feat(ai): add Qwen Token Plan as built-in provider (#6858)

Add Alibaba Cloud Model Studio Token Plan subscription service as two built-in API-key providers: qwen-token-plan (international, Singapore) and qwen-token-plan-cn (China, Beijing). Each provider exposes 15 text-generation models (Qwen, DeepSeek, GLM, Kimi, MiniMax) via the OpenAI-compatible endpoint with DashScope enable_thinking support. Model metadata is sourced from models.dev; qwen3.8-max-preview is hardcoded until models.dev includes it. Also fixes kimi-coding test references (k2p7 -> kimi-for-coding) after models.dev catalog update picked up by generate-models. Closes #6850
2026-07-20 19:53:30 +08:00
parent d9f7f81473
commit bbb91fa8ae
27 changed files with 605 additions and 0 deletions
@@ -1825,6 +1825,57 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			}
 		}

+		// Process Alibaba Cloud Model Studio Token Plan models
+		// Two regions (international / cn) with identical catalogs, separate
+		// endpoints and API keys (sk-sp- prefix). models.dev keys are
+		// "alibaba-token-plan[-cn]"; pi exposes them as "qwen-token-plan[-cn]".
+		const qwenTokenPlanCompat: OpenAICompletionsCompat = {
+			thinkingFormat: "qwen",
+			supportsDeveloperRole: false,
+			supportsStore: false,
+		};
+		const qwenTokenPlanVariants = [
+			{
+				source: "alibaba-token-plan",
+				provider: "qwen-token-plan",
+				baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
+			},
+			{
+				source: "alibaba-token-plan-cn",
+				provider: "qwen-token-plan-cn",
+				baseUrl: "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
+			},
+		] as const;
+
+		for (const { source, provider, baseUrl } of qwenTokenPlanVariants) {
+			const providerModels = data[source]?.models;
+			if (!providerModels) continue;
+
+			for (const [modelId, model] of Object.entries(providerModels)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider,
+					baseUrl,
+					compat: qwenTokenPlanCompat,
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
 		console.log(`Loaded ${models.length} tool-capable models from models.dev`);
 		return models;
 	} catch (error) {
@@ -2227,6 +2278,29 @@ async function generateModels() {
 		});
 	}

+	// Add qwen3.8-max-preview to Qwen Token Plan providers until models.dev includes it
+	for (const qwenTpProvider of ["qwen-token-plan", "qwen-token-plan-cn"] as const) {
+		if (!allModels.some((m) => m.provider === qwenTpProvider && m.id === "qwen3.8-max-preview")) {
+			const baseUrl =
+				qwenTpProvider === "qwen-token-plan"
+					? "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
+					: "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1";
+			allModels.push({
+				id: "qwen3.8-max-preview",
+				name: "Qwen3.8 Max Preview",
+				api: "openai-completions",
+				provider: qwenTpProvider,
+				baseUrl,
+				compat: { thinkingFormat: "qwen", supportsDeveloperRole: false, supportsStore: false } satisfies OpenAICompletionsCompat,
+				reasoning: true,
+				input: ["text", "image"],
+				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+				contextWindow: 1000000,
+				maxTokens: 65536,
+			});
+		}
+	}
+
 	// Add "auto" alias for openrouter/auto
 	if (!allModels.some(m => m.provider === "openrouter" && m.id === "auto")) {
 		allModels.push({