fix: remove nectarine experimental model

- Removed nectarine-alpha-new-reasoning-effort-2025-07-25 from openai.ts
- Removed nectarine handling from openai-native.ts (renamed to handleGpt5Message)
- Removed associated changeset file
- Keep GPT-5 models with developer role handling

Author: hannesrudolph

.changeset/gpt5-support.md

@@ -36,16 +36,6 @@ export const openAiNativeModels = {
 		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,

packages/types/src/providers/openai.ts

@@ -53,8 +53,8 @@ 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) || this.isGpt5Model(model.id)) {
-			yield* this.handleNectarineMessage(model, systemPrompt, messages)
+		} else if (this.isGpt5Model(model.id)) {
+			yield* this.handleGpt5Message(model, systemPrompt, messages)
 		} else {
 			yield* this.handleDefaultModelMessage(model, systemPrompt, messages)
 		}
@@ -131,7 +131,7 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 		yield* this.handleStreamResponse(stream, model)
 	}
 
-	private async *handleNectarineMessage(
+	private async *handleGpt5Message(
 		model: OpenAiNativeModel,
 		systemPrompt: string,
 		messages: Anthropic.Messages.MessageParam[],
@@ -150,10 +150,6 @@ export class OpenAiNativeHandler extends BaseProvider implements SingleCompletio
 		yield* this.handleStreamResponse(stream, model)
 	}
 
-	private isNectarineModel(modelId: string): boolean {
-		return modelId.includes("nectarine")
-	}
-
 	private isGpt5Model(modelId: string): boolean {
 		return modelId.startsWith("gpt-5")
 	}