feat(infra): p6 hardening - observability and deploy compose

- 5 NestJS services add /metrics endpoint via app.getHttpAdapter()
- prometheus.yml scales to 8 services with rule_files and alertmanager
- monitoring compose replaces blackbox with Loki+Promtail
- Grafana datasource adds Loki
- docker-compose.deploy.yml scales to 11 services
- deploy.env.example completes Neo4j/ES/ClickHouse/LLM vars
- teacher-bff adds health.controller
- CI removes continue-on-error on lint step
- teacher-portal lint script changed to eslint src
This commit is contained in:
SpecialX
2026-07-09 10:21:06 +08:00
parent 3ca654619f
commit 566060fade
21 changed files with 554 additions and 59 deletions

View File

@@ -7,6 +7,7 @@ import { env } from "./config/env.js";
import { logger } from "./shared/observability/logger.js";
import { checkEsConnection, closeEs } from "./config/elasticsearch.js";
import { closeDb } from "./config/database.js";
import { metricsRegistry } from "./shared/observability/metrics.js";
async function bootstrap(): Promise<void> {
initTracer();
@@ -22,6 +23,13 @@ async function bootstrap(): Promise<void> {
app.useGlobalFilters(new GlobalErrorFilter());
app.enableShutdownHooks();
// Prometheus 指标端点:不鉴权,供 Prometheus 抓取。
// 返回 register.metrics()Promise<string>,含 Content-Type text/plain; version=0.0.4; charset=utf-8
app.getHttpAdapter().get("/metrics", async (req, res) => {
res.set("Content-Type", metricsRegistry.contentType);
res.end(await metricsRegistry.metrics());
});
await app.listen(env.PORT);
logger.info({ port: env.PORT }, "Msg service started");