Link test report: PD hub has no measurable effect; adb push slowness is adbd-specific

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DDwfd6Ki8UfG4hK6W5YpJz

docs/ADB-IN-CAR.md

@@ -106,18 +106,17 @@ Tested with the tablet on the Orin, charging through the PD hub:
   165 MB debug APK install failed, and so will `flutter run`'s first install.
   The app's own traffic (small, 5 Hz) is unaffected so far.
 
-**The PD hub causes the packet loss.** With the tablet on a plain C-to-C cable
-straight to the Orin, ping loss is 0% at every size, even at 100 packets/s, and a
-raw one-way TCP transfer Orin → tablet runs at **~4.3 MB/s** with 4 retransmits
-in 20 MB.
+**Follow-up the same day: the hub is not the cause.** A replug later, the link
+tested clean through the PD hub with and without the charger, and on a plain
+cable: 0% loss up to 500 packets/s, 0 retransmits. The lossy state did not come
+back. Details: [link test report](impl/reports/LINK-TEST-2026-10-11.md).
 
-**adb push is still slow without the hub: ~0.14 MB/s, 175 retransmits in 20 MB**,
-against 4 for the raw transfer. Cause not found. A bulk transfer running beside a
-ping burst loses nothing, so it is not simply traffic in both directions.
+**adb push stays slow on a healthy link: ~0.14 MB/s**, with the Orin
+retransmitting ~220 segments per 20 MB, while the app's own TCP over the same
+link runs at 2–6 MB/s with none. Specific to the adbd connection; unexplained.
 
-Until both are understood, install at the desk over USB, and use the car path for
-`logcat`, `shell` and screenshots. The car still needs the PD hub to charge the
-tablet, so the hub, or its replacement, needs its own test.
+So: install at the desk over USB, and use the car path for `logcat`, `shell`,
+screenshots and `am start`.
 
 A test trap: commands started from `adb shell` on the tablet use Android's
 default network (WiFi), not the USB link. `nc 192.168.55.1 …` from there gets