test(ai): Add image input test for Anthropic Haiku 3.5

- Added image handling test for Claude 3.5 Haiku
- Ensures vision capabilities are properly tested

packages/ai/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@mariozechner/pi-ai",
-	"version": "0.5.13",
+	"version": "0.5.14",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./dist/index.js",

packages/ai/test/providers.test.ts

@@ -597,11 +597,11 @@ describe("AI Providers E2E Tests", () => {
         });
     });
 
-    describe.skipIf(!process.env.OPENROUTER_API_KEY)("OpenRouter Provider (Kimi K2)", () => {
+    describe.skipIf(!process.env.OPENROUTER_API_KEY)("OpenRouter Provider (GLM 4.5)", () => {
         let llm: OpenAICompletionsLLM;
 
         beforeAll(() => {
-            llm = createLLM("openrouter", "moonshotai/kimi-k2", process.env.OPENROUTER_API_KEY!);
+            llm = createLLM("openrouter", "z-ai/glm-4.5", process.env.OPENROUTER_API_KEY!);
         });
 
         it("should complete basic text generation", async () => {
@@ -651,5 +651,9 @@ describe("AI Providers E2E Tests", () => {
         it("should handle multi-turn with thinking and tools", async () => {
             await multiTurn(llm, {thinking: {enabled: true}});
         });
+
+        it("should handle image input", async () => {
+            await handleImage(llm);
+        });
     });
 });