feat(dashboard): add HTTP health probe for cross-container gateway detection

The dashboard's gateway status detection relied solely on local PID checks
(os.kill + /proc), which fails when the gateway runs in a separate container.

Changes:
- web_server.py: Add _probe_gateway_health() that queries the gateway's HTTP
  /health/detailed endpoint when the local PID check fails. Activated by
  setting the GATEWAY_HEALTH_URL env var (e.g. http://gateway:8642/health).
  Falls back to standard PID check when the env var is not set.
- api_server.py: Add GET /health/detailed endpoint that returns full gateway
  state (platforms, gateway_state, active_agents, pid, etc.) without auth.
  The existing GET /health remains unchanged for backwards compatibility.
- StatusPage.tsx: Handle the case where gateway_pid is null but the gateway
  is running remotely, displaying 'Running (remote)' instead of 'PID null'.

Environment variables:
- GATEWAY_HEALTH_URL: URL of the gateway health endpoint (e.g.
  http://gateway-container:8642/health). Unset = local PID check only.
- GATEWAY_HEALTH_TIMEOUT: Probe timeout in seconds (default: 3).
This commit is contained in:
Hermes Agent
2026-04-14 05:17:17 +00:00
committed by Teknium
parent 397386cae2
commit 45595f4805
6 changed files with 78 additions and 1 deletions

View File

@@ -80,6 +80,7 @@ export const en: Translations = {
notRunning: "Not running",
startFailed: "Start failed",
pid: "PID",
runningRemote: "Running (remote)",
noneRunning: "None",
gatewayFailedToStart: "Gateway failed to start",
lastUpdate: "Last update",

View File

@@ -83,6 +83,7 @@ export interface Translations {
notRunning: string;
startFailed: string;
pid: string;
runningRemote: string;
noneRunning: string;
gatewayFailedToStart: string;
lastUpdate: string;

View File

@@ -80,6 +80,7 @@ export const zh: Translations = {
notRunning: "未运行",
startFailed: "启动失败",
pid: "进程",
runningRemote: "运行中(远程)",
noneRunning: "无",
gatewayFailedToStart: "网关启动失败",
lastUpdate: "最后更新",

View File

@@ -53,7 +53,8 @@ export default function StatusPage() {
};
function gatewayValue(): string {
if (status!.gateway_running) return `${t.status.pid} ${status!.gateway_pid}`;
if (status!.gateway_running && status!.gateway_pid) return `${t.status.pid} ${status!.gateway_pid}`;
if (status!.gateway_running) return t.status.runningRemote;
if (status!.gateway_state === "startup_failed") return t.status.startFailed;
return t.status.notRunning;
}