fix+logging: model load logging, CPU fallback, log level audit

Bugs fixed (from high-effort review):
- InsightFace CPU fallback now passes providers=['CPUExecutionProvider'] and
  wraps in _suppress_output() so broken GPU drivers don't cause fallback to
  try the same broken provider again, and C-extension noise stays suppressed
- scheduler.py: BaseException → Exception (KeyboardInterrupt already re-raised;
  winnow has no sys.exit() calls, so SystemExit would not occur, but Exception
  is the correct scope)
- compose.yml: fix inverted AUTO_MODE comment (docker run -it enables
  interactive mode via TTY, not non-interactive)

Model loading logging (embeddings.py):
- InsightFace: disk cache check, "not cached — downloading now (~300 MB)",
  "loading into memory on GPU/CPU...", "ready on GPU/CPU (Xs)"
- SigLIP: same treatment; cache path derived dynamically from model_name
  via HuggingFace slug convention (models--org--model) so it stays correct
  if the model variant ever changes

Logging level audit (INFO/DEBUG/WARNING/ERROR):
- diversity.py: internal algo steps (clustering, medoids, adaptive threshold,
  auto-stop decision) → DEBUG; final selection summaries stay INFO
- immich_api.py: "Fetching assets" and "Retained N assets" → DEBUG (callers
  already print this to the console via rprint)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

compose.yml

@@ -10,8 +10,8 @@ services:
 
       # ── Mode & Strategy ───────────────────────────────────────────────────
       # Auto mode is active by default when no TTY is present (Docker/cron).
-      # Run with `docker run -it` or set AUTO_MODE=true to force non-interactive
-      # in a terminal.
+      # Set AUTO_MODE=true to force auto mode in an interactive terminal.
+      # To run interactively: docker exec -it winnow winnow
       # TRAINING_MODE: face = upload to Frigate face recognition API
       #                object = save crops to output dir for manual Frigate placement
       - TRAINING_MODE=face