Initial commit: FaceFusion REST API

FastAPI wrapper around FaceFusion v3.5.3 submodule with:
- Sync and async (job-based) processing endpoints
- FaceFusion bridge with manual key registration and Lock-serialized processing
- Multi-target Dockerfile (CPU + CUDA GPU)
- Docker Compose configs for dev, prod-cpu, and prod-gpu
- Gitea CI/CD workflow with dual image builds
- All 11 FaceFusion processors supported via options API

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/routers/system.py

@@ -0,0 +1,56 @@
+import logging
+import os
+
+import psutil
+
+from fastapi import APIRouter
+
+from app.schemas.system import GpuDevice, HealthResponse, SystemInfoResponse
+from app.services import facefusion_bridge
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix='/api/v1', tags=['system'])
+
+
+@router.get('/health', response_model=HealthResponse)
+async def health_check():
+    return HealthResponse()
+
+
+@router.get('/system', response_model=SystemInfoResponse)
+async def system_info():
+    providers = facefusion_bridge.get_execution_providers()
+    gpu_devices = _detect_gpu_devices()
+    mem = psutil.virtual_memory()
+
+    return SystemInfoResponse(
+        execution_providers=providers,
+        gpu_devices=gpu_devices,
+        cpu_count=os.cpu_count(),
+        memory_total=mem.total,
+        memory_available=mem.available,
+    )
+
+
+def _detect_gpu_devices():
+    devices = []
+    try:
+        import subprocess
+        result = subprocess.run(
+            ['nvidia-smi', '--query-gpu=index,name,memory.total,memory.used', '--format=csv,noheader,nounits'],
+            capture_output=True, text=True, timeout=5,
+        )
+        if result.returncode == 0:
+            for line in result.stdout.strip().split('\n'):
+                parts = [p.strip() for p in line.split(',')]
+                if len(parts) >= 4:
+                    devices.append(GpuDevice(
+                        id=int(parts[0]),
+                        name=parts[1],
+                        memory_total=int(float(parts[2])) * 1024 * 1024,
+                        memory_used=int(float(parts[3])) * 1024 * 1024,
+                    ))
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        pass
+    return devices