fix: add explicit max_output_tokens for GPT-5 Responses API

- Added max_output_tokens parameter to GPT-5 request body using model.maxTokens
- This prevents GPT-5 from defaulting to very large token limits (e.g., 120k)
- Updated tests to expect max_output_tokens in GPT-5 request bodies
- Fixed test for handling unhandled stream events by properly mocking SDK fallback

Author: hannesrudolph

packages/types/src/message.ts

@@ -176,6 +176,17 @@ export const clineMessageSchema = z.object({
 	contextCondense: contextCondenseSchema.optional(),
 	isProtected: z.boolean().optional(),
 	apiProtocol: z.union([z.literal("openai"), z.literal("anthropic")]).optional(),
+	metadata: z
+		.object({
+			gpt5: z
+				.object({
+					previous_response_id: z.string().optional(),
+					instructions: z.string().optional(),
+					reasoning_summary: z.string().optional(),
+				})
+				.optional(),
+		})
+		.optional(),
 })
 
 export type ClineMessage = z.infer<typeof clineMessageSchema>

packages/types/src/provider-settings.ts

@@ -3,6 +3,11 @@ import { z } from "zod"
 import { reasoningEffortsSchema, verbosityLevelsSchema, modelInfoSchema } from "./model.js"
 import { codebaseIndexProviderSchema } from "./codebase-index.js"
 
+// Extended schema that includes "minimal" for GPT-5 models
+export const extendedReasoningEffortsSchema = z.union([reasoningEffortsSchema, z.literal("minimal")])
+
+export type ReasoningEffortWithMinimal = z.infer<typeof extendedReasoningEffortsSchema>
+
 /**
  * ProviderName
  */
@@ -76,7 +81,7 @@ const baseProviderSettingsSchema = z.object({
 
 	// Model reasoning.
 	enableReasoningEffort: z.boolean().optional(),
-	reasoningEffort: reasoningEffortsSchema.optional(),
+	reasoningEffort: extendedReasoningEffortsSchema.optional(),
 	modelMaxTokens: z.number().optional(),
 	modelMaxThinkingTokens: z.number().optional(),
 

packages/types/src/providers/openai.ts

@@ -12,6 +12,7 @@ export const openAiNativeModels = {
 		supportsImages: true,
 		supportsPromptCache: true,
 		supportsReasoningEffort: true,
+		reasoningEffort: "medium",
 		inputPrice: 1.25,
 		outputPrice: 10.0,
 		cacheReadsPrice: 0.13,
@@ -23,6 +24,7 @@ export const openAiNativeModels = {
 		supportsImages: true,
 		supportsPromptCache: true,
 		supportsReasoningEffort: true,
+		reasoningEffort: "medium",
 		inputPrice: 0.25,
 		outputPrice: 2.0,
 		cacheReadsPrice: 0.03,
@@ -34,6 +36,7 @@ export const openAiNativeModels = {
 		supportsImages: true,
 		supportsPromptCache: true,
 		supportsReasoningEffort: true,
+		reasoningEffort: "medium",
 		inputPrice: 0.05,
 		outputPrice: 0.4,
 		cacheReadsPrice: 0.01,
@@ -229,5 +232,6 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
 export const azureOpenAiDefaultApiVersion = "2024-08-01-preview"
 
 export const OPENAI_NATIVE_DEFAULT_TEMPERATURE = 0
+export const GPT5_DEFAULT_TEMPERATURE = 1.0
 
 export const OPENAI_AZURE_AI_INFERENCE_PATH = "/models/chat/completions"

src/api/index.ts

@@ -44,6 +44,7 @@ export interface SingleCompletionHandler {
 export interface ApiHandlerCreateMessageMetadata {
 	mode?: string
 	taskId: string
+	previousResponseId?: string
 }
 
 export interface ApiHandler {