Notes: 2026-08-20 text wake_up CUDA failure + Retry-After verification

Incident record for the first level-2 wake failure (cumem allocator,
text hard-down ~16 min, container restart restored it) plus the
caller-side findings from remote-access testing: 503 Retry-After
verified present on every server path, and the model-alias 404 quirk.

Co-Authored-By: Claude <noreply@anthropic.com>

TODO.md

@@ -42,6 +42,9 @@ but did not wake models on request; the front door's real job. Design record:
 
 ## Housekeeping
 
+- [ ] 2026-08-20: first L2 wake failure (CUDA cumem error, text hard-down
+      ~16 min, restart fixed) — incident + follow-ups in
+      `NOTES-2026-08-20-wake-cuda-failure.md`.
 - [ ] Delete `Qwen3.6-35B-A3B-FP8.corrupt-20260817` (43 GB, in MODEL_ROOT)
       once the repaired FP8 copy is trusted.
 - [x] Old-stack leftovers removed 2026-08-17 before `git init`: nginx.conf,