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

packages/ai/test/openai-completions-tool-choice.test.ts

@@ -1088,6 +1088,18 @@ describe("openai-completions tool_choice", () => {
 		}
 	});
 
+	it("stores Qwen Token Plan reasoning replay compat in built-in metadata", () => {
+		const providers = ["qwen-token-plan", "qwen-token-plan-cn"] as const;
+
+		for (const provider of providers) {
+			const model = getModel(provider, "qwen3.7-max")!;
+			expect(model.compat?.thinkingFormat).toBe("qwen");
+			expect(model.compat?.requiresReasoningContentOnAssistantMessages).toBeUndefined();
+			expect(model.compat?.supportsDeveloperRole).toBe(false);
+			expect(model.compat?.supportsStore).toBe(false);
+		}
+	});
+
 	it("replays Xiaomi MiMo assistant tool calls with empty reasoning_content when thinking is missing", async () => {
 		const model = getModel("xiaomi", "mimo-v2.5-pro")!;
 		const assistantMessage: AssistantMessage = {