feat(pxpipe): PXPIPE token saver — multimodal prompt compression (#2465)

Add pxpipe as an experimental fifth Token Saver: Claude-format request
bodies above a configurable size threshold are rendered as dense PNGs
via the pxpipe-proxy library API (transformAnthropicMessages) before
dispatch, cutting estimated input tokens by ~35-60% on token-dense
contexts. Integration follows the Headroom pattern: applied to the final
body in chatCore just before dispatch, fail-open on any error/timeout.

Managed npm install into DATA_DIR/pxpipe, dynamic loader with per-version
cache-bust, JSONL event log with rotation, /api/pxpipe/* endpoints, Token
Saver card (marked experimental) + /dashboard/pxpipe page, and per-request
Activated/Skipped annotation in Request Details. Disabled by default.

src/app/api/pxpipe/logs/route.js

@@ -0,0 +1,18 @@
+import { NextResponse } from "next/server";
+import { getInstallLogTail } from "@/lib/pxpipe/install.js";
+import { readPxpipeEvents } from "@/lib/pxpipe/events.js";
+
+export const dynamic = "force-dynamic";
+
+export async function GET(request) {
+  try {
+    const { searchParams } = new URL(request.url);
+    const limit = Math.min(Number(searchParams.get("limit")) || 100, 500);
+    return NextResponse.json({
+      installLog: getInstallLogTail(),
+      events: readPxpipeEvents({ limit }).reverse(),
+    });
+  } catch (error) {
+    return NextResponse.json({ error: error.message }, { status: 500 });
+  }
+}