feat(frontend): update sessions page for enhanced health monitoring

- Add new status badges: starting, probing, unhealthy
- Show tunnel error only when tunnel_status is unreachable
- Show app error badge with status code for error_response
- Add collapsible probe output section for diagnostics
- Update health polling to check all active instances
- Only show Recreate Tunnel button for unreachable tunnels
This commit is contained in:
Fusion
2026-05-22 21:26:05 +02:00
parent 2a9e57ad0d
commit d5f9df33b7
14 changed files with 779 additions and 49 deletions
+121 -14
View File
@@ -244,24 +244,94 @@ def connect_container_to_network(container_name: str, network_name: str = "backe
return result.returncode == 0
def get_container_status(container_id: str) -> str:
def get_container_status(container_id: str) -> dict[str, Any]:
"""Get the status of a Docker container.
Args:
container_id: Docker container ID
Returns:
Container status string (running, exited, etc.)
Dict with 'status' (running, exited, restarting, not_found),
'exit_code' (int or None), and 'health' (health status or None)
"""
result = subprocess.run(
["docker", "inspect", "-f", "{{.State.Status}}", container_id],
[
"docker", "inspect", "-f",
"{{.State.Status}}|{{.State.ExitCode}}|{{if .State.Health}}{{.State.Health.Status}}{{else}}none{{end}}",
container_id,
],
capture_output=True,
text=True,
)
if result.returncode == 0:
return result.stdout.strip()
return "unknown"
if result.returncode != 0:
return {"status": "not_found", "exit_code": None, "health": None}
parts = result.stdout.strip().split("|")
status = parts[0] if parts else "unknown"
exit_code = int(parts[1]) if len(parts) > 1 and parts[1].isdigit() else None
health = parts[2] if len(parts) > 2 and parts[2] != "none" else None
return {"status": status, "exit_code": exit_code, "health": health}
def wait_for_container_running(
container_id: str, timeout: int = 30, interval: float = 2.0
) -> dict[str, Any]:
"""Wait for a container to reach the running state.
Polls docker inspect until the container status is "running" or timeout.
Args:
container_id: Docker container ID
timeout: Maximum seconds to wait
interval: Seconds between polls
Returns:
Dict with 'success' (bool), 'status' (str), 'exit_code' (int or None),
and 'waited_seconds' (float)
"""
import time
start_time = time.time()
while time.time() - start_time < timeout:
info = get_container_status(container_id)
if info["status"] == "running":
return {
"success": True,
"status": "running",
"exit_code": None,
"waited_seconds": time.time() - start_time,
}
if info["status"] == "exited":
return {
"success": False,
"status": "exited",
"exit_code": info["exit_code"],
"waited_seconds": time.time() - start_time,
}
if info["status"] == "not_found":
return {
"success": False,
"status": "not_found",
"exit_code": None,
"waited_seconds": time.time() - start_time,
}
time.sleep(interval)
# Timeout reached
info = get_container_status(container_id)
return {
"success": False,
"status": info["status"],
"exit_code": info["exit_code"],
"waited_seconds": time.time() - start_time,
}
def get_container_logs(container_id: str, tail: int = 100) -> str:
@@ -424,14 +494,15 @@ def recreate_tunnel(
def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
"""Check if a tunnel URL is healthy.
"""Check if a tunnel URL is healthy with smart error classification.
Args:
url: The tunnel URL to check
timeout: Request timeout in seconds
Returns:
Dict with 'healthy' (bool) and 'status_code' (int or None)
Dict with 'tunnel_status' (healthy, unreachable, error_response, not_applicable),
'status_code' (int or None), 'healthy' (bool), and 'error' (str or None)
"""
import subprocess
@@ -444,13 +515,49 @@ def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
timeout=timeout + 5,
)
status_code = int(result.stdout.strip())
if 200 <= status_code < 400:
return {
"tunnel_status": "healthy",
"status_code": status_code,
"healthy": True,
"error": None,
}
elif status_code in (502, 503, 504):
# Application error, not tunnel error
return {
"tunnel_status": "error_response",
"status_code": status_code,
"healthy": False,
"error": f"Application returned HTTP {status_code}",
}
else:
return {
"tunnel_status": "error_response",
"status_code": status_code,
"healthy": False,
"error": f"HTTP {status_code}",
}
except subprocess.TimeoutExpired:
return {
"healthy": 200 <= status_code < 400,
"status_code": status_code,
}
except (ValueError, subprocess.TimeoutExpired, Exception) as e:
return {
"healthy": False,
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": "Tunnel request timed out",
}
except (ValueError, Exception) as e:
error_str = str(e).lower()
# Classify connection errors
if any(err in error_str for err in ["connection refused", "econnrefused", "could not resolve", "nodename"]):
return {
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": f"Tunnel unreachable: {e}",
}
return {
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": str(e),
}