Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
133 changes: 17 additions & 116 deletions apps/web/src/hooks/use-service-resources.ts
Original file line number Diff line number Diff line change
@@ -1,124 +1,25 @@
import { useMutation, useQuery, useQueryClient } from "@tanstack/react-query";

import { api } from "@/lib/api";
import type { ServiceResourcesResponse } from "../../../server/src/observability/service-resources";
import type { SubsystemHealthState } from "../../../server/src/observability/subsystem-tracker";

export type ResourceHealthState =
| "healthy"
| "degraded"
| "unavailable"
| "running"
| "idle"
| "disabled"
| "unknown";

export type ResourceSample = {
at: number;
serverCpuPercent: number;
serverRssBytes: number;
serverHeapBytes: number;
agentCpuPercent: number | null;
agentRssBytes: number | null;
hostLoad1: number;
subsystems: Record<string, SubsystemResourceSample>;
};

export type SubsystemResourceSample = {
p95DurationMs: number | null;
failures: number;
metadata: Record<string, number>;
};
export type {
ResourceSample,
ServiceResourcesResponse,
SubsystemResourceSample,
} from "../../../server/src/observability/service-resources";
export type { SubsystemSnapshot } from "../../../server/src/observability/subsystem-tracker";

export type SubsystemSnapshot = {
id: string;
label: string;
description: string;
state: ResourceHealthState;
statusReason: "failure" | "stale" | "stuck" | null;
expectedCadenceMs: number | null;
lastStartedAt: number | null;
lastCompletedAt: number | null;
lastSucceededAt: number | null;
lastFailedAt: number | null;
lastDurationMs: number | null;
p95DurationMs: number | null;
inFlight: number;
runs: number;
failures: number;
lastError: string | null;
metadata: Record<string, number>;
};

export type ServiceResourcesResponse = {
collectionEnabled: boolean;
generatedAt: number;
processStartedAt: number;
availableHistoryMs: number;
sampleIntervalMs: number;
overall: {
state: "healthy" | "degraded" | "unavailable" | "unknown";
reasons: Array<{ code: string; message: string }>;
};
capabilities: {
processTreeMetrics: "available" | "unsupported" | "error";
eventLoopMetrics: "available";
};
current: {
server: {
cpuPercent: number;
rssBytes: number;
heapUsedBytes: number;
heapTotalBytes: number;
externalBytes: number;
uptimeSeconds: number;
};
host: {
load1: number;
load5: number;
load15: number;
cpuCount: number;
totalMemoryBytes: number;
freeMemoryBytes: number;
};
agents: {
supported: boolean;
cpuPercent: number | null;
rssBytes: number | null;
processCount: number | null;
sampledAt: number | null;
error: string | null;
};
database: {
state: "healthy" | "unavailable" | "unknown";
latencyMs: number | null;
sampledAt: number | null;
pool: { total: number; idle: number; waiting: number; max: number };
};
eventLoop: { p95DelayMs: number };
http: {
requestsPerMinute: number;
inFlight: number;
errorRatePercent: number;
p95DurationMs: number | null;
};
workloads: {
runningAgents: number;
sseClients: number;
streams: number;
streamViewers: number;
terminalObservers: number;
terminalViewers: number;
scheduledJobs: number;
jobMonitors: number;
gitRefreshesInFlight: number;
uiEventsPublished: number;
uiWriteFailures: number;
terminalPolls: number;
terminalPollFailures: number;
};
};
subsystems: SubsystemSnapshot[];
series: ResourceSample[];
};
/**
* Every state the resource dashboard renders a badge for. `stateLabel` and
* `stateBadgeVariant` are called with both `subsystem.state` and
* `overall.state`, so this tracks both server unions rather than restating
* where they differ.
*/
export type ResourceHealthState =
| SubsystemHealthState
| ServiceResourcesResponse["overall"]["state"];

export type ResourceWindow = "15m" | "1h";

Expand Down
Loading