feat: Add GPT-5 Pro with background mode auto-resume and polling

packages/types/src/model.ts

@@ -63,6 +63,9 @@ export const modelInfoSchema = z.object({
 	supportsReasoningBudget: z.boolean().optional(),
 	// Capability flag to indicate whether the model supports temperature parameter
 	supportsTemperature: z.boolean().optional(),
+	// When true, this model must be invoked using Responses background mode.
+	// Providers should auto-enable background:true, stream:true, and store:true.
+	backgroundMode: z.boolean().optional(),
 	requiredReasoningBudget: z.boolean().optional(),
 	supportsReasoningEffort: z.boolean().optional(),
 	supportedParameters: z.array(modelParametersSchema).optional(),

packages/types/src/provider-settings.ts

@@ -297,6 +297,15 @@ const openAiNativeSchema = apiModelIdProviderModelSchema.extend({
 	// OpenAI Responses API service tier for openai-native provider only.
 	// UI should only expose this when the selected model supports flex/priority.
 	openAiNativeServiceTier: serviceTierSchema.optional(),
+	// Enable OpenAI Responses background mode when using Responses API.
+	// Opt-in; defaults to false when omitted.
+	openAiNativeBackgroundMode: z.boolean().optional(),
+	// Background auto-resume/poll settings (no UI; plumbed via options)
+	openAiNativeBackgroundAutoResume: z.boolean().optional(),
+	openAiNativeBackgroundResumeMaxRetries: z.number().int().min(0).optional(),
+	openAiNativeBackgroundResumeBaseDelayMs: z.number().int().min(0).optional(),
+	openAiNativeBackgroundPollIntervalMs: z.number().int().min(0).optional(),
+	openAiNativeBackgroundPollMaxMinutes: z.number().int().min(1).optional(),
 })
 
 const mistralSchema = apiModelIdProviderModelSchema.extend({

packages/types/src/providers/openai.ts

@@ -37,6 +37,21 @@ export const openAiNativeModels = {
 			{ name: "priority", contextWindow: 400000, inputPrice: 2.5, outputPrice: 20.0, cacheReadsPrice: 0.25 },
 		],
 	},
+	"gpt-5-pro-2025-10-06": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: false,
+		supportsReasoningEffort: false, // This is set to false to prevent the ui from displaying the reasoning effort selector
+		reasoningEffort: "high", // Pro model uses high reasoning effort by default and must be specified
+		inputPrice: 15.0,
+		outputPrice: 120.0,
+		description:
+			"GPT-5 Pro: A slow, reasoning-focused model for complex problems. Uses background mode with resilient streaming — requests may take some time and will automatically reconnect if they time out.",
+		supportsVerbosity: true,
+		supportsTemperature: false,
+		backgroundMode: true,
+	},
 	"gpt-5-mini-2025-08-07": {
 		maxTokens: 128000,
 		contextWindow: 400000,

src/api/providers/__tests__/openai-native-usage.spec.ts

@@ -344,6 +344,38 @@ describe("OpenAiNativeHandler - normalizeUsage", () => {
 		})
 	})
 
+	it("should produce identical usage chunk when background mode is enabled", () => {
+		const usage = {
+			input_tokens: 120,
+			output_tokens: 60,
+			cache_creation_input_tokens: 10,
+			cache_read_input_tokens: 30,
+		}
+
+		const baselineHandler = new OpenAiNativeHandler({
+			openAiNativeApiKey: "test-key",
+			apiModelId: "gpt-5-pro-2025-10-06",
+		})
+		const backgroundHandler = new OpenAiNativeHandler({
+			openAiNativeApiKey: "test-key",
+			apiModelId: "gpt-5-pro-2025-10-06",
+			openAiNativeBackgroundMode: true,
+		})
+
+		const baselineUsage = (baselineHandler as any).normalizeUsage(usage, baselineHandler.getModel())
+		const backgroundUsage = (backgroundHandler as any).normalizeUsage(usage, backgroundHandler.getModel())
+
+		expect(baselineUsage).toMatchObject({
+			type: "usage",
+			inputTokens: 120,
+			outputTokens: 60,
+			cacheWriteTokens: 10,
+			cacheReadTokens: 30,
+			totalCost: expect.any(Number),
+		})
+		expect(backgroundUsage).toEqual(baselineUsage)
+	})
+
 	describe("cost calculation", () => {
 		it("should pass total input tokens to calculateApiCostOpenAI", () => {
 			const usage = {