fix(system): retired heartbeat rows no longer alarm on status page

- GET /system/health splits processes into current instances (hosts with
  a beat in the last 10 min, newest per host+kind, not stopped) and
  retiredProcesses[]; 45s stale and level only consider current ones
- heartbeat writer marks stopped_at on graceful exit (migration 0043),
  upsert clears it; pure api role now stops its writer on SIGTERM
- scheduled job system.heartbeat_cleanup (maintain, 1h) deletes rows
  without a beat for 24h and samples older than 7 days
- status page: per-role alarms ("io worker 45 秒没有心跳"), collapsible
  retired instances; glossary/runbook updated
- bump all members to 0.2.2, CHANGELOG [0.2.2]

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
rootandClaude Opus 5.5 committed 2026-09-28 23:31:21 +08:00
1 parent fa261eb6cd
commit b4c9b1ead2
32 files changed
+747 -91

No files matched your search

+25
View File
@@ -2167,6 +2167,31 @@ export const Api = {
query: browser.BrowserProvidersQuery,
response: z.object({ items: z.array(browser.BrowserProviderView) }),
}),
createProvider: ep({
method: "post",
path: "/browser/providers",
scope: "admin",
summary: "登记浏览器服务(camofox 地址、访问凭据存凭证库、启用)",
body: browser.BrowserProviderCreate,
response: browser.BrowserProviderView,
}),
updateProvider: ep({
method: "patch",
path: "/browser/providers/{id}",
scope: "admin",
summary: "修改浏览器服务地址、访问凭据或启用(环境变量登记的只能改启用)",
params: browser.BrowserProviderParams,
body: browser.BrowserProviderUpdate,
response: browser.BrowserProviderView,
}),
probeProvider: ep({
method: "post",
path: "/browser/providers/{id}/probe",
scope: "admin",
summary: "测试连通:探测该浏览器服务的 /health 与 /openapi.json 并写回能力",
params: browser.BrowserProviderParams,
response: browser.BrowserProviderView,
}),
sessions: ep({
method: "get",
path: "/browser/sessions",
+29 -1
View File
@@ -240,8 +240,12 @@ export const BrowserProviderView = z.object({
baseUrl: z.string().nullable(),
/** 访问凭据的 secret 引用(明文永不出 API) */
secretRef: Id.nullable(),
/** env = 由 BROWSER_PROVIDER_URL / BROWSER_ACCESS_KEY 登记(地址与凭据只能改部署配置);null = 设置页登记 */
managedBy: z.enum(["env"]).nullable(),
/** 是否配置了访问凭据(secret 或环境变量) */
hasAccessKey: z.boolean(),
enabled: z.boolean(),
/** 最近一次声明/探测到的能力;verified 只由人工核验写入 config.verified */
/** 最近一次声明/探测到的能力;verified 只由人工核验写入(config.verified 或适配器内置的已核验版本表) */
capabilities: BrowserCapabilities.nullable(),
verifiedAt: Timestamp.nullable(),
healthStatus: InstanceHealth,
@@ -251,6 +255,30 @@ export const BrowserProviderView = z.object({
});
export type BrowserProviderView = z.infer<typeof BrowserProviderView>;
const HttpUrl = z
.string()
.url()
.refine((u) => /^https?:\/\//i.test(u), "只支持 http(s) 地址");
/** 设置页登记浏览器服务(camofox);accessKey 明文只在请求里出现一次,落库为 secret */
export const BrowserProviderCreate = z.object({
name: z.string().min(1).max(64),
baseUrl: HttpUrl,
accessKey: z.string().min(1).max(512).optional(),
enabled: z.boolean().optional(),
});
export type BrowserProviderCreate = z.infer<typeof BrowserProviderCreate>;
/** 改地址 / 凭据 / 启用;accessKey = null 清除凭据 */
export const BrowserProviderUpdate = z.object({
baseUrl: HttpUrl.optional(),
accessKey: z.string().min(1).max(512).nullable().optional(),
enabled: z.boolean().optional(),
});
export type BrowserProviderUpdate = z.infer<typeof BrowserProviderUpdate>;
export const BrowserProviderParams = z.object({ id: Id });
export const BrowserProvidersQuery = z.object({
/** true = 现场探测 /health 与 /openapi.json 并写回 */
probe: QueryBool,
+6 -1
View File
@@ -381,8 +381,10 @@ export const SystemProcess = z.object({
lastBeatAt: Timestamp,
/** 距上次心跳秒数 */
beatAgeSec: z.number().nonnegative(),
/** 超过 45s 没心跳 */
/** 超过 45s 没心跳(只对当前实例告警) */
stale: z.boolean(),
/** 进程正常退出时写入;非 null 即已下线 */
stoppedAt: Timestamp.nullable(),
/** 最近一次采样的事件循环延迟 */
eventLoopLagMs: NonNegInt,
/** 最近一个心跳周期(15s)内的最大延迟 */
@@ -434,7 +436,10 @@ export const SystemHealth = z.object({
checkedAt: Timestamp,
/** 处理本请求的 api 进程 */
api: z.object({ version: z.string(), startedAt: Timestamp, uptimeSec: z.number().nonnegative() }),
/** 当前实例:最近 10 分钟内有心跳的 host 上、同 host 同 kind 最新启动且未退出的进程;stale 与告警只看这里 */
processes: z.array(SystemProcess),
/** 已下线实例:已正常退出、所在 host 10 分钟没有心跳(容器已重建)、或被同 host 新进程替换;不计入 level */
retiredProcesses: z.array(SystemProcess),
sse: z.object({ connections: NonNegInt }),
db: z.object({
level: HealthLevel,