refactor(ai): separate conversation and generation lowering

packages/ai/src/protocols/open-responses.ts

@@ -689,13 +689,30 @@ const lowerMessages = Effect.fn("OpenResponses.lowerMessages")(function* (reques
   return input
 })
 
-const lowerOptions = (request: LLMRequest) => {
-  const options = OpenResponsesOptions.resolve(request)
+export const lowerConversation = Effect.fn("OpenResponses.lowerConversation")(function* (
+  request: LLMRequest,
+  extension: Extension,
+) {
   const instructions = ProviderShared.joinText(request.system)
+  return {
+    model: request.model.id,
+    input: yield* lowerMessages(request, extension),
+    ...(instructions ? { instructions } : {}),
+  }
+})
+
+export const lowerGeneration = (request: LLMRequest) => {
+  const options = OpenResponsesOptions.resolve(request)
+  const generation = request.generation
   const cacheKey = ProviderShared.promptCacheKey(request)
   const parallelToolCalls = resolveParallelToolCalls(request)
   return {
-    ...(instructions ? { instructions } : {}),
+    stream: true as const,
+    max_output_tokens: generation?.maxTokens,
+    temperature: generation?.temperature,
+    top_p: generation?.topP,
+    presence_penalty: generation?.presencePenalty,
+    frequency_penalty: generation?.frequencyPenalty,
     ...(options.store !== undefined ? { store: options.store } : {}),
     ...(options.metadata ? { metadata: options.metadata } : {}),
     ...(options.safetyIdentifier ? { safety_identifier: options.safetyIdentifier } : {}),
@@ -723,7 +740,7 @@ export const resolveParallelToolCalls = (request: LLMRequest) => {
   return disabled === undefined ? undefined : !disabled
 }
 
-const allowedToolChoice = (request: LLMRequest) => {
+export const allowedToolChoice = (request: LLMRequest) => {
   const allowed = OpenResponsesOptions.resolve(request).allowedTools
   if (!allowed) return undefined
   return {
@@ -737,11 +754,10 @@ export const fromRequestWithExtension = Effect.fn("OpenResponses.fromRequestWith
   request: LLMRequest,
   extension: Extension,
 ) {
-  const generation = request.generation
   const toolSchemaCompatibility = request.model.compatibility?.toolSchema
   return {
-    model: request.model.id,
-    input: yield* lowerMessages(request, extension),
+    ...(yield* lowerConversation(request, extension)),
+    ...lowerGeneration(request),
     tools:
       request.tools.length === 0
         ? undefined
@@ -755,13 +771,6 @@ export const fromRequestWithExtension = Effect.fn("OpenResponses.fromRequestWith
     tool_choice:
       allowedToolChoice(request) ??
       (request.toolChoice ? yield* lowerToolChoice(extension.name, request.toolChoice) : undefined),
-    stream: true as const,
-    max_output_tokens: generation?.maxTokens,
-    temperature: generation?.temperature,
-    top_p: generation?.topP,
-    presence_penalty: generation?.presencePenalty,
-    frequency_penalty: generation?.frequencyPenalty,
-    ...lowerOptions(request),
   }
 })
 

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

@@ -5,7 +5,7 @@ import { Auth } from "../route/auth.js"
 import { Endpoint } from "../route/endpoint.js"
 import { Protocol } from "../route/protocol.js"
 import { HttpTransport } from "../route/transport/index.js"
-import { LLMRequest, type JsonSchema, type ToolDefinition } from "../schema/index.js"
+import type { LLMRequest, JsonSchema, ToolDefinition } from "../schema/index.js"
 import { OpenResponses } from "./open-responses.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { OpenAIImage } from "./utils/openai-image.js"
@@ -125,15 +125,10 @@ const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>, tool
 const decodeBody = ProviderShared.validateWith(Schema.decodeUnknownEffect(OpenAIResponsesBody))
 
 const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request: LLMRequest) {
-  const body = yield* OpenResponses.fromRequestWithExtension(
-    LLMRequest.update(request, { tools: [], toolChoice: undefined }),
-    extension,
-  )
   const toolSchemaCompatibility = request.model.compatibility?.toolSchema
-  const parallelToolCalls = OpenResponses.resolveParallelToolCalls(request)
   return yield* decodeBody({
-    ...body,
-    ...(parallelToolCalls === undefined ? {} : { parallel_tool_calls: parallelToolCalls }),
+    ...(yield* OpenResponses.lowerConversation(request, extension)),
+    ...OpenResponses.lowerGeneration(request),
     tools:
       request.tools.length === 0
         ? undefined
@@ -141,7 +136,8 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
             lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility)),
           ),
     tool_choice:
-      body.tool_choice ?? (request.toolChoice ? yield* lowerToolChoice(request.toolChoice, request.tools) : undefined),
+      OpenResponses.allowedToolChoice(request) ??
+      (request.toolChoice ? yield* lowerToolChoice(request.toolChoice, request.tools) : undefined),
   })
 })
 

packages/ai/test/provider/conversation-lowering.test.ts

@@ -0,0 +1,30 @@
+import { expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, Message } from "../../src/index.js"
+import { OpenAI } from "../../src/providers.js"
+import { OpenResponses } from "../../src/protocols/open-responses.js"
+import { it } from "../lib/effect.js"
+
+it.effect("conversation lowering excludes generation settings and tool definitions", () =>
+  Effect.gen(function* () {
+    const body = yield* OpenResponses.lowerConversation(
+      LLM.request({
+        model: OpenAI.configure({ apiKey: "test" }).responses("fixture"),
+        system: "Keep the context",
+        messages: [Message.user("hello"), Message.assistant("hi")],
+        generation: { maxTokens: 100, temperature: 0.5 },
+        providerOptions: { store: false },
+        tools: [{ name: "unsupported", description: "Generation only", inputSchema: {}, native: { unsupported: {} } }],
+      }),
+      { id: "open-responses", name: "Open Responses" },
+    )
+    expect(body).toEqual({
+      model: "fixture",
+      instructions: "Keep the context",
+      input: [
+        { role: "user", content: [{ type: "input_text", text: "hello" }] },
+        { type: "message", role: "assistant", content: [{ type: "output_text", text: "hi" }] },
+      ],
+    })
+  }),
+)