feat(health): System Health in three groups, a score that sees lag; admin user detail
Dashboard → System Health is grouped into AgentHub, Machine and Agent
activity. The machine (GET /api/host, every signed-in user) is drawn by
components/health/HostHealth.tsx: host card beside the CPU/memory history,
then CPU (threads as compact cells + temperatures/GPUs), disks & network,
busiest processes, and per-user tiles. Concurrency bars each show their own
agent type on hover.
The Health Score (client/src/lib/healthScore.ts) is now 100 minus what each
check costs, between an amber and a red threshold: event-loop p99
(server/lib/loop-delay.js, shared with /api/metrics), Linux PSI pressure for
CPU, memory and disk I/O (/api/host `pressure`; load per core without PSI),
RAM, the database's disk, V8 heap, hooks silent while agents work, and agent
errors in the last 24 h. All-time success rate, API errors and the transcript
cache hit rate no longer count. /api/settings/info adds server.event_loop and
activity {last_event_at, working_agents, agents_24h}.
Administration: a user row opens its detail in place (GET
/api/users/:id/details — spend, account pool share, live panes, workspaces,
newest sessions); the server panel is gone, member tmux folded into the table;
the Sessions list shows each row's owner in server mode.
This commit is contained in:
+159
-8
@@ -546,6 +546,83 @@ export type ServerUserUsage = AuthUser & {
|
||||
logins?: number;
|
||||
lastLoginAt?: string | null;
|
||||
};
|
||||
/** A priced slice of a user's spend (`GET /api/users/:id/details`). */
|
||||
export type UsageSlice = { key: string; cost: number; tokens: number; sessions: number };
|
||||
/** One pool account as one user's detail sees it: the account's totals and their share. */
|
||||
export type UserPoolAccount = {
|
||||
name: string;
|
||||
kind: string;
|
||||
email: string | null;
|
||||
expired: boolean;
|
||||
/** Their group/pin lets them run on it (false = they ran on it before). */
|
||||
allowed: boolean;
|
||||
pinned: boolean;
|
||||
quota: PoolAccount["quota"] | CodexPoolAccount["quota"];
|
||||
quotaPercent: number | null;
|
||||
full: boolean;
|
||||
livePanes: number;
|
||||
spend5h: number;
|
||||
spend7d: number;
|
||||
userSpend5h: number;
|
||||
userSpend7d: number;
|
||||
userTokens5h: number;
|
||||
userTokens7d: number;
|
||||
userRuns7d: number;
|
||||
userLivePanes: number;
|
||||
userLastAt: string | null;
|
||||
};
|
||||
/** `GET /api/users/:id/details` — the Administration page's user detail. */
|
||||
export type UserDetails = {
|
||||
user: AuthUser & { disabled: boolean; logins: number; lastLoginAt: string | null };
|
||||
sessions: { total: number; active: number; firstAt: string | null; lastAt: string | null };
|
||||
usage: {
|
||||
today: { cost: number; tokens: number };
|
||||
last7d: { cost: number; tokens: number };
|
||||
last30d: { cost: number; tokens: number };
|
||||
/** 30 local days, the oldest first. */
|
||||
daily: { date: string; cost: number; tokens: number }[];
|
||||
byTool: UsageSlice[];
|
||||
byModel: UsageSlice[];
|
||||
};
|
||||
workspaces: {
|
||||
id: number;
|
||||
title: string;
|
||||
cwd: string;
|
||||
tool: string;
|
||||
kind: string;
|
||||
branch: string | null;
|
||||
status: string;
|
||||
createdAt: string;
|
||||
sessions: number;
|
||||
lastActiveAt: string | null;
|
||||
livePanes: number;
|
||||
}[];
|
||||
panes: {
|
||||
id: string;
|
||||
laneId: number;
|
||||
laneTitle: string;
|
||||
laneCwd: string;
|
||||
tool: string;
|
||||
model: string | null;
|
||||
account: string | null;
|
||||
proxy: string | null;
|
||||
sessionId: string | null;
|
||||
startedAt: string;
|
||||
status: string;
|
||||
}[];
|
||||
recentSessions: (Session & { tokens?: number })[];
|
||||
pool: Partial<
|
||||
Record<
|
||||
PoolTool,
|
||||
{
|
||||
pin: string | null;
|
||||
group: { id: number; name: string } | null;
|
||||
accounts: UserPoolAccount[];
|
||||
}
|
||||
>
|
||||
>;
|
||||
audit: AuditEntry[];
|
||||
};
|
||||
/** One member's own tmux server (`GET /api/users/tmux`). */
|
||||
export interface MemberTmuxRow {
|
||||
id: number;
|
||||
@@ -578,6 +655,8 @@ export interface HostUsageGroup {
|
||||
kind: "user" | "host" | "system";
|
||||
userId?: number;
|
||||
username?: string;
|
||||
/** The user's display name, null when none is set (absent from an older server). */
|
||||
displayName?: string | null;
|
||||
/** % of the whole machine's CPU (100 = every core busy) over the sample. */
|
||||
cpu: number;
|
||||
/** Resident memory, bytes (shared pages count in every process). */
|
||||
@@ -587,13 +666,31 @@ export interface HostUsageGroup {
|
||||
/** Busiest processes, by the kernel's short name only. */
|
||||
top: { pid: number; name: string; cpu: number; memory: number }[];
|
||||
}
|
||||
/** One `/proc/pressure/<resource>` reading, in % of the window. */
|
||||
export interface HostPressure {
|
||||
some10: number;
|
||||
some60: number;
|
||||
full10: number;
|
||||
}
|
||||
|
||||
/** `GET /api/host` — hardware, load, disks and per-user usage. */
|
||||
export interface HostStats {
|
||||
at: string;
|
||||
hostname: string;
|
||||
os: { platform: string; release: string; distro: string | null; arch: string };
|
||||
uptime: number;
|
||||
cpu: { model: string | null; cores: number; load: number[] };
|
||||
/** When the machine booted (ISO); absent from an older server. */
|
||||
bootTime?: string;
|
||||
cpu: {
|
||||
model: string | null;
|
||||
/** Logical CPUs (threads). */
|
||||
cores: number;
|
||||
load: number[];
|
||||
/** Physical cores from /proc/cpuinfo; null when it cannot tell. */
|
||||
physicalCores?: number | null;
|
||||
/** Busy % of each logical CPU over the sample; [] off Linux. */
|
||||
perCore?: number[];
|
||||
};
|
||||
memory: { total: number; available: number; used: number; swapTotal: number; swapUsed: number };
|
||||
disks: {
|
||||
device: string;
|
||||
@@ -609,6 +706,46 @@ export interface HostStats {
|
||||
gpus: { name: string; utilization: number; memoryUsed: number; memoryTotal: number }[];
|
||||
/** null off Linux. */
|
||||
usage: { cpu: number; sampleMs: number; groups: HostUsageGroup[] } | null;
|
||||
/** Bytes/s per network interface over the sample (`lo` left out). */
|
||||
network?: { name: string; rx: number; tx: number }[];
|
||||
/** Bytes/s per whole disk over the sample. */
|
||||
diskIo?: { name: string; read: number; write: number }[];
|
||||
/** `/sys/class/hwmon` sensors; [] when none. */
|
||||
temperatures?: { chip: string; label: string; celsius: number }[];
|
||||
/** Linux PSI (`/proc/pressure/*`): % of the last 10 / 60 s tasks stalled on
|
||||
* each resource; null without PSI (or off Linux). */
|
||||
pressure?: {
|
||||
cpu: HostPressure | null;
|
||||
memory: HostPressure | null;
|
||||
io: HostPressure | null;
|
||||
} | null;
|
||||
/** The ten busiest processes machine-wide; `group` is a `HostUsageGroup` key. */
|
||||
topProcesses?: { pid: number; name: string; cpu: number; memory: number; group: string }[];
|
||||
/** The dashboard's own process. */
|
||||
process?: { pid: number; node: string; uptime: number; rss: number; heapUsed: number };
|
||||
}
|
||||
/** One point of `GET /api/host/history`. */
|
||||
export interface HostHistoryPoint {
|
||||
at: string;
|
||||
/** Machine CPU %, null when it could not be sampled. */
|
||||
cpu: number | null;
|
||||
/** Memory used, % of total. */
|
||||
memory: number | null;
|
||||
memoryUsed: number;
|
||||
swapUsed: number;
|
||||
load1: number | null;
|
||||
/** Per user id: CPU % and resident bytes (users with any use only). */
|
||||
users: Record<string, { cpu: number; memory: number }>;
|
||||
}
|
||||
export type HostHistoryRange = "1h" | "6h" | "24h";
|
||||
/** `GET /api/host/history` — kept in memory since the server started. */
|
||||
export interface HostHistory {
|
||||
range: HostHistoryRange;
|
||||
intervalMs: number;
|
||||
/** False when this server keeps no history (local mode, not Linux). */
|
||||
running: boolean;
|
||||
startedAt: string | null;
|
||||
points: HostHistoryPoint[];
|
||||
}
|
||||
|
||||
/** One user's home folder on disk (`GET /api/users/storage`); null = not measured. */
|
||||
@@ -1090,9 +1227,11 @@ export const api = {
|
||||
/** DELETE /api/me/avatar — back to the initials. */
|
||||
removeAvatar: () => request<MyAccount>("/me/avatar", { method: "DELETE" }),
|
||||
},
|
||||
/** GET /api/host — the Server tab: hardware and each user's CPU/memory share (staff). */
|
||||
/** GET /api/host — System Health's machine cards and the Administration users table's CPU/RAM (local mode, or staff). */
|
||||
host: {
|
||||
stats: () => request<HostStats>("/host"),
|
||||
history: (range: HostHistoryRange = "1h") =>
|
||||
request<HostHistory>(`/host/history?range=${range}`),
|
||||
},
|
||||
// ───────────────────────── Server mode staff views (routes/users.js) ─────────────────────────
|
||||
users: {
|
||||
@@ -1102,6 +1241,9 @@ export const api = {
|
||||
/** GET /api/users — every account with its recent usage (admin/analyst). */
|
||||
list: () =>
|
||||
request<{ users: ServerUserUsage[] }>(`/users?tz_offset=${new Date().getTimezoneOffset()}`),
|
||||
/** GET /api/users/:id/details — one account in full (admin/analyst). */
|
||||
details: (id: number) =>
|
||||
request<UserDetails>(`/users/${id}/details?tz_offset=${new Date().getTimezoneOffset()}`),
|
||||
/** GET /api/users/audit — staff reads of members' sessions and admins'
|
||||
* account changes, newest first. */
|
||||
audit: () => request<{ entries: AuditEntry[] }>("/users/audit"),
|
||||
@@ -2010,10 +2152,13 @@ export const api = {
|
||||
purged_agents: number;
|
||||
}>("/settings/cleanup", { method: "POST", body: JSON.stringify(params) }),
|
||||
gc: (body: { dryRun?: boolean } = {}) =>
|
||||
request<{ reaped: number[]; capped: { path: string; sizeBefore: number }[] }>("/workspaces/gc", {
|
||||
method: "POST",
|
||||
body: JSON.stringify(body),
|
||||
}),
|
||||
request<{ reaped: number[]; capped: { path: string; sizeBefore: number }[] }>(
|
||||
"/workspaces/gc",
|
||||
{
|
||||
method: "POST",
|
||||
body: JSON.stringify(body),
|
||||
}
|
||||
),
|
||||
},
|
||||
|
||||
// ─────────────────────────────── Workflows API ──────────────────────────────
|
||||
@@ -4288,7 +4433,10 @@ export const api = {
|
||||
/** GET /api/lanes/:id/memory — CLAUDE.md/AGENTS.md and Claude's auto memory, read-only. */
|
||||
memory: (id: number) => request<{ files: LaneMemoryFile[] }>(`/workspaces/${id}/memory`),
|
||||
update: (id: number, patch: Partial<Lane>) =>
|
||||
request<{ lane: Lane }>(`/workspaces/${id}`, { method: "PATCH", body: JSON.stringify(patch) }),
|
||||
request<{ lane: Lane }>(`/workspaces/${id}`, {
|
||||
method: "PATCH",
|
||||
body: JSON.stringify(patch),
|
||||
}),
|
||||
/**
|
||||
* POST /api/lanes/:id/stage — advance the pipeline stage.
|
||||
* @param id The lane id.
|
||||
@@ -4299,7 +4447,10 @@ export const api = {
|
||||
id: number,
|
||||
body: { stage: string; status?: string; evidence?: string; note?: string; result?: string }
|
||||
) =>
|
||||
request<{ lane: Lane }>(`/workspaces/${id}/stage`, { method: "POST", body: JSON.stringify(body) }),
|
||||
request<{ lane: Lane }>(`/workspaces/${id}/stage`, {
|
||||
method: "POST",
|
||||
body: JSON.stringify(body),
|
||||
}),
|
||||
/**
|
||||
* GET /api/lanes/:id/preflight?action=reset|remove|purge — read the
|
||||
* action-specific facts that a destructive request must echo as `expect`.
|
||||
|
||||
Reference in New Issue
Block a user