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)"""

systemd/ai-orchestrator.service

@@ -0,0 +1,24 @@
+[Unit]
+Description=AI Model Orchestrator for RunPod
+After=network.target
+StartLimitIntervalSec=0
+
+[Service]
+Type=simple
+Restart=always
+RestartSec=10
+User=root
+WorkingDirectory=/workspace/ai
+EnvironmentFile=/workspace/ai/.env
+ExecStart=/usr/bin/python3 /workspace/ai/model-orchestrator/orchestrator_subprocess.py
+StandardOutput=journal
+StandardError=journal
+SyslogIdentifier=ai-orchestrator
+
+# Process management
+KillMode=process
+KillSignal=SIGTERM
+TimeoutStopSec=30
+
+[Install]
+WantedBy=multi-user.target