batchCooking/apps/admin-web/src/pages/monitoring/MonitoringPage.tsx
Nicolas b61636f73d feat(admin): monitoring des microservices + heartbeat du worker LLM
PR 4 du chantier admin. Board de sante temps reel des dependances.

- POST /internal/tech-steps/heartbeat (requireInternalWorker) ->
  recordWorkerHeartbeat : upsert WorkerHeartbeat (cle fixe
  "tech-step-llm-worker"), lastRunAt/lastResult pour un ping "job".
  Schema workerHeartbeatSchema dans packages/shared.
- services/tech-step-llm-worker : api-client.postHeartbeat (best-effort,
  ne throw jamais) appele au boot (index.ts), a chaque tick et apres
  chaque job (scheduler.ts, avec job/ok/counts).
- admin-monitoring.service.ts + GET /admin/monitoring (requireAdmin) :
  sonde active bornee (~2 s) de Postgres (SELECT 1), l'API (uptime/RSS),
  tech-step-intent-service (/health), et le worker via son heartbeat.
  Statut up/degraded/down/unknown ; une sonde down ne casse ni les autres
  ni l'endpoint. Seuils worker : > 8 j degraded, > 21 j down.
- MonitoringView / ServiceHealthView dans packages/shared.
- Front : MonitoringPage (grille de cartes coloree par statut, re-poll
  15 s), logique pure monitoring.ts, i18n admin.monitoring.*,
  AdminApiClient.getMonitoring.
- Tests : Mocha admin-monitoring.test.ts (heartbeat 401/400/upsert
  job+boot ; GET /admin/monitoring 401, board 4 cibles, worker unknown
  sans heartbeat puis up apres) ; Cypress monitoring.cy.ts (2 verts).
  Worker mocha : 6/6 toujours verts.
- specs/backend-architecture.md : section monitoring. .gitignore :
  apps/admin-web/cypress/{screenshots,videos,downloads}.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-28 19:05:41 +02:00

110 lines
3.6 KiB
TypeScript

import type { MonitoringView, ServiceHealthView } from "@batch-cooking/shared";
import { useEffect, useState } from "react";
import { useTranslation } from "react-i18next";
import { adminApiClient } from "../../api/client";
import "../admin-page.scss";
import "./monitoring-page.scss";
import { clockTime, POLL_INTERVAL_MS, statusModifier } from "./monitoring";
type MonitoringState =
| { status: "loading" }
| { status: "loaded"; data: MonitoringView }
| { status: "error" };
/**
* Microservice health board. Fetches `GET /admin/monitoring` on mount and
* re-polls every {@link POLL_INTERVAL_MS} ms. One card per probed target
* (Postgres, API, intent-service, LLM worker), coloured by status.
*/
export function MonitoringPage() {
const { t } = useTranslation();
const [state, setState] = useState<MonitoringState>({ status: "loading" });
useEffect(() => {
let cancelled = false;
function load() {
adminApiClient
.getMonitoring()
.then((data) => {
if (!cancelled) setState({ status: "loaded", data });
})
.catch(() => {
if (!cancelled)
setState((prev) => (prev.status === "loaded" ? prev : { status: "error" }));
});
}
load();
const timer = setInterval(load, POLL_INTERVAL_MS);
return () => {
cancelled = true;
clearInterval(timer);
};
}, []);
return (
<div className="admin-page">
<h1 className="admin-page__title">{t("admin.monitoring.title")}</h1>
<p className="admin-page__lead">{t("admin.monitoring.lead")}</p>
{state.status === "loading" && (
<p className="admin-page__placeholder">{t("admin.common.loading")}</p>
)}
{state.status === "error" && (
<p className="admin-page__placeholder">{t("admin.common.loadError")}</p>
)}
{state.status === "loaded" && (
<>
<p className="monitoring-checked">
{t("admin.monitoring.lastChecked", { time: clockTime(state.data.generatedAt) })}
</p>
<div className="monitoring-grid">
{state.data.services.map((service) => (
<ServiceCard key={service.key} service={service} />
))}
</div>
</>
)}
</div>
);
}
function ServiceCard({ service }: { service: ServiceHealthView }) {
const { t } = useTranslation();
return (
<article className={`monitoring-card monitoring-card--${statusModifier(service.status)}`}>
<header className="monitoring-card__head">
<span className="monitoring-card__dot" aria-hidden="true" />
<h2>{t(`admin.monitoring.service.${service.key}`, { defaultValue: service.key })}</h2>
<span className="monitoring-card__status">
{t(`admin.monitoring.status.${service.status}`)}
</span>
</header>
<dl className="monitoring-card__meta">
{service.latencyMs !== null && (
<div>
<dt>{t("admin.monitoring.latency")}</dt>
<dd>{service.latencyMs} ms</dd>
</div>
)}
{service.detail && (
<div>
<dt>{t("admin.monitoring.detail")}</dt>
<dd>{service.detail}</dd>
</div>
)}
{service.lastRunAt !== undefined && (
<div>
<dt>{t("admin.monitoring.lastRun")}</dt>
<dd>
{service.lastRunAt ? clockTime(service.lastRunAt) : t("admin.monitoring.never")}
{service.lastResult?.job ? ` · ${service.lastResult.job}` : ""}
{service.lastResult?.ok === false ? ` · ${t("admin.monitoring.jobFailed")}` : ""}
</dd>
</div>
)}
</dl>
</article>
);
}