feat: add /v1/models endpoint and systemd service for orchestrator

- Add OpenAI-compatible /v1/models endpoint to list available models
- Create systemd service file for proper service management
- Service runs as root with automatic restart on failure
- Logs to systemd journal for easy debugging

model-orchestrator/orchestrator.py

@@ -282,6 +282,27 @@ async def list_models():
     }
 
 
+@app.get("/v1/models")
+async def list_models_openai():
+    """OpenAI-compatible models listing endpoint"""
+    models_list = []
+    for model_name, model_info in model_registry.items():
+        models_list.append({
+            "id": model_name,
+            "object": "model",
+            "created": int(time.time()),
+            "owned_by": "pivoine-gpu",
+            "permission": [],
+            "root": model_name,
+            "parent": None,
+        })
+
+    return {
+        "object": "list",
+        "data": models_list
+    }
+
+
 @app.post("/v1/chat/completions")
 async def chat_completions(request: Request):
     """OpenAI-compatible chat completions endpoint (text models)"""