feat: add GPT-5 models with updated context windows

- Added gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-nano-2025-08-07 models
- All GPT-5 models configured with 400,000 context window
- Updated nectarine model context window to 256,000
- All models configured with reasoning effort support
- Set gpt-5-2025-08-07 as default OpenAI Native model
- Added GPT-5 model handling in openai-native.ts
- Updated tests to reflect new default model

packages/types/src/providers/openai.ts

@@ -3,10 +3,10 @@ import type { ModelInfo } from "../model.js"
 // https://openai.com/api/pricing/
 export type OpenAiNativeModelId = keyof typeof openAiNativeModels
 
-export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-4o"
+export const openAiNativeDefaultModelId: OpenAiNativeModelId = "gpt-5-2025-08-07"
 
 export const openAiNativeModels = {
-	"nectarine-alpha-new-reasoning-effort-2025-07-25": {
+	"gpt-5-2025-08-07": {
 		maxTokens: 128000,
 		contextWindow: 400000,
 		supportsImages: true,
@@ -16,6 +16,36 @@ export const openAiNativeModels = {
 		outputPrice: 0,
 		cacheReadsPrice: 0,
 	},
+	"gpt-5-mini-2025-08-07": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: true,
+		inputPrice: 0,
+		outputPrice: 0,
+		cacheReadsPrice: 0,
+	},
+	"gpt-5-nano-2025-08-07": {
+		maxTokens: 128000,
+		contextWindow: 400000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: true,
+		inputPrice: 0,
+		outputPrice: 0,
+		cacheReadsPrice: 0,
+	},
+	"nectarine-alpha-new-reasoning-effort-2025-07-25": {
+		maxTokens: 128000,
+		contextWindow: 256000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningEffort: true,
+		inputPrice: 0,
+		outputPrice: 0,
+		cacheReadsPrice: 0,
+	},
 	"gpt-4.1": {
 		maxTokens: 32_768,
 		contextWindow: 1_047_576,

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

@@ -455,7 +455,7 @@ describe("OpenAiNativeHandler", () => {
 				openAiNativeApiKey: "test-api-key",
 			})
 			const modelInfo = handlerWithoutModel.getModel()
-			expect(modelInfo.id).toBe("gpt-4o") // Default model
+			expect(modelInfo.id).toBe("gpt-5-2025-08-07") // Default model
 			expect(modelInfo.info).toBeDefined()
 		})
 	})

src/api/providers/openai-native.ts

@@ -53,7 +53,7 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 			yield* this.handleReasonerMessage(model, id, systemPrompt, messages)
 		} else if (model.id.startsWith("o1")) {
 			yield* this.handleO1FamilyMessage(model, systemPrompt, messages)
-		} else if (this.isNectarineModel(model.id)) {
+		} else if (this.isNectarineModel(model.id) || this.isGpt5Model(model.id)) {
 			yield* this.handleNectarineMessage(model, systemPrompt, messages)
 		} else {
 			yield* this.handleDefaultModelMessage(model, systemPrompt, messages)
@@ -154,6 +154,10 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 		return modelId.includes("nectarine")
 	}
 
+	private isGpt5Model(modelId: string): boolean {
+		return modelId.startsWith("gpt-5")
+	}
+
 	private async *handleStreamResponse(
 		stream: AsyncIterable<OpenAI.Chat.Completions.ChatCompletionChunk>,
 		model: OpenAiNativeModel,