Fix OpenRouter model: use deepseek-chat-v3 (was invalid model)

The previous model openai/gpt-oss-120b:free doesn't exist (404).
Changed to deepseek/deepseek-chat-v3-0324:free which is a valid
free model on OpenRouter.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/llm_client.py

@@ -50,7 +50,7 @@ class LLMClient:
             self.providers.append({
                 "name": "openrouter",
                 "key": openrouter_key,
-                "model": os.getenv("OPENROUTER_MODEL", "openai/gpt-oss-120b:free"),
+                "model": os.getenv("OPENROUTER_MODEL", "deepseek/deepseek-chat-v3-0324:free"),
                 "url": "https://openrouter.ai/api/v1/chat/completions"
             })