fix: add controlled service restart console

backend/app/api/main.py

@@ -12,6 +12,7 @@ from app.api.v1 import (
     collected_data,
     visualization,
     bgp,
+    system_control,
 )
 
 api_router = APIRouter()
@@ -27,5 +28,6 @@ api_router.include_router(tasks.router, prefix="/tasks", tags=["tasks"])
 api_router.include_router(dashboard.router, prefix="/dashboard", tags=["dashboard"])
 api_router.include_router(alerts.router, prefix="/alerts", tags=["alerts"])
 api_router.include_router(settings.router, prefix="/settings", tags=["settings"])
+api_router.include_router(system_control.router, prefix="/system", tags=["system"])
 api_router.include_router(visualization.router, prefix="/visualization", tags=["visualization"])
 api_router.include_router(bgp.router, prefix="/bgp", tags=["bgp"])

backend/app/api/v1/system_control.py

@@ -0,0 +1,167 @@
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+
+from fastapi import APIRouter, Depends, HTTPException, status
+from pydantic import BaseModel
+
+from app.core.config import ROOT_DIR
+from app.core.security import get_current_user
+from app.models.user import User
+from app.services.system_control import (
+    build_task_id,
+    clear_active_task_id,
+    get_active_task_id,
+    get_allowed_command,
+    get_runner_script_path,
+    is_task_stale,
+    get_task_logs,
+    require_super_admin,
+    serialize_task,
+    set_active_task_id,
+    upsert_task_state,
+)
+
+router = APIRouter()
+
+
+class RestartTaskCreate(BaseModel):
+    action: str
+
+
+class RestartTaskResponse(BaseModel):
+    task_id: str
+    action: str
+    status: str
+    stage: str
+    message: str
+    created_at: str
+    updated_at: str
+    requested_by: dict[str, object] | None = None
+
+
+class RestartTaskLogsResponse(BaseModel):
+    task_id: str
+    lines: list[str]
+
+
+def ensure_super_admin(current_user: User) -> None:
+    if not require_super_admin(current_user.role):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Only super_admin can restart services",
+        )
+
+
+@router.post("/restart-tasks", response_model=RestartTaskResponse)
+async def create_restart_task(
+    payload: RestartTaskCreate,
+    current_user: User = Depends(get_current_user),
+):
+    ensure_super_admin(current_user)
+
+    command = get_allowed_command(payload.action)
+    if command is None:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="Unsupported system action",
+        )
+
+    active_task_id = get_active_task_id()
+    if active_task_id:
+        active_task = serialize_task(active_task_id)
+        if active_task and is_task_stale(active_task):
+            upsert_task_state(
+                active_task_id,
+                status="failed",
+                stage="failed",
+                message="Previous restart task became stale and was released",
+            )
+            clear_active_task_id(active_task_id)
+        elif active_task and active_task.get("status") in {"queued", "running"}:
+            raise HTTPException(
+                status_code=status.HTTP_409_CONFLICT,
+                detail="Another restart task is already in progress",
+            )
+
+    task_id = build_task_id()
+    requested_by = {"id": current_user.id, "username": current_user.username}
+    task_state = upsert_task_state(
+        task_id,
+        action=payload.action,
+        status="queued",
+        stage="accepted",
+        message="Restart task accepted",
+        requested_by=requested_by,
+    )
+    set_active_task_id(task_id)
+
+    env = os.environ.copy()
+    backend_path = str(ROOT_DIR / "backend")
+    existing_pythonpath = env.get("PYTHONPATH", "")
+    env["PYTHONPATH"] = (
+        f"{backend_path}{os.pathsep}{existing_pythonpath}"
+        if existing_pythonpath
+        else backend_path
+    )
+
+    try:
+        subprocess.Popen(
+            [
+                sys.executable,
+                str(get_runner_script_path()),
+                "--task-id",
+                task_id,
+                "--action",
+                payload.action,
+            ],
+            cwd=str(ROOT_DIR),
+            env=env,
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+            start_new_session=True,
+        )
+    except OSError as exc:
+        task_state = upsert_task_state(
+            task_id,
+            action=payload.action,
+            status="failed",
+            stage="failed",
+            message=f"Unable to start restart runner: {exc}",
+            requested_by=requested_by,
+        )
+        clear_active_task_id(task_id)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=task_state["message"],
+        ) from exc
+
+    return task_state
+
+
+@router.get("/restart-tasks/{task_id}", response_model=RestartTaskResponse)
+async def get_restart_task(
+    task_id: str,
+    current_user: User = Depends(get_current_user),
+):
+    ensure_super_admin(current_user)
+
+    task = serialize_task(task_id)
+    if task is None:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Restart task not found")
+    return task
+
+
+@router.get("/restart-tasks/{task_id}/logs", response_model=RestartTaskLogsResponse)
+async def get_restart_task_logs(
+    task_id: str,
+    current_user: User = Depends(get_current_user),
+):
+    ensure_super_admin(current_user)
+
+    task = serialize_task(task_id)
+    if task is None:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Restart task not found")
+    return {"task_id": task_id, "lines": get_task_logs(task_id)}