenAIOptions.isReasoningEffort(reasoningEffort))
-    return yield* invalid(`OpenAI Chat does not support reasoning effort ${reasoningEffort}`)
   return {
     ...(store !== undefined ? { store } : {}),
     ...(reasoningEffort ? { reasoning_effort: reasoningEffort } : {}),

packages/llm/src/protocols/openai-responses.ts

@@ -457,8 +457,6 @@ const lowerOptions = Effect.fn("OpenAIResponses.lowerOptions")(function* (reques
   const store = OpenAIOptions.store(request)
   const promptCacheKey = OpenAIOptions.promptCacheKey(request)
   const effort = OpenAIOptions.reasoningEffort(request)
-  if (effort && !OpenAIOptions.isReasoningEffort(effort))
-    return yield* invalid(`OpenAI Responses does not support reasoning effort ${effort}`)
   const summary = OpenAIOptions.reasoningSummary(request)
   const include = OpenAIOptions.include(request)
   const verbosity = OpenAIOptions.textVerbosity(request)

packages/llm/src/protocols/utils/openai-options.ts

@@ -1,11 +1,9 @@
 import { Schema } from "effect"
-import type { LLMRequest, ReasoningEffort, TextVerbosity as TextVerbosityValue } from "../../schema"
+import type { LLMRequest, TextVerbosity as TextVerbosityValue } from "../../schema"
 import { ReasoningEfforts, TextVerbosity } from "../../schema"
 
-export const OpenAIReasoningEfforts = ReasoningEfforts.filter(
-  (effort): effort is Exclude<ReasoningEffort, "max"> => effort !== "max",
-)
-export type OpenAIReasoningEffort = (typeof OpenAIReasoningEfforts)[number]
+export const OpenAIReasoningEfforts = ReasoningEfforts
+export type OpenAIReasoningEffort = string
 
 // Mirrors OpenAI's `ResponseIncludable` union from the official SDK. Keep this
 // in lockstep with `openai-node/src/resources/responses/responses.ts`.
@@ -23,22 +21,16 @@ export type OpenAIResponseIncludable = (typeof OpenAIResponseIncludables)[number
 export const OpenAIServiceTiers = ["auto", "default", "flex", "priority"] as const
 export type OpenAIServiceTier = (typeof OpenAIServiceTiers)[number]
 
-const REASONING_EFFORTS = new Set<string>(ReasoningEfforts)
-const OPENAI_REASONING_EFFORTS = new Set<string>(OpenAIReasoningEfforts)
 const TEXT_VERBOSITY = new Set<string>(["low", "medium", "high"])
 const INCLUDABLES = new Set<string>(OpenAIResponseIncludables)
 const SERVICE_TIERS = new Set<string>(OpenAIServiceTiers)
 
-export const OpenAIReasoningEffort = Schema.Literals(OpenAIReasoningEfforts)
+export const OpenAIReasoningEffort = Schema.String
 export const OpenAITextVerbosity = TextVerbosity
 export const OpenAIResponseIncludable = Schema.Literals(OpenAIResponseIncludables)
 export const OpenAIServiceTier = Schema.Literals(OpenAIServiceTiers)
 
-const isAnyReasoningEffort = (effort: unknown): effort is ReasoningEffort =>
-  typeof effort === "string" && REASONING_EFFORTS.has(effort)
-
-export const isReasoningEffort = (effort: unknown): effort is OpenAIReasoningEffort =>
-  typeof effort === "string" && OPENAI_REASONING_EFFORTS.has(effort)
+export const isReasoningEffort = (effort: unknown): effort is OpenAIReasoningEffort => typeof effort === "string"
 
 const isTextVerbosity = (value: unknown): value is TextVerbosityValue =>
   typeof value === "string" && TEXT_VERBOSITY.has(value)
@@ -50,9 +42,9 @@ export const store = (request: LLMRequest): boolean | undefined => {
   return typeof value === "boolean" ? value : undefined
 }
 
-export const reasoningEffort = (request: LLMRequest): ReasoningEffort | undefined => {
+export const reasoningEffort = (request: LLMRequest): string | undefined => {
   const value = options(request)?.reasoningEffort
-  return isAnyReasoningEffort(value) ? value : undefined
+  return typeof value === "string" ? value : undefined
 }
 
 export const reasoningSummary = (request: LLMRequest): "auto" | undefined =>

packages/llm/src/schema/ids.ts

@@ -27,7 +27,7 @@ export const ToolCallID = Schema.String
 export type ToolCallID = Schema.Schema.Type<typeof ToolCallID>
 
 export const ReasoningEfforts = ["none", "minimal", "low", "medium", "high", "xhigh", "max"] as const
-export const ReasoningEffort = Schema.Literals(ReasoningEfforts)
+export const ReasoningEffort = Schema.String
 export type ReasoningEffort = Schema.Schema.Type<typeof ReasoningEffort>
 
 export const TextVerbosity = Schema.Literals(["low", "medium", "high"])

packages/llm/test/provider/anthropic-messages.test.ts

@@ -57,6 +57,23 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
+  it.effect("lowers adaptive thinking settings with effort", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLM.updateRequest(request, {
+          providerOptions: {
+            anthropic: { thinking: { type: "adaptive", display: "summarized" }, effort: "low" },
+          },
+        }),
+      )
+
+      expect(prepared.body).toMatchObject({
+        thinking: { type: "adaptive", display: "summarized" },
+        output_config: { effort: "low" },
+      })
+    }),
+  )
+
   it.effect("lowers chronological system updates natively for Claude Opus 4.8 with cache hints", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(

packages/llm/test/provider/openai-chat.test.ts

@@ -98,12 +98,26 @@ describe("OpenAI Chat route", () => {
         LLM.request({
           model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).chat("gpt-4o-mini"),
           prompt: "think",
-          providerOptions: { openai: { reasoningEffort: "low" } },
+          providerOptions: { openai: { reasoningEffort: "max" } },
         }),
       )
 
       expect(prepared.body.store).toBe(false)
-      expect(prepared.body.reasoning_effort).toBe("low")
+      expect(prepared.body.reasoning_effort).toBe("max")
+    }),
+  )
+
+  it.effect("passes through custom OpenAI-compatible reasoning effort strings", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          model,
+          prompt: "think",
+          providerOptions: { openai: { reasoningEffort: "experimental" } },
+        }),
+      )
+
+      expect(prepared.body.reasoning_effort).toBe("experimental")
     }),
   )
 

packages/llm/test/provider/openai-responses.test.ts

@@ -69,6 +69,16 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
+  it.effect("passes through custom OpenAI reasoning effort strings", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
+        LLM.updateRequest(request, { providerOptions: { openai: { reasoningEffort: "experimental" } } }),
+      )
+
+      expect(prepared.body.reasoning).toEqual({ effort: "experimental" })
+    }),
+  )
+
   it.effect("omits unsupported semantic service tiers", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare(