alex/headquarter
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files
apps/api/src/api/tool_instances.py
+135 -24
View File
@@ -30,11 +30,14 @@ from src.services.docker import (
execute_compose_command,
find_free_port,
get_container_id,
get_container_logs,
get_container_name,
get_container_status,
recreate_tunnel,
render_compose_template,
start_cloudflared_tunnel,
stop_cloudflared_tunnel,
wait_for_container_running,
write_compose_file,
write_config_files,
write_env_file,
@@ -552,20 +555,67 @@ async def start_instance(
else:
logger.warning("Failed to connect %s to backend network", container_name)
instance.status = "starting"
instance.last_started_at = datetime.now()
await session.commit()
logger.info("Instance %s container is running, checking readiness", instance.id)
# Verify container reached running state
if instance.container_id:
instance.status = "starting"
instance.last_started_at = datetime.now()
await session.commit()
logger.info("Instance %s: verifying container startup...", instance.id)
startup_result = wait_for_container_running(instance.container_id, timeout=30, interval=2.0)
if not startup_result["success"]:
# Container failed to start
error_msg = f"Container failed to start: status={startup_result['status']}"
if startup_result["exit_code"] is not None:
error_msg += f", exit_code={startup_result['exit_code']}"
# Get logs for debugging
logs = get_container_logs(instance.container_id, tail=50)
instance.status = "error"
await session.commit()
logger.error(
"Instance %s container startup failed after %.1fs: %s\nLogs:\n%s",
instance.id,
startup_result["waited_seconds"],
error_msg,
logs,
)
return {
"status": "error",
"error": error_msg,
"logs": logs,
}
logger.info(
"Instance %s container started successfully after %.1fs",
instance.id,
startup_result["waited_seconds"],
)
# Execute readiness probe if configured
tool_type = await session.get(ToolType, instance.tool_type_id)
if tool_type and tool_type.readiness_probe:
probe_config = tool_type.readiness_probe
probe_command = probe_config.get("command", "")
probe_timeout = probe_config.get("timeout", 30)
probe_interval = probe_config.get("interval", 2)
if tool_type and instance.container_id:
# Determine probe command
probe_command = None
probe_timeout = 30
probe_interval = 2
if probe_command and instance.container_id:
if tool_type.readiness_probe:
probe_config = tool_type.readiness_probe
probe_command = probe_config.get("command", "")
probe_timeout = probe_config.get("timeout", 30)
probe_interval = probe_config.get("interval", 2)
elif "web" in (tool_type.interfaces or []):
# Default probe for web tools
probe_command = f"curl -f http://localhost:{tool_type.default_port or 8080}"
probe_timeout = 30
probe_interval = 2
if probe_command:
instance.status = "probing"
await session.commit()
logger.info(
"Executing readiness probe for instance %s: command='%s', timeout=%d, interval=%d",
instance.id, probe_command, probe_timeout, probe_interval
@@ -578,14 +628,25 @@ async def start_instance(
interval=probe_interval,
)
# Store probe result
instance.probe_result = {
"success": success,
"command": probe_command,
"logs": probe_logs,
"timestamp": datetime.now().isoformat(),
}
if not success:
instance.status = "failed"
instance.url = None
instance.public_url = None
instance.status = "unhealthy"
await session.commit()
logger.error("Readiness probe failed for instance %s: %s", instance.id, "\n".join(probe_logs))
logger.error(
"Readiness probe failed for instance %s after %ds: %s",
instance.id,
probe_timeout,
"\n".join(probe_logs),
)
return {
"status": "failed",
"status": "unhealthy",
"error": f"Readiness probe failed after {probe_timeout}s",
"probe_logs": probe_logs,
}
@@ -956,6 +1017,17 @@ async def recreate_tunnel_endpoint(
detail="instance must be running to recreate tunnel",
)
# Validate tunnel is actually broken before recreating
if instance.url:
tunnel_health = check_tunnel_health(instance.url)
if tunnel_health["tunnel_status"] == "error_response":
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"Tunnel is working but application returned HTTP {tunnel_health.get('status_code')}. Recreating the tunnel will not fix this issue.",
)
elif tunnel_health["tunnel_status"] == "healthy":
return {"status": "healthy", "url": instance.url, "message": "Tunnel is already healthy"}
# 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
@@ -987,8 +1059,8 @@ async def recreate_tunnel_endpoint(
@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.",
summary="Check instance health",
description="Check container and tunnel health for an instance.",
)
async def check_instance_tunnel_health(
project_id: uuid.UUID,
@@ -997,7 +1069,7 @@ async def check_instance_tunnel_health(
user_id: uuid.UUID = Depends(get_current_user_id),
session: AsyncSession = Depends(get_db_session),
) -> dict:
"""Check tunnel health for an instance.
"""Check health for an instance (container + tunnel).
Args:
project_id: UUID of the project.
@@ -1007,7 +1079,7 @@ async def check_instance_tunnel_health(
session: Database session.
Returns:
Dictionary with health status.
Dictionary with container_status, tunnel_status, probe_status, and overall healthy flag.
"""
_user = await _get_user(session, user_id)
_project = await _get_owned_project(project_id, user_id, session)
@@ -1018,11 +1090,50 @@ async def check_instance_tunnel_health(
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"}
# Check container status
container_info = {"status": "not_found", "exit_code": None, "health": None}
if instance.container_id:
container_info = get_container_status(instance.container_id)
health = check_tunnel_health(instance.url)
return health
# Build response
response = {
"healthy": False,
"container_status": container_info["status"],
"container_health": container_info["health"],
"tunnel_status": "not_applicable",
"tunnel_status_code": None,
"probe_status": "not_applicable",
"last_probe_output": None,
"error": None,
}
# Determine probe status
if instance.status == "probing":
response["probe_status"] = "pending"
elif instance.probe_result:
response["probe_status"] = "success" if instance.probe_result.get("success") else "failed"
response["last_probe_output"] = "\n".join(instance.probe_result.get("logs", []))[:500]
# Check tunnel health if instance has a URL and is web-enabled
if instance.url and instance.status in ("running", "unhealthy"):
tunnel_health = check_tunnel_health(instance.url)
response["tunnel_status"] = tunnel_health["tunnel_status"]
response["tunnel_status_code"] = tunnel_health.get("status_code")
if tunnel_health.get("error"):
response["error"] = tunnel_health["error"]
# Overall healthy only if container is running AND tunnel is healthy
container_healthy = container_info["status"] == "running"
tunnel_healthy = response["tunnel_status"] == "healthy"
response["healthy"] = container_healthy and tunnel_healthy
# If container is not running, override error message
if not container_healthy:
response["error"] = f"Container is {container_info['status']}"
if container_info["exit_code"] is not None:
response["error"] += f" (exit code: {container_info['exit_code']})"
return response
@router.get(
apps/api/src/models/tool_instance.py
+4 -1
View File
@@ -2,7 +2,7 @@ import uuid
from datetime import datetime
from typing import TYPE_CHECKING
from sqlalchemy import DateTime, ForeignKey, Integer, String
from sqlalchemy import DateTime, ForeignKey, Integer, JSON, String
from sqlalchemy import Uuid as UUID
from sqlalchemy.orm import Mapped, mapped_column, relationship
@@ -62,6 +62,9 @@ class ToolInstance(UUIDPrimaryKeyMixin, TimestampMixin, Base):
last_stopped_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
probe_result: Mapped[dict | None] = mapped_column(
JSON, nullable=True
)
tool_type: Mapped["ToolType"] = relationship()
repository: Mapped["GitRepository"] = relationship()
apps/api/src/services/docker.py
+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),
}