feat(sessions): add stop confirmation, health checks, and tunnel recreation

- Add inline confirmation dialog before stopping instances
- Delete instances from state immediately without page reload
- Add health check polling every 30s for running instances
- Show tunnel error badge when tunnel is unreachable
- Add 'Fix Tunnel' button to recreate broken tunnels
- Update API client with health check and tunnel recreation endpoints

apps/api/src/api/tool_instances.py

@@ -23,10 +23,12 @@ from src.models.tool_instance import ToolInstance
 from src.models.tool_type import ToolType
 from src.models.user import User
 from src.services.docker import (
+    check_tunnel_health,
     ensure_instance_directory,
     execute_compose_command,
     find_free_port,
     get_container_id,
+    recreate_tunnel,
     start_cloudflared_tunnel,
     stop_cloudflared_tunnel,
     get_container_name,
@@ -691,6 +693,114 @@ async def get_instance_logs(
     return {"logs": logs}
 
 
+@router.post(
+    "/{project_id}/repositories/{repo_id}/instances/{instance_id}/recreate-tunnel",
+    summary="Recreate tunnel",
+    description="Recreate the temporary Cloudflare tunnel for a running instance.",
+)
+async def recreate_tunnel_endpoint(
+    project_id: uuid.UUID,
+    repo_id: uuid.UUID,
+    instance_id: uuid.UUID,
+    user_id: uuid.UUID = Depends(get_current_user_id),
+    session: AsyncSession = Depends(get_db_session),
+) -> dict:
+    """Recreate the temporary tunnel for an instance.
+
+    Args:
+        project_id: UUID of the project.
+        repo_id: UUID of the repository.
+        instance_id: UUID of the instance.
+        user_id: ID of the authenticated user.
+        session: Database session.
+
+    Returns:
+        Dictionary with new URL and status.
+    """
+    _user = await _get_user(session, user_id)
+    _project = await _get_owned_project(project_id, user_id, session)
+
+    instance = await session.get(ToolInstance, instance_id)
+    if instance is None or instance.repository_id != repo_id:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail="instance not found"
+        )
+
+    if instance.status != "running":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="instance must be running to recreate tunnel",
+        )
+
+    # Get tool type for default port
+    tool_type = await session.get(ToolType, instance.tool_type_id)
+    instance_port = tool_type.default_port if tool_type and tool_type.default_port else 8080
+
+    try:
+        tunnel_info = recreate_tunnel(
+            container_name=instance.container_name or instance.name,
+            port=instance_port,
+            old_pid=instance.tunnel_id,
+        )
+        instance.tunnel_id = tunnel_info["pid"]
+        instance.public_url = tunnel_info["url"]
+        instance.url = tunnel_info["url"]
+        await session.commit()
+        logger.info(
+            "Recreated tunnel for instance %s: pid=%s, url=%s",
+            instance.id,
+            tunnel_info["pid"],
+            tunnel_info["url"],
+        )
+        return {"status": "healthy", "url": instance.url}
+    except Exception as exc:
+        logger.exception("Failed to recreate tunnel for instance %s", instance.id)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Failed to recreate tunnel: {str(exc)}",
+        )
+
+
+@router.get(
+    "/{project_id}/repositories/{repo_id}/instances/{instance_id}/health",
+    summary="Check tunnel health",
+    description="Check if the temporary Cloudflare tunnel for an instance is healthy.",
+)
+async def check_instance_tunnel_health(
+    project_id: uuid.UUID,
+    repo_id: uuid.UUID,
+    instance_id: uuid.UUID,
+    user_id: uuid.UUID = Depends(get_current_user_id),
+    session: AsyncSession = Depends(get_db_session),
+) -> dict:
+    """Check tunnel health for an instance.
+
+    Args:
+        project_id: UUID of the project.
+        repo_id: UUID of the repository.
+        instance_id: UUID of the instance.
+        user_id: ID of the authenticated user.
+        session: Database session.
+
+    Returns:
+        Dictionary with health status.
+    """
+    _user = await _get_user(session, user_id)
+    _project = await _get_owned_project(project_id, user_id, session)
+
+    instance = await session.get(ToolInstance, instance_id)
+    if instance is None or instance.repository_id != repo_id:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail="instance not found"
+        )
+
+    if not instance.url or instance.status != "running":
+        return {"healthy": False, "status_code": None, "error": "instance not running"}
+
+    health = check_tunnel_health(instance.url)
+    return health
+
+
 @router.get(
     "/{project_id}/repositories/{repo_id}/instances/{instance_id}/proxy/{path:path}",
     summary="Proxy to instance",

apps/api/src/services/docker.py

@@ -329,3 +329,57 @@ def stop_cloudflared_tunnel(pid: str) -> None:
         os.kill(int(pid), signal.SIGTERM)
     except ProcessLookupError:
         pass  # Already stopped
+
+
+def recreate_tunnel(
+    container_name: str, port: int, old_pid: str | None = None
+) -> dict[str, str]:
+    """Recreate a temporary Cloudflare tunnel.
+
+    Stops the old tunnel (if pid provided) and starts a new one.
+
+    Args:
+        container_name: Name of the Docker container to tunnel to
+        port: Port number the container listens on
+        old_pid: Optional PID of the old tunnel process to stop
+
+    Returns:
+        Dict with 'url' and 'pid' for the new tunnel
+    """
+    if old_pid:
+        stop_cloudflared_tunnel(old_pid)
+
+    return start_cloudflared_tunnel(container_name, port)
+
+
+def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, any]:
+    """Check if a tunnel URL is healthy.
+
+    Args:
+        url: The tunnel URL to check
+        timeout: Request timeout in seconds
+
+    Returns:
+        Dict with 'healthy' (bool) and 'status_code' (int or None)
+    """
+    import subprocess
+
+    try:
+        result = subprocess.run(
+            ["curl", "-s", "-o", "/dev/null", "-w", "%{http_code}",
+             "--max-time", str(timeout), url],
+            capture_output=True,
+            text=True,
+            timeout=timeout + 5,
+        )
+        status_code = int(result.stdout.strip())
+        return {
+            "healthy": 200 <= status_code < 400,
+            "status_code": status_code,
+        }
+    except (ValueError, subprocess.TimeoutExpired, Exception) as e:
+        return {
+            "healthy": False,
+            "status_code": None,
+            "error": str(e),
+        }