Fold the brain and health screens into Home

Home is the one overview now: the brain graph flat across the top, the flow
switches, then the health sections. The /brain and /health routes and their
sidebar entries are gone.

- charts report their cursor and clicks, so hovering one filters the list
  beside it to that minute and a click pins it until Escape or Clear
- chart values round to about three significant digits, the legend mounts
  under the plot so it can wrap without leaving the card, and axis ticks
  shorten past a thousand
- the embedded brain leaves the wheel to the page rather than zooming
- number fields no longer draw their up/down spinner (NOTEPAD)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017MeiWk3Yq12n2pTvnQWYvt
This commit is contained in:
2026-08-17 00:17:14 +02:00
co-authored by Claude Fable 5
parent fe346ea7a3
commit affb0a5f8c
15 changed files with 835 additions and 592 deletions
@@ -0,0 +1,369 @@
import { useQuery, useQueryClient } from "@tanstack/react-query"
import { ChevronDown, ChevronRight, X } from "lucide-react"
import { useEffect, useState } from "react"
import type { EventRow, HistoryPoint } from "@/client"
import { UplotChart } from "@/components/Common/UplotChart"
import { useEngineEvents } from "@/components/Flow/liveStore"
import { PANEL_SECTION } from "@/components/Flow/SidePanel"
import { Button } from "@/components/ui/button"
import { cn, compact } from "@/lib/utils"
import {
ago,
auditQueryOptions,
CARD,
clock,
deadLetterQueryOptions,
failuresQueryOptions,
healthKeys,
minuteOf,
runsQueryOptions,
timeseriesQueryOptions,
} from "./queries"
/** How much of each list is shown while it is not tied to a moment. */
const RUNS_SHOWN = 15
const FAILURES_SHOWN = 25
/**
* A moment picked off a chart.
*
* Hovering previews it, so the list under the pointer scrubs along with the
* cursor. A click holds it: reading the list means moving the pointer off the
* chart, and a held moment ignores the cursor until it is released.
*/
function useMoment() {
const [hovered, setHovered] = useState<number | null>(null)
const [pinned, setPinned] = useState<number | null>(null)
useEffect(() => {
if (pinned === null) return
const release = (event: KeyboardEvent) => {
if (event.key === "Escape") setPinned(null)
}
window.addEventListener("keydown", release)
return () => window.removeEventListener("keydown", release)
}, [pinned])
return {
/** The minute the paired list is showing, or null for all of it. */
at: pinned ?? hovered,
pinned,
onCursor: setHovered,
onSelect: (ts: number | null) =>
setPinned((held) => (ts === null || ts === held ? null : ts)),
release: () => setPinned(null),
}
}
type Moment = ReturnType<typeof useMoment>
/** One chart, and the moment it hands to its list. */
function Chart({
title,
labels,
plots,
moment,
}: {
title: string
labels: string[]
plots: HistoryPoint[][]
moment: Moment
}) {
return (
<div
className={cn(
CARD,
"flex h-64 flex-col",
moment.pinned !== null && "border-primary",
)}
>
<div className="flex items-baseline justify-between gap-2">
<h2 className={PANEL_SECTION}>{title}</h2>
<span className="text-xs text-muted-foreground">
{moment.pinned !== null ? "Esc clears" : "click to pin"}
</span>
</div>
<UplotChart
labels={labels}
plots={plots}
empty="Nothing has run yet."
onCursor={moment.onCursor}
onSelect={moment.onSelect}
/>
</div>
)
}
/** What a list is showing, and the way back to all of it. */
function ListHeader({ title, moment }: { title: string; moment: Moment }) {
return (
<div className="flex min-h-6 flex-wrap items-center gap-2">
<h2 className={PANEL_SECTION}>{title}</h2>
{moment.at !== null ? (
<span className="text-xs text-muted-foreground">
{moment.pinned !== null ? "pinned to" : "showing"} {clock(moment.at)}
</span>
) : null}
{moment.pinned !== null ? (
<Button
variant="ghost"
size="sm"
className="-my-1 h-6 gap-1 px-2 text-xs"
onClick={moment.release}
>
<X className="size-3" />
Clear
</Button>
) : null}
</div>
)
}
function Failure({ event }: { event: EventRow }) {
const [open, setOpen] = useState(false)
const [first, ...rest] = event.detail.split("\n")
return (
<div className="border-b border-border py-2 last:border-0">
<button
type="button"
className="flex w-full items-start gap-2 text-left"
onClick={() => setOpen(!open)}
disabled={rest.length === 0}
>
{rest.length ? (
open ? (
<ChevronDown className="mt-0.5 size-4 shrink-0 text-muted-foreground" />
) : (
<ChevronRight className="mt-0.5 size-4 shrink-0 text-muted-foreground" />
)
) : (
<span className="size-4 shrink-0" />
)}
<span className="min-w-0 flex-1">
<span className="font-mono text-sm">
{event.node || event.flow || "engine"}
</span>
<span className="ml-2 text-sm text-muted-foreground">{first}</span>
</span>
<span className="shrink-0 text-xs text-muted-foreground">
{ago(event.ts)}
</span>
</button>
{open && rest.length ? (
<pre className="mt-2 max-h-64 overflow-auto rounded-md border border-border bg-muted/40 p-3 font-mono text-xs">
{rest.join("\n")}
</pre>
) : null}
</div>
)
}
/**
* What the engine has been doing, as charts over a day and the records behind
* them.
*
* The two charts each drive the list beside them: throughput picks the runs of
* a minute, failures and timing picks that minute's failures.
*/
export function HealthActivity() {
const live = useEngineEvents()
const queryClient = useQueryClient()
const runsAt = useMoment()
const failuresAt = useMoment()
const { data: series } = useQuery(timeseriesQueryOptions())
const { data: runs } = useQuery(runsQueryOptions())
const { data: failures } = useQuery(failuresQueryOptions())
const { data: audit } = useQuery(auditQueryOptions())
const { data: dead } = useQuery(deadLetterQueryOptions())
// Something just went wrong on the socket. The row for it is written on the
// collector's next flush, so the refetch waits that out rather than asking
// for a failure the database does not have yet.
//
// The newest event's minute, not the count: the count stops changing once the
// ring is full, and a per-event key would let a flapping node restart the
// timer forever without it ever firing.
const seen = live.length ? Math.floor(live[live.length - 1].ts / 60) : 0
useEffect(() => {
if (!seen) return
const timer = setTimeout(() => {
queryClient.invalidateQueries({ queryKey: healthKeys.events })
queryClient.invalidateQueries({ queryKey: healthKeys.summary })
}, 16000)
return () => clearTimeout(timer)
}, [seen, queryClient])
const points = series ?? []
const at = (
pick: (point: (typeof points)[number]) => number,
): HistoryPoint[] =>
points.map((point) => ({ ts: point.ts, value: pick(point) }))
const shownRuns =
runsAt.at === null
? (runs ?? []).slice(0, RUNS_SHOWN)
: (runs ?? []).filter((run) => minuteOf(run.started_at) === runsAt.at)
const shownFailures =
failuresAt.at === null
? (failures ?? []).slice(0, FAILURES_SHOWN)
: (failures ?? []).filter((event) => minuteOf(event.ts) === failuresAt.at)
return (
<>
<section className="grid gap-4 lg:grid-cols-2">
<Chart
title="Throughput per minute"
labels={["messages", "executions"]}
plots={[
at((point) => point.messages),
at((point) => point.executions),
]}
moment={runsAt}
/>
<Chart
title="Failures and timing (ms)"
labels={["errors", "avg", "lag"]}
plots={[
at((point) => point.errors),
at((point) => point.avg_ms),
at((point) => point.avg_lag_ms),
]}
moment={failuresAt}
/>
</section>
<section className="grid content-start gap-4 lg:grid-cols-2">
<div className="grid content-start gap-3">
<ListHeader title="Recent runs" moment={runsAt} />
<div
className={cn(
CARD,
// Capped rather than as long as it happens to be: the two lists
// sit side by side, and a filtered one is meant to be scrolled.
"max-h-96 overflow-y-auto",
runsAt.pinned !== null && "border-primary",
)}
data-testid="recent-runs"
>
{shownRuns.length ? (
shownRuns.map((run) => (
<div
key={run.id}
className="flex items-baseline gap-3 border-b border-border py-2 text-sm last:border-0"
>
<span className="min-w-0 flex-1 truncate font-mono">
{run.flow}
</span>
<span className="text-xs text-muted-foreground">
{run.source}
</span>
<span
className={
run.status === "error"
? "text-destructive"
: run.status === "ok"
? "text-status-success"
: "text-muted-foreground"
}
>
{run.status}
</span>
<span className="w-16 text-right text-muted-foreground">
{compact(run.duration_ms)} ms
</span>
<span className="w-16 text-right text-xs text-muted-foreground">
{ago(run.started_at)}
</span>
</div>
))
) : (
<p className="text-sm text-muted-foreground">
{runsAt.at === null
? "No runs recorded yet."
: "No run from this minute is in the recent list."}
</p>
)}
</div>
</div>
<div className="grid content-start gap-3">
<ListHeader title="Failures" moment={failuresAt} />
<div
className={cn(
CARD,
"max-h-96 overflow-y-auto",
failuresAt.pinned !== null && "border-primary",
)}
data-testid="failures"
>
{shownFailures.length ? (
shownFailures.map((event) => (
<Failure key={event.id} event={event} />
))
) : (
<p className="text-sm text-muted-foreground">
{failuresAt.at === null
? "Nothing has failed in the last day."
: "Nothing failed in this minute."}
</p>
)}
</div>
</div>
</section>
{dead?.length ? (
<section className="grid gap-3">
<h2 className={PANEL_SECTION}>Given up on</h2>
<div className={CARD}>
{dead.map((item) => (
<div
key={item.id}
className="flex items-baseline gap-3 border-b border-border py-2 text-sm last:border-0"
>
<span className="min-w-0 flex-1 truncate font-mono">
{item.node}
</span>
<span className="text-muted-foreground">{item.reason}</span>
<span className="text-xs text-muted-foreground">
{ago(item.ts)}
</span>
</div>
))}
</div>
</section>
) : null}
<section className="grid gap-3">
<h2 className={PANEL_SECTION}>Changes</h2>
<div className={CARD}>
{audit?.length ? (
audit.map((event) => (
<div
key={event.id}
className="flex items-baseline gap-3 border-b border-border py-2 text-sm last:border-0"
>
<span className="min-w-0 flex-1 truncate">
{event.actor} {event.detail}
{event.flow ? (
<span className="ml-1 font-mono text-muted-foreground">
{event.flow}
</span>
) : null}
</span>
<span className="shrink-0 text-xs text-muted-foreground">
{ago(event.ts)}
</span>
</div>
))
) : (
<p className="text-sm text-muted-foreground">
Nothing has changed yet.
</p>
)}
</div>
</section>
</>
)
}
@@ -0,0 +1,195 @@
import { useQuery } from "@tanstack/react-query"
import { Link } from "@tanstack/react-router"
import type { FlowRollup, HistoryPoint } from "@/client"
import { shape } from "@/components/Flow/MessageSparkline"
import { PANEL_SECTION } from "@/components/Flow/SidePanel"
import { Badge } from "@/components/ui/badge"
import { compact } from "@/lib/utils"
import {
ago,
CARD,
failuresQueryOptions,
flowRollupsQueryOptions,
summaryQueryOptions,
} from "./queries"
function Tile({
label,
value,
note,
}: {
label: string
value: string
note?: string
}) {
return (
<div className={CARD}>
<div className={PANEL_SECTION}>{label}</div>
<div className="mt-1 text-2xl">{value}</div>
{note ? (
<div className="text-xs text-muted-foreground">{note}</div>
) : null}
</div>
)
}
/** A flow's execution trend, drawn from the 60 slices the rollup carries. */
function Spark({ counts }: { counts: number[] }) {
const points: HistoryPoint[] = counts.map((value, index) => ({
ts: index,
value,
}))
if (points.every((point) => point.value === 0)) {
return <span className="text-xs text-muted-foreground">nothing yet</span>
}
const { line } = shape(points)
return (
<svg
viewBox="0 0 100 100"
preserveAspectRatio="none"
className="h-6 w-24 overflow-visible"
aria-hidden="true"
>
<path
d={line}
fill="none"
stroke="var(--chart-1)"
strokeWidth="1.5"
vectorEffect="non-scaling-stroke"
/>
</svg>
)
}
/**
* How the engine is doing, and how each flow has been doing for a day.
*
* The tiles are the standing state; the table below is the same day the charts
* cover, one row per flow.
*/
export function HealthOverview() {
const { data: summary } = useQuery(summaryQueryOptions())
const { data: flows } = useQuery(flowRollupsQueryOptions())
// Shares the list below's cache entry, for the one tile that dates them.
const { data: failures } = useQuery(failuresQueryOptions())
const queue = (summary?.queue ?? {}) as Record<string, number>
const degraded = summary?.status === "degraded"
return (
<>
<section className="grid gap-3">
<div className="flex items-center gap-3">
<h2 className={PANEL_SECTION}>Health</h2>
<Badge variant={degraded ? "destructive" : "secondary"}>
{degraded ? "Degraded" : "Running normally"}
</Badge>
</div>
{summary?.problems.length ? (
<p className="text-sm text-muted-foreground">
{summary.problems.join(" · ")}
</p>
) : null}
<div className="grid gap-3 sm:grid-cols-2 lg:grid-cols-5">
<Tile
label="Nodes"
value={String(summary?.nodes.total ?? 0)}
note={
summary?.nodes.error
? `${summary.nodes.error} failed to load`
: "all loaded"
}
/>
<Tile
label="Flows running"
value={`${summary?.flows.running ?? 0}/${summary?.flows.total ?? 0}`}
note={
summary?.flows.quarantined
? `${summary.flows.quarantined} quarantined`
: summary?.flows.paused
? `${summary.flows.paused} paused`
: "none paused"
}
/>
<Tile
label="Failures (24h)"
value={String(summary?.failures_24h ?? 0)}
note={
failures?.length
? `latest ${ago(failures[0].ts)}`
: "nothing recorded"
}
/>
<Tile
label="Queue in flight"
value={String(queue.pending ?? 0)}
note={`${queue.delayed ?? 0} waiting · ${queue.parked ?? 0} parked`}
/>
<Tile
label="Loop lag"
value={`${compact(summary?.loop_lag.ewma ?? 0)} ms`}
note={`peak ${compact(summary?.loop_lag.max_60s ?? 0)} ms in the last minute`}
/>
</div>
</section>
<section className="grid gap-3">
<h2 className={PANEL_SECTION}>Flow activity (24h)</h2>
<div className={`${CARD} overflow-x-auto`}>
<table className="w-full text-sm">
<thead className="text-xs text-muted-foreground">
<tr className="text-left">
<th className="pb-2 font-medium">Flow</th>
<th className="pb-2 font-medium">Executions</th>
<th className="pb-2 font-medium">Errors</th>
<th className="pb-2 font-medium">Avg</th>
<th className="pb-2 font-medium">Lag</th>
<th className="pb-2 font-medium">Trend</th>
</tr>
</thead>
<tbody>
{(flows ?? []).map((row: FlowRollup) => (
<tr key={row.flow} className="border-t border-border">
<td className="py-2">
<Link
to="/flows/$flowName"
params={{ flowName: row.flow }}
className="font-mono hover:underline"
>
{row.flow || "—"}
</Link>
</td>
<td className="py-2">{row.executions}</td>
<td className="py-2">
{row.errors ? (
<Badge variant="destructive">{row.errors} failed</Badge>
) : (
<span className="text-muted-foreground">none</span>
)}
</td>
<td className="py-2">{compact(row.avg_ms)} ms</td>
<td className="py-2">{compact(row.avg_lag_ms)} ms</td>
<td className="py-2">
<Spark counts={row.spark} />
</td>
</tr>
))}
{flows?.length === 0 ? (
<tr>
<td
colSpan={6}
className="py-6 text-center text-muted-foreground"
>
No flow has run in the last day.
</td>
</tr>
) : null}
</tbody>
</table>
</div>
</section>
</>
)
}
+99
View File
@@ -0,0 +1,99 @@
import { ObservabilityService } from "@/client"
/** The live view; anything older is the collector's rollups. */
export const HOURS = 24
/** Another tab can change things, and the engine fails flows on its own. */
const REFRESH = 30_000
/**
* How deep the run and failure lists are read.
*
* Deeper than they are shown: picking a minute off a chart filters these rows
* client-side, and a list holding only the newest handful would have nothing
* to find for any minute but the current one.
*
* ponytail: the runs endpoint caps at 200 and takes no time range, so a busy
* engine still only covers its last minute or so. A `since` parameter is what
* would let a moment on the chart reach the whole day.
*/
const RUN_DEPTH = 200
const EVENT_DEPTH = 100
export const healthKeys = {
all: ["observability"] as const,
summary: ["observability", "summary"] as const,
events: ["observability", "events"] as const,
}
/** The resting surface these screens are built from. */
export const CARD = "rounded-lg border border-border bg-card p-4 shadow-e1"
export const summaryQueryOptions = () => ({
queryKey: healthKeys.summary,
queryFn: () => ObservabilityService.readSummary(),
refetchInterval: 10_000,
})
export const timeseriesQueryOptions = () => ({
queryKey: ["observability", "timeseries", HOURS] as const,
queryFn: () => ObservabilityService.readTimeseries({ hours: HOURS }),
refetchInterval: REFRESH,
})
export const flowRollupsQueryOptions = () => ({
queryKey: ["observability", "flows", HOURS] as const,
queryFn: () => ObservabilityService.readFlowRollups({ hours: HOURS }),
refetchInterval: REFRESH,
})
export const runsQueryOptions = () => ({
queryKey: ["observability", "runs"] as const,
queryFn: () => ObservabilityService.readRuns({ limit: RUN_DEPTH }),
refetchInterval: REFRESH,
})
export const failuresQueryOptions = () => ({
queryKey: [...healthKeys.events, "failure"] as const,
queryFn: () =>
ObservabilityService.readEvents({ kind: "failure", limit: EVENT_DEPTH }),
refetchInterval: REFRESH,
})
export const auditQueryOptions = () => ({
queryKey: [...healthKeys.events, "audit"] as const,
queryFn: () => ObservabilityService.readEvents({ kind: "audit", limit: 15 }),
refetchInterval: REFRESH,
})
export const deadLetterQueryOptions = () => ({
queryKey: ["observability", "dead-letter"] as const,
queryFn: () => ObservabilityService.readDeadLetters({ limit: 20 }),
refetchInterval: REFRESH,
})
/** How long ago something happened, in the coarsest unit that still says it. */
export function ago(ts: string | number | null | undefined): string {
if (!ts) return "—"
const stamp = typeof ts === "number" ? ts * 1000 : Date.parse(ts)
const seconds = Math.max(0, (Date.now() - stamp) / 1000)
if (seconds < 90) return `${Math.round(seconds)}s ago`
if (seconds < 5400) return `${Math.round(seconds / 60)}m ago`
if (seconds < 172800) return `${Math.round(seconds / 3600)}h ago`
return `${Math.round(seconds / 86400)}d ago`
}
/**
* The minute a timestamp belongs to, as unix seconds.
*
* Minutes are the granularity the engine stores its metrics at, so this is
* also the finest moment a chart can be asked about.
*/
export const minuteOf = (ts: string) => Math.floor(Date.parse(ts) / 60000) * 60
/** A moment as a clock reading, which is how the charts label their axis. */
export const clock = (ts: number) =>
new Date(ts * 1000).toLocaleTimeString([], {
hour: "2-digit",
minute: "2-digit",
})