molecule-core/canvas/src/components/CommunicationOverlay.tsx
Hongming Wang 26b5b21238 Fix CommunicationOverlay rate-limit storm: cap fan-out + gate on visibility
User report 2026-05-04: 8+ workspace tenant (Design Director + 6 sub-agents
+ 3 standalones) saw sustained 429s in canvas console hitting
/workspaces/<id>/activity?limit=5. Server-side rate limit is 600 req/min/IP.

Three compounding issues in CommunicationOverlay:
1. Polled regardless of visibility — collapsed panel still hammered the API
2. 10s cadence — 6 req every 10s = 36 req/min from this overlay alone
3. Fan-out cap of 6 workspaces — scaled linearly with workspace count

Fix:
- Gate setInterval on `visible` (effect re-runs when collapsed/expanded)
- Cadence 10s → 30s
- Fan-out cap 6 → 3

Combined: ~36 req/min worst case → 6 req/min worst case (6x reduction),
0 req/min when collapsed.

Tests:
- Fan-out cap: 6 online nodes mounted → exactly 3 fetches (was 6)
- Offline gate: offline workspace never polled
- Cadence: timer at 10s = no new fetch; timer at 30s = next batch fires

Each test would fail if the corresponding dial regressed.

Follow-up (out of scope): structurally right fix is to consume the
WORKSPACE_ACTIVITY WS broadcast instead of polling per-workspace. Server
already publishes the events; canvas just isn't subscribing yet.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 03:18:42 -07:00

201 lines
8.0 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"use client";
import { useState, useEffect, useCallback, useRef } from "react";
import { useCanvasStore } from "@/store/canvas";
import { api } from "@/lib/api";
import { COMM_TYPE_LABELS } from "@/lib/design-tokens";
interface Communication {
id: string;
sourceId: string;
targetId: string;
sourceName: string;
targetName: string;
type: "a2a_send" | "a2a_receive" | "task_update";
summary: string;
status: string;
timestamp: string;
durationMs: number | null;
}
/**
* Overlay showing recent A2A communications between workspaces.
* Renders as a floating log panel that auto-updates.
*/
export function CommunicationOverlay() {
const [comms, setComms] = useState<Communication[]>([]);
const [visible, setVisible] = useState(true);
const selectedNodeId = useCanvasStore((s) => s.selectedNodeId);
const nodes = useCanvasStore((s) => s.nodes);
const nodesRef = useRef(nodes);
nodesRef.current = nodes;
const fetchComms = useCallback(async () => {
try {
// Fan-out cap: each polled workspace = 1 round-trip. The platform
// rate limits at 600 req/min/IP; combined with heartbeats + other
// canvas polling, every workspace polled here costs ~6 req/min
// (1 every 30s × 1 per workspace). Capping at 3 keeps this
// overlay's footprint at 18 req/min worst case — well under
// budget even with 8+ workspaces visible. Caught 2026-05-04 when
// a user with 8+ workspaces (Design Director + 6 sub-agents +
// 3 standalones) saw sustained 429s in canvas console.
const onlineNodes = nodesRef.current.filter((n) => n.data.status === "online");
const allComms: Communication[] = [];
for (const node of onlineNodes.slice(0, 3)) {
try {
const activities = await api.get<Array<{
id: string;
workspace_id: string;
activity_type: string;
source_id: string | null;
target_id: string | null;
summary: string | null;
status: string;
duration_ms: number | null;
created_at: string;
}>>(`/workspaces/${node.id}/activity?limit=5`);
for (const a of activities) {
if (a.activity_type === "a2a_send" || a.activity_type === "a2a_receive") {
const sourceNode = nodes.find((n) => n.id === (a.source_id || a.workspace_id));
const targetNode = nodes.find((n) => n.id === (a.target_id || ""));
allComms.push({
id: a.id,
sourceId: a.source_id || a.workspace_id,
targetId: a.target_id || "",
sourceName: sourceNode?.data.name || "Unknown",
targetName: targetNode?.data.name || "Unknown",
type: a.activity_type as Communication["type"],
summary: a.summary || "",
status: a.status,
timestamp: a.created_at,
durationMs: a.duration_ms,
});
}
}
} catch {
// Skip workspaces that fail
}
}
// Sort by timestamp, newest first, dedupe
const seen = new Set<string>();
const sorted = allComms
.sort((a, b) => b.timestamp.localeCompare(a.timestamp))
.filter((c) => {
if (seen.has(c.id)) return false;
seen.add(c.id);
return true;
})
.slice(0, 20);
setComms(sorted);
} catch {
// Silently handle API errors
}
}, []);
useEffect(() => {
// Gate polling on visibility — when the user collapses the overlay
// the data isn't being read, so the per-workspace fan-out becomes
// pure rate-limit overhead. Pre-fix this overlay polled regardless
// of whether the panel was shown, costing ~36 req/min from a
// hidden surface.
if (!visible) return;
fetchComms();
// 30s cadence (was 10s). At 3-workspace fan-out that's 6 req/min
// worst case from this overlay. Combined with heartbeats (~30/min)
// and other canvas polling, leaves ample headroom under the 600/
// min/IP server-side rate limit even at 8+ workspace tenants.
const interval = setInterval(fetchComms, 30000);
return () => clearInterval(interval);
}, [fetchComms, visible]);
if (!visible || comms.length === 0) {
return (
<button
type="button"
onClick={() => setVisible(true)}
aria-label="Show communications panel"
className="fixed top-16 right-4 z-30 px-3 py-1.5 bg-surface-sunken/90 border border-line/50 rounded-lg text-[10px] text-ink-mid hover:text-ink transition-colors"
>
<span aria-hidden="true"> </span>{comms.length > 0 ? `${comms.length} comms` : "Communications"}
</button>
);
}
return (
<div className="fixed top-16 right-4 z-30 w-[320px] max-h-[400px] bg-surface-sunken/95 border border-line/50 rounded-xl shadow-xl shadow-black/30 backdrop-blur-sm overflow-hidden">
<div className="flex items-center justify-between px-3 py-2 border-b border-line/60">
<div className="text-[10px] font-semibold text-ink-mid uppercase tracking-wider">
<span aria-hidden="true"> </span>Communications ({comms.length})
</div>
<button
type="button"
onClick={() => setVisible(false)}
aria-label="Close communications panel"
className="text-ink-soft hover:text-ink-mid text-xs"
>
<span aria-hidden="true"></span>
</button>
</div>
<div className="overflow-y-auto max-h-[350px] p-2 space-y-1">
{comms.map((c) => {
const isSelected = selectedNodeId === c.sourceId || selectedNodeId === c.targetId;
const typeColor = c.type === "a2a_send" ? "text-cyan-400" : c.type === "a2a_receive" ? "text-accent" : "text-warm";
const typeIcon = c.type === "a2a_send" ? "↗" : c.type === "a2a_receive" ? "↙" : "◆";
const statusIcon = c.status === "ok" ? "✓" : c.status === "error" ? "✕" : "⏱";
const statusColor = c.status === "ok" ? "text-good" : c.status === "error" ? "text-bad" : "text-warm";
const age = formatAge(c.timestamp);
return (
<div
key={c.id}
className={`rounded-lg px-2.5 py-1.5 text-[9px] border transition-all ${
isSelected
? "bg-blue-950/30 border-blue-800/40"
: "bg-surface-card/30 border-line/20 hover:bg-surface-card/50"
}`}
>
<div className="flex items-center justify-between gap-2">
<div className="flex items-center gap-1.5 min-w-0">
<span className={typeColor} aria-hidden="true">{typeIcon}</span>
<span className="sr-only">{COMM_TYPE_LABELS[c.type] ?? c.type}</span>
<span className="text-ink-mid font-medium truncate">
{c.sourceName}
</span>
<span className="text-ink-mid" aria-hidden="true"></span>
<span className="sr-only">to</span>
<span className="text-ink-mid truncate">{c.targetName}</span>
</div>
<div className="flex items-center gap-1 shrink-0">
<span className={statusColor} aria-hidden="true">{statusIcon}</span>
<span className="sr-only">{c.status}</span>
<span className="text-ink-mid">{age}</span>
</div>
</div>
{c.summary && (
<div className="text-ink-soft truncate mt-0.5 pl-4">{c.summary}</div>
)}
{c.durationMs && (
<div className="text-ink-mid pl-4">{c.durationMs}ms</div>
)}
</div>
);
})}
</div>
</div>
);
}
function formatAge(timestamp: string): string {
const diff = Date.now() - new Date(timestamp).getTime();
if (diff < 60000) return `${Math.floor(diff / 1000)}s`;
if (diff < 3600000) return `${Math.floor(diff / 60000)}m`;
if (diff < 86400000) return `${Math.floor(diff / 3600000)}h`;
return `${Math.floor(diff / 86400000)}d`;
}